Bela Gipp

Timo Spinde, Manuel Plank, Jan-David Krieger et al.

Media coverage has a substantial effect on the public perception of events. Nevertheless, media outlets are often biased. One way to bias news articles is by altering the word choice. The automatic identification of bias by word choice is challenging, primarily due to the lack of a gold standard data set and high context dependencies. This paper presents BABE, a robust and diverse data set created by trained experts, for media bias research. We also analyze why expert labeling is essential within this domain. Our data set offers better annotation quality and higher inter-annotator agreement than existing work. It consists of 3,700 sentences balanced among topics and outlets, containing media bias labels on the word and sentence level. Based on our data, we also introduce a way to detect bias-inducing sentences in news articles automatically. Our best performing BERT-based model is pre-trained on a larger corpus consisting of distant labels. Fine-tuning and evaluating the model on our proposed supervised data set, we achieve a macro F1-score of 0.804, outperforming existing methods.

Jan Philip Wahle, Terry Ruas, Frederic Kirstein et al.

The recent success of large language models for text generation poses a severe threat to academic integrity, as plagiarists can generate realistic paraphrases indistinguishable from original work. However, the role of large autoregressive transformers in generating machine-paraphrased plagiarism and their detection is still developing in the literature. This work explores T5 and GPT-3 for machine-paraphrase generation on scientific articles from arXiv, student theses, and Wikipedia. We evaluate the detection performance of six automated solutions and one commercial plagiarism detection software and perform a human study with 105 participants regarding their detection performance and the quality of generated examples. Our results suggest that large models can rewrite text humans have difficulty identifying as machine-paraphrased (53% mean acc.). Human experts rate the quality of paraphrases generated by GPT-3 as high as original texts (clarity 4.0/5, fluency 4.2/5, coherence 3.8/5). The best-performing detection model (GPT-3) achieves a 66% F1-score in detecting paraphrases.

Martin Wessel, Tomáš Horych, Terry Ruas et al.

Although media bias detection is a complex multi-task problem, there is, to date, no unified benchmark grouping these evaluation tasks. We introduce the Media Bias Identification Benchmark (MBIB), a comprehensive benchmark that groups different types of media bias (e.g., linguistic, cognitive, political) under a common framework to test how prospective detection techniques generalize. After reviewing 115 datasets, we select nine tasks and carefully propose 22 associated datasets for evaluating media bias detection techniques. We evaluate MBIB using state-of-the-art Transformer techniques (e.g., T5, BART). Our results suggest that while hate speech, racial bias, and gender bias are easier to detect, models struggle to handle certain bias types, e.g., cognitive and political bias. However, our results show that no single technique can outperform all the others significantly. We also find an uneven distribution of research interest and resource allocation to the individual tasks in media bias. A unified benchmark encourages the development of more robust systems and shifts the current paradigm in media bias detection evaluation towards solutions that tackle not one but multiple media bias types simultaneously.

Jan Philip Wahle, Terry Ruas, Saif M. Mohammad et al.

DBLP is the largest open-access repository of scientific articles on computer science and provides metadata associated with publications, authors, and venues. We retrieved more than 6 million publications from DBLP and extracted pertinent metadata (e.g., abstracts, author affiliations, citations) from the publication texts to create the DBLP Discovery Dataset (D3). D3 can be used to identify trends in research activity, productivity, focus, bias, accessibility, and impact of computer science research. We present an initial analysis focused on the volume of computer science research (e.g., number of papers, authors, research activity), trends in topics of interest, and citