publications | Michael Färber's Research Group

For complete and updated list, see my Google Scholar profile.

Selected publications.

2025

In-Context Learning for Information Extraction using Fully Synthetic Demonstrations

In XLLM@ACL, Vienna, Austria, 2025

Abs PDF

Large, high-quality annotated corpora remain scarce in document-level entity and relation extraction in zero-shot or few-shot settings. In this paper, we present a fully automatic, LLM-based pipeline for synthetic data generation and in-context learning for document-level entity and relation extraction. In contrast to existing approaches that rely on manually annotated demonstrations or direct zero-shot inference, our method combines synthetic data generation with retrieval-based in-context learning, using a reasoning-optimized language model. This allows us to build a high-quality demonstration database without manual annotation and to dynamically retrieve relevant examples at inference time. Based on our approach we produce a synthetic dataset of over 5k Wikipedia abstracts with approximately 59k entities and 30k relation triples. Finally, we evaluate in-context learning performance on the DocIE shared task, extracting entities and relations from long documents in a zero-shot setting. We find that in-context joint entity and relation extraction at document-level remains a challenging task, even for state-of-the-art large language models.
Natural Language Inference Fine-tuning for Scientific Hallucination Detection

In SDP@ACL, Vienna, Austria, 2025

Abs PDF

Modern generative Large Language Models (LLMs) are capable of generating text that sounds coherent and convincing, but are also prone to producing hallucinations, facts that contradict the world knowledge. Even in the case of Retrieval-Augmented Generation (RAG) systems, where relevant context is first retrieved and passed in the input, the generated facts can contradict or not be verifiable by the provided references. This has motivated SciHal 2025, a shared task that focuses on the detection of hallucinations for scientific content. The two subtasks focused on: (1) predicting whether a claim from a generated LLM answer is entailed, contradicted, or unverifiable by the used references; (2) predicting a fine-grained category of erroneous claims. Our best performing approach used an ensemble of fine-tuned encoder-only ModernBERT and DeBERTa-v3 models for classification. Out of nine competing teams, our approach achieved the first place in sub-task 1 and the second place in sub-task 2.
Paths to Causality: Finding Informative Subgraphs within Knowledge Graphs for Knowledge-Based Causal Discovery

Yuni Susanti, and Michael Färber

In KDD, 2025

Abs DOI PDF

Inferring causal relationships between variable pairs is crucial for understanding multivariate interactions in complex systems. Knowledge-based causal discovery—which involves inferring causal relationships by reasoning over the metadata of variables (e.g., names or textual context)—offers a compelling alternative to traditional methods that rely on observational data. However, existing methods using Large Language Models (LLMs) often produce unstable and inconsistent results, compromising their reliability for causal inference. To address this, we introduce a novel approach that integrates Knowledge Graphs (KGs) with LLMs to enhance knowledge-based causal discovery. Our approach identifies informative metapath-based subgraphs within KGs and further refines their selection using Learning-to-Rank models. The top-ranked subgraphs are then incorporated into zero-shot prompts, improving the effectiveness of LLMs in inferring the causal relationship. Extensive experiments on biomedical and open-domain datasets demonstrate that our method outperforms most baselines by up to 44.8 points in F1 scores, evaluated across diverse LLMs and KGs. Our code and datasets are available on GitHub.
Revisiting Projection-based Data Transfer for Cross-Lingual Named Entity Recognition in Low-Resource Languages

Andrei Politov, Oleh Shkalikov, René Jäkel, and 1 more author

In NoDaLiDa/Baltic-HLT, Tallinn, Estonia, 2025

Abs PDF

Cross-lingual Named Entity Recognition (NER) leverages knowledge transfer between languages to identify and classify named entities, making it particularly useful for low-resource languages. We show that the data-based cross-lingual transfer method is an effective technique for cross-lingual NER and can outperform multilingual language models for low-resource languages. This paper introduces two key enhancements to the annotation projection step in cross-lingual NER for low-resource languages. First, we explore refining word alignments using back-translation to improve accuracy. Second, we present a novel formalized projection approach of matching source entities with extracted target candidates. Through extensive experiments on two datasets spanning 57 languages, we demonstrated that our approach surpasses existing projection-based methods in low-resource settings. These findings highlight the robustness of projection-based data transfer as an alternative to model-based methods for cross-lingual named entity recognition in low-resource languages.
Predicting Company ESG Ratings from News Articles Using Multivariate Time-series Analysis

Tanja Aue, Adam Jatowt, and Michael Färber

In TempWeb@WWW, Sydney, Australia, 2025

Abs PDF

In recent years, corporate environmental, social, and governance (ESG) engagement has received significant public attention. As mandatory ESG reporting is increasingly adopted and investors place greater emphasis on sustainability in their decisions, the demand for transparent and reliable ESG ratings is growing. However, existing automatic approaches to ESG rating prediction remain limited. Many rely on traditional machine learning methods like random forests or social network analysis, rather than leveraging incoming news article streams and large multivariate time series data, which, for the first time, enables capturing the dynamic relationships between topics, sentiments, and events. In this paper, we propose a novel approach to predicting ESG ratings from news articles by uniquely combining multivariate time series construction with advanced deep learning techniques. We create an extensive dataset of 3.7 million news articles spanning three years and covering 3,000 U.S. companies, providing a robust foundation for training and evaluating our approach. Our approach achieves high accuracy and outperforms existing approaches, underscoring its potential as a scalable, data-driven solution for ESG rating prediction.
SimplifyMyText: An LLM-Based System for Inclusive Plain Language Text Simplification

Michael Färber, Parisa Aghdam, Kyuri Im, and 2 more authors

In ECIR, Lucca,Italy, 2025

Abs PDF

Text simplification is essential for making complex content accessible to diverse audiences who face comprehension challenges. Yet, the limited availability of simplified materials creates significant barriers to personal and professional growth and hinders social inclusion. Although researchers have explored various methods for automatic text simplification, none fully leverage large language models (LLMs) to offer tailored customization for different target groups and varying levels of simplicity. Moreover, despite its proven benefits for both consumers and organizations, the well-established practice of plain language remains underutilized. In this paper, we introduce https://simplifymytext.org, the first system designed to produce plain language content from multiple input formats, including typed text and file uploads, with flexible customization options for diverse audiences. We employ GPT-4 and Llama-3 and evaluate outputs across multiple metrics. Overall, our work contributes to research on automatic text simplification and highlights the importance of tailored communication in promoting inclusivity.
Explainable LiDAR 3D Point Cloud Segmentation and Clustering for Detecting Airplane-Generated Wind Turbulence

Zhan Qu, Shuzhou Yuan, Michael Färber, and 3 more authors

In KDD, Toronto, Canada, 2025

Abs PDF

Wake vortices—strong, coherent air turbulences created by aircrafts—pose a significant risk to aviation safety and therefore require accurate and reliable detection methods. In this paper, we present an advanced, explainable machine learning method that utilizes Light Detection and Ranging (LiDAR) data for effective wake vortex detection. Our method leverages a dynamic graph CNN (DGCNN) with semantic segmentation to partition a 3D LiDAR point cloud into meaningful segments. Further refinement is achieved through clustering techniques. A novel feature of our research is the use of a perturbation-based explanation technique, which clarifies the model’s decision-making processes for air traffic regulators and controllers, increasing transparency and building trust. Our experimental results, based on measured and simulated LiDAR scans compared against four baseline methods, underscore the effectiveness and reliability of our approach. This combination of semantic segmentation and clustering for real-time wake vortex tracking significantly advances aviation safety measures, ensuring that these are both effective and comprehensible.
ComplexTempQA: A 100m Dataset for Complex Temporal Question Answering

Raphael Gruber, Abdelrahman Abdallah, Michael Färber, and 1 more author

In EMNLP, Suzhou, China, 2025

Abs PDF

We introduce ComplexTempQA,a large-scale dataset consisting of over 100 million question-answer pairs designed to tackle the challenges in temporal question answering. ComplexTempQA significantly surpasses existing benchmarks in scale and scope. Utilizing Wikipedia and Wikidata, the dataset covers questions spanning over two decades and offers an unmatched scale. We introduce a new taxonomy that categorizes questions as attributes, comparisons, and counting questions, revolving around events, entities, and time periods, respectively. A standout feature of ComplexTempQA is the high complexity of its questions, which demand reasoning capabilities for answering such as across-time comparison, temporal aggregation, and multi-hop reasoning involving temporal event ordering and entity recognition. Additionally, each question is accompanied by detailed metadata, including specific time scopes, allowing for comprehensive evaluation of temporal reasoning abilities of large language models.
Graph-Guided Textual Explanation Generation Framework

Shuzhou Yuan, Jingyi Sun, Ran Zhang, and 4 more authors

, Suzhou, China, 2025

Abs

Natural language explanations (NLEs) are commonly used to provide plausible free-text explanations of a model’s reasoning about its predictions. However, recent work has questioned their faithfulness, as they may not accurately reflect the model’s internal reasoning process regarding its predicted answer. In contrast, highlight explanations–input fragments critical for the model’s predicted answers–exhibit measurable faithfulness. Building on this foundation, we propose G-Tex, a Graph-Guided Textual Explanation Generation framework designed to enhance the faithfulness of NLEs. Specifically, highlight explanations are first extracted as faithful cues reflecting the model’s reasoning logic toward answer prediction. They are subsequently encoded through a graph neural network layer to guide the NLE generation, which aligns the generated explanations with the model’s underlying reasoning toward the predicted answer. Experiments on T5 and BART using three reasoning datasets show that G-Tex improves NLE faithfulness by up to 12.18% compared to baseline methods. Additionally, G-Tex generates NLEs with greater semantic and lexical similarity to human-written ones. Human evaluations show that G-Tex can decrease redundant content and enhance the overall quality of NLEs. Our work presents a novel method for explicitly guiding NLE generation to enhance faithfulness, serving as a foundation for addressing broader criteria in NLE and generated text.
CoDy: Counterfactual Explainers for Dynamic Graphs

Zhan Qu, Daniel Gomm, and Michael Färber

, Vancouver, Canada, 2025

Abs PDF

Temporal Graph Neural Networks (TGNNs) are widely used to model dynamic systems where relationships and features evolve over time. Although TGNNs demonstrate strong predictive capabilities in these domains, their complex architectures pose significant challenges for explainability. Counterfactual explanation methods provide a promising solution by illustrating how modifications to input graphs can influence model predictions. To address this challenge, we present CoDy—Counterfactual Explainer for Dynamic Graphs—a model-agnostic, instance-level explanation approach that identifies counterfactual subgraphs to interpret TGNN predictions. CoDy employs a search algorithm that combines Monte Carlo Tree Search with heuristic selection policies, efficiently exploring a vast search space of potential explanatory subgraphs by leveraging spatial, temporal, and local event impact information. Extensive experiments against state-of-the-art factual and counterfactual baselines demonstrate CoDy’s effectiveness, with improvements of 16% in AUFSC+ over the strongest baseline. Our code is available at: https://github.com/daniel-gomm/CoDy
Hallucinations Can Improve Large Language Models in Drug Discovery

Shuzhou Yuan, and Michael Färber

2025

Abs PDF

Hallucinations in large language models (LLMs), plausible but factually inaccurate text, are often viewed as undesirable. However, recent work suggests that such outputs may hold creative potential. In this paper, we investigate whether hallucinations can improve LLMs on molecule property prediction, a key task in early-stage drug discovery. We prompt LLMs to generate natural language descriptions from molecular SMILES strings and incorporate these often hallucinated descriptions into downstream classification tasks. Evaluating seven instruction-tuned LLMs across five datasets, we find that hallucinations significantly improve predictive accuracy for some models. Notably, Falcon3-Mamba-7B outperforms all baselines when hallucinated text is included, while hallucinations generated by GPT-4o consistently yield the greatest gains between models. We further identify and categorize over 18,000 beneficial hallucinations, with structural misdescriptions emerging as the most impactful type, suggesting that hallucinated statements about molecular structure may increase model confidence. Ablation studies show that larger models benefit more from hallucinations, while temperature has a limited effect. Our findings challenge conventional views of hallucination as purely problematic and suggest new directions for leveraging hallucinations as a useful signal in scientific modeling tasks like drug discovery.
Large Physics Models: Towards a Collaborative Approach with Large Language Models and Foundation Models

Kristian G. Barman, Sascha Caron, Emily Sullivan, and 19 more authors

2025

Abs PDF

This paper outlines a roadmap for the development and evaluation of Large Physics Models (LPMs), tailored foundation models for physics. LPMs are proposed to integrate symbolic reasoning, physics-specific data processing, and interdisciplinary collaboration, enhancing research through development, evaluation, and philosophical reflection.

2024

Assessing Privacy Policies with AI: Ethical, Legal, and Technical Challenges

Irem Aydin, Hermann Diebel-Fischer, Vincent Freiberger, and 5 more authors

In AISyS, 2024

Abs PDF

The growing use of Machine Learning and Artificial Intelligence (AI), particularly Large Language Models (LLMs) like OpenAI’s GPT series, leads to disruptive changes across organizations. At the same time, there is a growing concern about how organizations handle personal data. Thus, privacy policies are essential for transparency in data processing practices, enabling users to assess privacy risks. However, these policies are often long and complex. This might lead to user confusion and consent fatigue, where users accept data practices against their interests, and abusive or unfair practices might go unnoticed. LLMss can be used to assess privacy policies for users automatically. In this interdisciplinary work, we explore the challenges of this approach in three pillars, namely technical feasibility, ethical implications, and legal compatibility of using LLMs to assess privacy policies. Our findings aim to identify potential for future research, and to foster a discussion on the use of LLM technologies for enabling users to fulfil their important role as decision-makers in a constantly developing AI-driven digital economy.
ML approaches for OTDR diagnoses in passive optical networks - event detection and classification: ways for ODN branch assignment

Michael Straub, Johannes Reber, Tarek Saier, and 7 more authors

J. Opt. Commun. Netw., 2024

Abs DOI PDF
Benefits of international collaboration in computer science: a case study of China, the European Union, and the United States

Alberto Gómez-Espés, Michael Färber, and Adam Jatowt

Scientometrics, 2024

Abs DOI PDF
Future Timelines: Extraction and Visualization of Future-related Content From News Articles

Juwal Regev, Adam Jatowt, and Michael Färber

In WSDM, 2024

Abs DOI PDF

In today’s rapidly evolving world, maintaining a comprehensiveoverview of the future landscape is essential for staying competitive and making informed decisions. However, given the largevolume of daily news, manually obtaining a thorough overview ofan entity’s future prospects is quite challenging. To address this, wepresent a system designed to automatically extract and summarizefuture-related information of a queried entity from news articles. Our approach utilizes a novel and publicly accessible multi-sourcedataset comprising 6,800 annotated sentences to fine-tune a language model to identify future-related sentences. We then use topicmodeling to extract the main topics from the data and rank themby relevance as well as present them on an interactive timeline. User evaluations have shown that the timelines and summariesour system produces are useful. The system is available as a webapplication at: https://chronicle2050.regevson.com.
Embedded Named Entity Recognition using Probing Classifiers

Nicholas Popovic, and Michael Färber

In EMNLP, Miami, FL, USA, 2024

Abs PDF

Streaming text generation has become a common way of increasing the responsiveness of language model powered applications, such as chat assistants. At the same time, extracting semantic information from generated text is a useful tool for applications such as automated fact checking or retrieval augmented generation. Currently, this requires either separate models during inference, which increases computational cost, or destructive fine-tuning of the language model. Instead, we propose an approach called EMBER which enables streaming named entity recognition in decoder-only language models without fine-tuning them and while incurring minimal additional computational cost at inference time. Specifically, our experiments show that EMBER maintains high token generation rates, with only a negligible decrease in speed of around 1% compared to a 43.64% slowdown measured for a baseline. We make our code and data available online1, including a toolkit2 for training, testing, and deploying efficient token classification models optimized for streaming text generation.
The Effects of Hallucinations in Synthetic Training Data for Relation Extraction

Steven Rogulsky, Nicholas Popovic, and Michael Färber

In KBC-LM@ISWC, Baltimore, USA, 2024

Abs PDF

Relation extraction is crucial for constructing knowledge graphs, with large high-quality datasets serving as the foundation for training, fine-tuning, and evaluating models. Generative data augmentation (GDA) is a common approach to expand such datasets. However, this approach often introduces hallucinations, such as spurious facts, whose impact on relation extraction remains underexplored. In this paper, we examine the effects of hallucinations on the performance of relation extraction on the document and sentence levels. Our empirical study reveals that hallucinations considerably compromise the ability of models to extract relations from text, with recall reductions between 19.1% and 39.2%. We identify that relevant hallucinations impair the model’s performance, while irrelevant hallucinations have a minimal impact. Additionally, we develop methods for the detection of hallucinations to improve data quality and model performance. Our approaches successfully classify texts as either ’hallucinated’ or ’clean,’ achieving high F1-scores of 83.8% and 92.2%. These methods not only assist in removing hallucinations but also help in estimating their prevalence within datasets, which is crucial for selecting high-quality data. Overall, our work confirms the profound impact of relevant hallucinations on the effectiveness of relation extraction models.
Knowledge Graph Structure as Prompt: Improving Small Language Models Capabilities for Knowledge-Based Causal Discovery

Yuni Susanti, and Michael Färber

In ISWC, Baltimore, MD, USA, 2024

Abs DOI PDF

Causal discovery aims to estimate causal structures among variables based on observational data. Large Language Models (LLMs) offer a fresh perspective to tackle the causal discovery problem by reasoning on the metadata associated with variables rather than their actual data values, an approach referred to as knowledge-based causal discovery. In this paper, we investigate the capabilities of Small Language Models (SLMs, defined as LLMs with fewer than 1 billion parameters) with prompt-based learning for knowledge-based causal discovery. Specifically, we present “KG Structure as Prompt”, a novel approach for integrating structural information from a knowledge graph, such as common neighbor nodes and metapaths, into prompt-based learning to enhance the capabilities of SLMs. Experimental results on three types of biomedical and open-domain datasets under few-shot settings demonstrate the effectiveness of our approach, surpassing most baselines and even conventional fine-tuning approaches trained on full datasets. Our findings further highlight the strong capabilities of SLMs: in combination with knowledge graphs and prompt-based learning, SLMs demonstrate the potential to surpass LLMs with larger number of parameters. Our code and datasets are available on GitHub.
AutoRDF2GML: Facilitating RDF Integration in Graph Machine Learning

Michael Färber, David Lamprecht, and Yuni Susanti

In ISWC, Baltimore, MD, USA, 2024

Abs DOI PDF

In this paper, we introduce AutoRDF2GML, a framework designed to convert RDF data into data representations tailored for graph machine learning tasks. AutoRDF2GML enables, for the first time, the creation of both content-based features—i.e., features based on RDF datatype properties—and topology-based features—i.e., features based on RDF object properties. Characterized by automated feature extraction, AutoRDF2GML makes it possible even for users less familiar with RDF and SPARQL to generate data representations ready for graph machine learning tasks, such as link prediction, node classification, and graph classification. Furthermore, we present four new benchmark datasets for graph machine learning, created from large RDF knowledge graphs using our framework. These datasets serve as valuable resources for evaluating graph machine learning approaches, such as graph neural networks. Overall, our framework effectively bridges the gap between the Graph Machine Learning and Semantic Web communities, paving the way for RDF-based machine learning applications.
GNNavi: Navigating the Information Flow in Large Language Models by Graph Neural Network

Shuzhou Yuan, Ercong Nie, Michael Färber, and 2 more authors

In ACL, Bangkok, Thailand, 2024

Abs DOI PDF

Large Language Models (LLMs) exhibit strong In-Context Learning (ICL) capabilities when prompts with demonstrations are used. However, fine-tuning still remains crucial to further enhance their adaptability. Prompt-based fine-tuning proves to be an effective fine-tuning method in low-data scenarios, but high demands on computing resources limit its practicality. We address this issue by introducing a prompt-based parameter-efficient finetuning (PEFT) approach. GNNAVI leverages insights into ICL’s information flow dynamics, which indicates that label words act in prompts as anchors for information propagation. GNNAVI employs a Graph Neural Network (GNN) layer to precisely guide the aggregation and distribution of information flow during the processing of prompts by hardwiring the desired information flow into the GNN. Our experiments on text classification tasks with GPT-2 and Llama2 show GNNAVI surpasses standard prompt-based fine-tuning methods in few-shot settings by updating just 0.2% to 0.5% of parameters. We compare GNNAVI with prevalent PEFT approaches, such as prefix tuning, LoRA and Adapter in terms of performance and efficiency. Our analysis reveals that GNNAVI enhances information flow and ensures a clear aggregation process.
GraSAME: Injecting Token-Level Structural Information to Pretrained Language Models via Graph-guided Self-Attention Mechanism

Shuzhou Yuan, and Michael Färber

In NAACL, Mexico City, Mexico, 2024

Abs DOI PDF

Pretrained Language Models (PLMs) benefit from external knowledge stored in graph structures for various downstream tasks. However, bridging the modality gap between graph structures and text remains a significant challenge. Traditional methods like linearizing graphs for PLMs lose vital graph connectivity, whereas Graph Neural Networks (GNNs) require cumbersome processes for integration into PLMs. In this work, we propose a novel graphguided self-attention mechanism, GraSAME. GraSAME seamlessly incorporates token-level structural information into PLMs without necessitating additional alignment or concatenation efforts. As an end-to-end, lightweight multimodal module, GraSAME follows a multitask learning strategy and effectively bridges the gap between graph and textual modalities, facilitating dynamic interactions between GNNs and PLMs. Our experiments on the graph-to-text generation task demonstrate that GraSAME outperforms baseline models and achieves results comparable to state-of-the-art (SOTA) models on WebNLG datasets. Furthermore, compared to SOTA models, GraSAME eliminates the need for extra pre-training tasks to adjust graph inputs and reduces the number of trainable parameters by over 100 million
KITspotlight: A System for Spotlighting Researchers in the Media

Michael Färber, Benjamin Zagoruiko, and Markus Wambach

In ICWE, Tampere, Finland, 2024

Abs DOI PDF

Academic institutions, such as universities, heavily rely on public relations and are therefore interested in media monitoring. However, tracking mentions of their researchers in news articles presents challenges, such as identifying affiliated personnel and their departments, and aggregating the extracted information. In this paper, we introduce KITspotlight, a novel system that automatically identifies researchers of the Karlsruhe Institute of Technology (KIT) in newspaper articles, associates these individuals with their departments, and presents this information visually. KITspotlight is tailored for department heads, administrative staff, and individual researchers, focusing either on the institution’s overall public visibility or on an individual researcher’s media presence. Based on an analysis of 2,280 articles over 12 months, our system provides a model for monitoring academic personnel at any research institution.
ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks

Bolei Ma, Ercong Nie, Shuzhou Yuan, and 4 more authors

In EACL, Malta, 2024

Abs PDF

Prompt-based methods have been successfully applied to multilingual pretrained language models for zero-shot cross-lingual understanding. However, most previous studies primarily focused on sentence-level classification tasks, and only a few considered token-level labeling tasks such as Named Entity Recognition (NER) and Part-of-Speech (POS) tagging. In this paper, we propose Token-Level Prompt Decomposition (TOPRO), which facilitates the prompt-based method for token-level sequence labeling tasks. The TOPRO method decomposes an input sentence into single tokens and applies one prompt template to each token. Our experiments on multilingual NER and POS tagging datasets demonstrate that TOPRO-based fine-tuning outperforms Vanilla fine-tuning and Prompt-Tuning in zero-shot cross-lingual transfer, especially for languages that are typologically different from the source language English. Our method also attains state-of-theart performance when employed with the mT5 model. Besides, our exploratory study in multilingual large language models shows that TOPRO performs much better than the current in-context learning method. Overall, the performance improvements show that TOPRO could potentially serve as a novel and simple benchmarking method for sequence labeling tasks
HyperPIE: Hyperparameter Information Extraction from Scientific Publications

Tarek Saier, Mayumi Ohta, Takuto Asakura, and 1 more author

In ECIR, Glasgow, UK, 2024

Abs DOI PDF

Automatic extraction of information from publications is key to making scientific knowledge machine readable at a large scale. The extracted information can, for example, facilitate academic search, decision making, and knowledge graph construction. An important type of information not covered by existing approaches is hyperparameters. In this paper, we formalize and tackle hyperparameter information extraction (HyperPIE) as an entity recognition and relation extraction task. We create a labeled data set covering publications from a variety of computer science disciplines. Using this data set, we train and evaluate BERT-based fine-tuned models as well as five large language models: GPT-3.5, GALACTICA, Falcon, Vicuna, and WizardLM. For fine-tuned models, we develop a relation extraction approach that achieves an improvement of 29% F1 over a state-of-the-art baseline. For large language models, we develop an approach leveraging YAML output for structured data extraction, which achieves an average improvement of 5.5% F1 in entity recognition over using JSON. With our best performing model we extract hyperparameter information from a large number of unannotated papers, and analyze patterns across disciplines. All our data and source code is publicly available at \urlhttps://github.com/IllDepence/hyperpie.
A Novel Machine Learning-based Equalizer for a Downstream 100G PAM-4 PON

Chen Shao, Elias G. Giacoumidis, Shi Li, and 4 more authors

In OFC, San Diego, CA, USA, 2024

Abs PDF

A frequency-calibrated SCINet (FC-SCINet) equalizer is proposed for downstream 100G PON with 28.7 dB path loss. At 5 km, FC-SCINet improves the BER by 88.87% compared to FFE and a 3-layer DNN with 10.57% lower complexity.
Advanced Equalization in 112 Gb/s Upstream PON Using a Novel Fourier Convolution-based Network

Chen Shao, Elias Giacoumidis, Patrick Matalla, and 6 more authors

2024

Abs PDF

This work presents FConvNet, a Fourier Convolution-based Network for equalization in upstream PON. It outperforms traditional equalizers in bit-error-rate and power efficiency, demonstrating potential for high-speed optical networks.
Machine Learning in Short-Reach Optical Systems: A Comprehensive Survey

Chen Shao, Elias Giacoumidis, Syed Moktacim Billah, and 6 more authors

2024

Abs PDF

This survey reviews the application of machine learning in short-reach optical systems. It categorizes ML techniques into traditional, convolutional, transformer-based, and Fourier-based models, highlighting their potential in tasks like equalization, fault detection, and bandwidth prediction, with a focus on PONs and hardware efficiency.
Implementation of an Open Chemistry Knowledge Base with a Semantic Wiki

Charlotte Neidiger, Tarek Saier, Kai Kühn, and 13 more authors

J. Cheminformatics, 2024

Abs DOI PDF

We present a concept for an open chemistry knowledge base that integrates research results into a collaboratively usable platform. To achieve this, we enhanced Semantic MediaWiki (SMW) with tools for capturing chemical structures in machine-readable formats and with data forms and models for standardized input and organization. These extensions enable effective comparison and contextual analysis of research within an expandable Wiki environment. The approach was demonstrated in the domain of CO2 reduction in homogeneous photocatalytic systems. Our work shows how subject-specific knowledge in chemistry can be collaboratively collected and managed by integrating cheminformatic tools into SMW, thereby providing a systematic, open alternative to commercial systems.
Incorporating Quantum Advantage in Quantum Circuit Generation through Genetic Programming

Christoph Stein, and Michael Färber

2024

Abs PDF

Designing efficient quantum circuits that leverage quantum advantage compared to classical computing has become increasingly critical. Genetic algorithms have shown potential in generating such circuits through artificial evolution. However, integrating quantum advantage into the fitness function of these algorithms remains unexplored. In this paper, we aim to enhance the efficiency of quantum circuit design by proposing two novel approaches for incorporating quantum advantage metrics into the fitness function of genetic algorithms.1 We evaluate our approaches based on the Bernstein-Vazirani Problem and the Unstructured Database Search Problem as test cases. The results demonstrate that our approaches not only improve the convergence speed of the genetic algorithm but also produce circuits comparable to expert-designed solutions. Our findings suggest that automated quantum circuit design using genetic algorithms that incorporate a measure of quantum advantage is a promising approach to accelerating the development of quantum algorithms.
Why Lift So Heavy? Slimming Large Language Models by Cutting Off the Layers

Shuzhou Yuan, Ercong Nie, Bolei Ma, and 1 more author

In IJCNN, Rome, Italy, 2024

Abs PDF

This paper investigates reducing the size of large language models (LLMs) by layer pruning. Surprisingly, removing layers can preserve or even improve performance in classification tasks, reducing model size significantly.

2023

Linked Papers With Code: The Latest in Machine Learning as an RDF Knowledge Graph

Michael Färber, and David Lamprecht

In ISWC, 2023

Abs PDF

In this paper, we introduce Linked Papers With Code (LPWC), an RDF knowledge graph that provides comprehensive, current information about almost 400,000 machine learning publications.
SemOpenAlex: The Scientific Landscape in 26 Billion RDF Triples

Michael Färber, David Lamprecht, Johan Krause, and 2 more authors

In ISWC, 2023

Abs PDF

We present SemOpenAlex, an extensive RDF knowledge graph that contains over 26 billion triples about scientific publications and their associated entities.
Biases in scholarly recommender systems: impact, prevalence, and mitigation

Michael Färber, Melissa Coutinho, and Shuzhou Yuan

Scientometrics, 2023

Abs DOI PDF
AI-Based OTDR Event Detection, Classification and Assignment to ODN Branches in Passive Optical Networks

Michael Straub, and others

Journal of Optical Communications and Networking, 2023

Abs

An AI-supported monitoring concept is demonstrated allowing detection and classification of events on OTDR traces with high precision and recall for application on a PON optical distribution network. We can also associate events with ODN branches by using deployment data of the PON topology.
Analyzing the impact of companies on AI research based on publications

Michael Färber, and Lazaros Tampakis

Scientometrics, 2023

Abs DOI PDF
A Full-Fledged Framework for Combining Entity Linking Systems and Components

Kristian Noullet, Ayoub Ourgani, and Michael Färber

In K-CAP, 2023

Abs DOI

In this paper, we propose a framework for combining entity linking methods, allowing multiple systems and their components to be used in combination to achieve optimal performance.
Linked Papers With Code: The Latest in Machine Learning as an RDF Knowledge Graph

Michael Färber, and David Lamprecht

In ISWC, Athens, Greece, 2023

Abs
A Full-fledged Commit Message Quality Checker Based on Machine Learning

David Faragó, Michael Färber, and Christian Petrov

In COMPSAC, Torino, Italy, 2023

Abs DOI
Ablesbarkeitsmesser: A System for Assessing the Readability of German Text

Florian Pickelmann, Michael Färber, and Adam Jatowt

In ECIR, Dublin, Ireland, 2023

Abs DOI
CoCon: A Data Set on Combined Contextualized Research Artifact Use

Tarek Saier, Youxiang Dong, and Michael Färber

In JCDL, 2023

Abs

We propose CoCon, a large scholarly data set reflecting the combined use of research artifacts in academic publications. The data set enables holistic analyses and provides a link prediction task for ’combined research artifact use prediction’.
Evaluating Generative Models for Graph-to-Text Generation

Shuzhou Yuan, and Michael Färber

In RANLP, 2023

Abs

This study evaluates generative models like GPT-3 and ChatGPT for graph-to-text generation in a zero-shot setting. The models are tested on AGENDA and WebNLG datasets, and their performance is compared with finetuned LLMs. While fluent outputs are achieved, challenges remain in handling semantic relationships and hallucination issues.
AI-based OTDR Event Detection, Classification and Assignment to ODN Branches in Passive Optical Networks

Robert Borkowski, Michael Färber, R. Bonk, and 1 more author

In ECOC, 2023

Abs DOI

This paper presents an AI-based approach for OTDR event detection, classification, and assignment to ODN branches in PONs. The method improves fault detection and maintenance efficiency in optical access networks.
Automatic Hint Generation

Adam Jatowt, Calvin Gehrer, and Michael Färber

In ICTIR, Taipei, Taiwan, 2023

Abs DOI

This paper introduces a new task: automatic hint generation to support learning and reasoning. A Wikipedia-based approach is proposed and evaluated, showing improved user performance compared to baseline hints.
Impact, Attention, Influence: Early Assessment of Autonomous Driving Datasets

Daniel Bogdoll, Jonas Hendl, Felix Schreyer, and 3 more authors

In ICCRE, 2023

Abs

This scientometric study proposes an Influence Score for early evaluation of autonomous driving datasets. It examines metadata and citation relations to predict dataset impact and guides dataset selection and design.
Measuring Variety, Balance, and Disparity: An Analysis of Media Coverage of the 2021 German Federal Election

Michael Färber, Jannik Schwade, and Adam Jatowt

2023

Abs

This paper introduces a framework to assess news diversity based on variety, balance, and disparity. Using over 26,000 headlines from the 2021 German election, it applies topic modeling and proposes a novel metric for disparity, contributing to automated media diversity analysis.
Vocab-Expander: A System for Creating Domain-Specific Vocabularies Based on Word Embeddings

Michael Färber, and Nicholas Popovic

In RANLP, 2023

Abs DOI

VOCAB-EXPANDER is an online tool for building domain-specific vocabularies using word embeddings and ConceptNet. It supports tasks in innovation management, education, and interdisciplinary communication through term expansion and graph-based visualization.
Theories About World Representations for the Internet of Things

Michael Färber, Yulia Svetashova, and Andreas Harth

In CARLA, 2023

Abs

This paper discusses intersubjectivity, symbol grounding, and dynamic ontologies as foundational components for modeling knowledge in IoT settings. It connects philosophical theories with practical implications in computer science.

2022

The Microsoft Academic Knowledge Graph enhanced: Author name disambiguation, publication classification, and embeddings

Michael Färber, and Lin Ao

Quant. Science Studies, 2022

Abs DOI PDF
The Green AI Ontology: An Ontology for Modeling the Energy Consumption of AI Models

Michael Färber, and David Lamprecht

In ISWC, Virtual Conference, Hangzhou, China, 2022

Abs
A Blocking-Based Approach to Enhance Large-Scale Reference Linking

Tarek Saier, Meng Luan, and Michael Färber

In LITE@JCDL, 2022

Abs
How does author affiliation affect preprint citation count?: analyzing citation bias at the institution and country level

Chifumi Nishioka, Michael Färber, and Tarek Saier

In JCDL, Cologne, Germany, 2022

Abs DOI
Few-Shot Document-Level Relation Extraction

Nicholas Popovic, and Michael Färber

In NAACL, Seattle, WA, United States, 2022

Abs DOI
AIFB-WebScience at SemEval-2022 Task 12: Relation Extraction First - Using Relation Extraction to Identify Entities

Nicholas Popovic, Walter Laurito, and Michael Färber

In SemEval@NAACL, 2022

Abs DOI
Which Publications’ Metadata Are in Which Bibliographic Databases? A System for Exploration

Michael Färber, Christoph Braun, Nicholas Popovic, and 2 more authors

In BIR@ECIR, Stavanger, Norway, 2022

Abs
Safety Aware Reinforcement Learning by Identifying Comprehensible Constraints in Expert Demonstrations

Leopold Müller, Lars Böcking, and Michael Färber

In SafeAI@AAAI, 2022

Abs
When to Use Which Neural Network? Finding the Right Neural Network Architecture for a Research Problem

Michael Färber, and Nicolas Weber

In SDU@AAAI, 2022

Abs
Explaining Convolutional Neural Networks by Tagging Filters

Anna Nguyen, Daniel Hagenmayer, Tobias Weller, and 1 more author

In AIMLAI@CIKM, 2022

Abs

This paper presents a method for explaining convolutional neural networks (CNNs) by tagging filters. The approach enhances the interpretability of CNNs and provides a clearer understanding of how filter activations relate to input features.
Sequence Labeling for Citation Field Extraction from Cyrillic Script References

Igor Shapiro, Tarek Saier, and Michael Färber

In SDU@AAAI, 2022

Abs

This paper presents a dataset and multilingual BERT-based model for citation field extraction from Cyrillic script references. The model significantly outperforms existing tools and contributes to multilingual scholarly data processing.

2021

The data set knowledge graph: Creating a linked open data source for data sets

Michael Färber, and David Lamprecht

Quant. Science Studies, 2021

Abs PDF
Cross-Lingual Citations in English Papers: A Large-Scale Analysis of Prevalence, Usage, and Impact

Tarek Saier, Michael Färber, and Tornike Tsereteli

International Journal on Digital Libraries, 2021

Abs PDF
Improving question answering for event-focused questions in temporal collections of news articles

Jiexin Wang, Adam Jatowt, Michael Färber, and 1 more author

Inf. Retr. J., 2021

Abs DOI PDF
Towards Full-Fledged Argument Search: A Framework for Extracting and Clustering Arguments from Unstructured Text

Michael Färber, and Anna Steyer

CoRR, 2021

Abs PDF
Are Investors Biased Against Women? Analyzing How Gender Affects Startup Funding in Europe

Michael Färber, and Alexander Klein

CoRR, 2021

Abs PDF
Recommending Datasets for Scientific Problem Descriptions

Michael Färber, and Ann-Kathrin Leisinger

In CIKM, Virtual Event, Queensland, Australia, 2021

Abs DOI
DataHunter: A System for Finding Datasets Based on Scientific Problem Descriptions

Michael Färber, and Ann-Kathrin Leisinger

In RecSys, Amsterdam, The Netherlands, 2021

Abs DOI
Quantifying Explanations of Neural Networks in E-Commerce Based on LRP

Anna Nguyen, Franz Krause, Daniel Hagenmayer, and 1 more author

In ECML-PKDD, Bilbao, Spain, 2021

Abs DOI
CLiT: Combining Linking Techniques for Everyone

Kristian Noullet, Samuel Printz, and Michael Färber

In ESWC, 2021

Abs DOI
Media Bias Everywhere? A Vision for Dealing with the Manipulation of Public Opinion

Michael Färber, and Frederic Bartscherer

In BIAS, Lucca, Italy, 2021

Abs DOI
C-Rex: A Comprehensive System for Recommending In-Text Citations with Explanations

Michael Färber, Vinzenz Zinecker, Isabela Bragaglia Cartus, and 2 more authors

In Sci-K@WWW, Virtual Event, Ljubljana, Slovenia, 2021

Abs DOI
Exploding TV Sets and Disappointing Laptops: Suggesting Interesting Content in News Archives Based on Surprise Estimation

Adam Jatowt, I-Chen Hung, Michael Färber, and 2 more authors

In ECIR, 2021

Abs DOI
Right for the Right Reasons: Making Image Classification Intuitively Explainable

Anna Nguyen, Adrian Oberföll, and Michael Färber

In ECIR, Virtual Event, 2021

Abs DOI
Identifying Used Methods and Datasets in Scientific Publications

Michael Färber, Alexander Albers, and Felix Schüber

In SDU@AAAI, 2021

Abs
Bootstrapping Multilingual Metadata Extraction: A Showcase in Cyrillic

Johan Krause, Igor Shapiro, Tarek Saier, and 1 more author

In SDP@NAACL, 2021

Abs DOI

Applications based on scholarly data are of ever increasing importance. This results in disadvantages for areas where high-quality data and compatible systems are not available, such as Cyrillic-script regions. This work showcases techniques for bootstrapping multilingual metadata extraction.
AWARE: An Ontology for Situational Awareness of Autonomous Vehicles in Manufacturing

Boulos El Asmar, Syrine Chelly, and Michael Färber

In CSKG@AAAI, 2021

Abs

AWARE is an ontology designed to represent situational awareness for autonomous transport robots in manufacturing. It integrates perceptions, decision logic, and environment context to support autonomy and reasoning.
Theories of Meaning for the Internet of Things

Michael Färber, Yulia Svetashova, and Andreas Harth

In Language, Cognition, and Mind, 2021

Abs DOI

This chapter explores foundational issues in knowledge representation for the Internet of Things, combining insights from epistemology, semantic theories, and computer science. It highlights the limitations of traditional ontologies and proposes a more dynamic, grounded, and intersubjective approach.

2020

Citation recommendation: approaches and datasets

Michael Färber, and Adam Jatowt

Int. J. Digit. Libr., 2020

Abs DOI PDF
unarXive: a large scholarly data set with publications’ full-text, annotated in-text citations, and links to metadata

Tarek Saier, and Michael Färber

Scientometrics, 2020

Abs DOI PDF
Analyzing the GitHub Repositories of Research Papers

Michael Färber

In JCDL, Virtual Event, China, 2020

Abs DOI
HybridCite: A Hybrid Model for Context-Aware Citation Recommendation

Michael Färber, and Ashwath Sampath

In JCDL, Virtual Event, China, 2020

Abs DOI
Who’s Behind That Website? Classifying Websites by the Degree of Commercial Intent

Michael Färber, Benjamin Scheer, and Frederic Bartscherer

In ICWE, Helsinki, Finland, 2020

Abs DOI
Annotating and Analyzing Biased Sentences in News Articles using Crowdsourcing

Sora Lim, Adam Jatowt, Michael Färber, and 1 more author

In LREC, Marseille, France, 2020

Abs
KORE 50^DYWC: An Evaluation Data Set for Entity Linking Based on DBpedia, YAGO, Wikidata, and Crunchbase

Kristian Noullet, Rico Mix, and Michael Färber

In LREC, Marseille, France, 2020

Abs
Answering Event-Related Questions over Long-Term News Article Archives

Jiexin Wang, Adam Jatowt, Michael Färber, and 1 more author

In ECIR, Lisbon, Portugal, 2020

Abs DOI
Semantic Modelling of Citation Contexts for Context-Aware Citation Recommendation

Tarek Saier, and Michael Färber

In ECIR, Lisbon, Portugal, 2020

Abs DOI
Neural Citation Recommendation: A Reproducibility Study

Michael Färber, Timo Klein, and Joan Sigloch

In BIR@ECIR, Lisbon, Portugal, 2020

Abs

2019

Linked Crunchbase: A Linked Data API and RDF Data Set About Innovative Companies

Michael Färber

CoRR, 2019

Abs PDF
The Microsoft Academic Knowledge Graph: A Linked Data Source with 8 Billion Triples of Scholarly Data

Michael Färber

In ISWC, Auckland, New Zealand, 2019

Abs DOI PDF
Identifying Twitter Bots Using a Convolutional Neural Network

Michael Färber, Agon Qurdina, and Lule Ahmedi

In CLEF, Lugano, Switzerland, 2019

Abs PDF
Determining How Citations Are Used in Citation Contexts

Michael Färber, and Ashwath Sampath

In TPDL, Oslo, Norway, 2019

Abs DOI PDF
Evaluating the Availability of Open Citation Data

Chifumi Nishioka, and Michael Färber

In BIRNDL@SIGIR, Paris, France, 2019

Abs PDF
Relational schemata for distributed SPARQL query processing

Victor Anthony Arrascue Ayala, Polina Koleva, Anas Alzogbi, and 6 more authors

In SBD@SIGMOD, Amsterdam, The Netherlands, 2019

Abs DOI PDF
ScholarSight: Visualizing Temporal Trends of Scientific Concepts

Michael Färber, Chifumi Nishioka, and Adam Jatowt

In JCDL, Champaign, IL, USA, 2019

Abs DOI PDF
Team Peter Brinkmann at SemEval-2019 Task 4: Detecting Biased News Articles Using Convolutional Neural Networks

Michael Färber, Agon Qurdina, and Lule Ahmedi

In SemEval@NAACL-HLT 2019, Minneapolis, MN, USA, 2019

Abs DOI PDF
Bibliometric-Enhanced arXiv: A Data Set for Paper-Based and Citation-Based Tasks

Tarek Saier, and Michael Färber

In BIR@ECIR, Cologne, Germany, 2019

Abs PDF
Finding Temporal Trends of Scientific Concepts

Michael Färber, and Adam Jatowt

In BIR@ECIR, Cologne, Germany, 2019

Abs PDF
PaperHunter: A System for Exploring Papers and Citation Contexts

Michael Färber, Ashwath Sampath, and Adam Jatowt

In ECIR, Cologne, Germany, 2019

Abs DOI PDF

2018

A Linked Data wrapper for CrunchBase

Michael Färber, Carsten Menne, and Andreas Harth

Semantic Web, 2018

Abs DOI PDF
Linked data quality of DBpedia, Freebase, OpenCyc, Wikidata, and YAGO

Michael Färber, Frederic Bartscherer, Carsten Menne, and 1 more author

Semantic Web, 2018

Abs DOI PDF
Which Knowledge Graph Is Best for Me?

Michael Färber, and Achim Rettinger

CoRR, 2018

Abs PDF
A High-Quality Gold Standard for Citation-based Tasks

Michael Färber, Alexander Thiemann, and Adam Jatowt

In LREC, Miyazaki, Japan, 2018

Abs PDF
PRoST: Distributed Execution of SPARQL Queries Using Mixed Partitioning Strategies

Matteo Cossu, Michael Färber, and Georg Lausen

In EDBT, Vienna, Austria, 2018

Abs DOI PDF
CITEWERTs: A System Combining Cite-Worthiness with Citation Recommendation

Michael Färber, Alexander Thiemann, and Adam Jatowt

In ECIR, Grenoble, France, 2018

Abs DOI PDF
To Cite, or Not to Cite? Detecting Citation Contexts in Text

Michael Färber, Alexander Thiemann, and Adam Jatowt

In ECIR, Grenoble, France, 2018

Abs DOI PDF
Linked data quality of DBpedia, Freebase, OpenCyc, Wikidata, and YAGO

Michael Färber, Frederic Bartscherer, Carsten Menne, and 1 more author

Semantic Web, 2018

DOI
Annotating Domain-Specific Texts with Babelfy: A Case Study

Michael Färber, Kristian Noullet, and Boulos El Asmar

In EYRE, 2018

Abs

This case study evaluates the performance of Babelfy for annotating domain-specific German texts. Results show that Babelfy achieves about 85% annotation accuracy, suggesting its viability for industrial applications.

2017

The xLiMe system: Cross-lingual and cross-modal semantic annotation, search and recommendation over live-TV, news and social media streams

Lei Zhang, Andreas Thalhammer, Achim Rettinger, and 3 more authors

Web Semantics, 2017

Abs DOI PDF
Semantic search for novel information

Michael Färber

2017

Abs

2016

XKnowSearch! Exploiting Knowledge Bases for Entity-based Cross-lingual Information Retrieval

Lei Zhang, Michael Färber, and Achim Rettinger

In Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, Indianapolis, Indiana, USA, 2016

Abs DOI PDF

In recent years, the amount of entities in large knowledge bases available on the Web has been increasing rapidly, making it possible to propose new ways of intelligent information access. Within the context of globalization, there is a clear need for techniques and systems that can enable multilingual and cross-lingual information access. In this paper, we present XKnowSearch!, a novel entity-based system for multilingual and cross-lingual information retrieval, which supports keyword search and also allows users to influence the search process according to their search intents. By leveraging the multilingual knowledge base on the Web, keyword queries and documents can be represented in their semantic forms, which can facilitate query disambiguation and expansion, and can also overcome the language barrier between queries and documents in different languages.
Exploiting Knowledge Bases for Multilingual and Cross-lingual Semantic Annotation and Search

Lei Zhang, Michael Färber, Andreas Thalhammer, and 2 more authors

In ISWC, Bethlehem, PA, USA, 2016

Abs

This paper presents X-LiSA, an infrastructure for multilingual and cross-lingual semantic annotation, and XKnowSearch!, a system for entity-based semantic search. These tools utilize large knowledge bases to improve cross-lingual access to information and semantic search through disambiguation and translation of keyword queries.

2015

Using a semantic wiki for technology forecast and technology monitoring

Michael Färber

Program, 2015

Abs DOI PDF

2014

Kuphi - an Investigation Tool for Searching for and via Semantic Relations

Michael Färber, Lei Zhang, and Achim Rettinger

In ESWC, Anissaras, Crete, Greece, 2014

Abs DOI PDF
xLiD-Lexica: Cross-lingual Linked Data Lexica

Lei Zhang, Michael Färber, and Achim Rettinger

In LREC, Reykjavik, Iceland, 2014

Abs PDF
Exploiting Semantic Annotations for Entity-based Information Retrieval

Lei Zhang, Michael Färber, Thanh Tran, and 1 more author

In ISWC, Riva del Garda, Italy, 2014

Abs PDF

2013

A Comparative Evaluation of Cross-Lingual Text Annotation Techniques

Lei Zhang, Achim Rettinger, Michael Färber, and 1 more author

In CLEF, 2013

Abs DOI PDF
Ontology-Supported Document Ranking for Novelty Search

Michael Färber

In ESWC, Montpellier, France, 2013

Abs DOI PDF
A semantic wiki for novelty search on documents

Michael Färber, and Achim Rettinger

In BIR, Delft, The Netherlands, 2013

Abs PDF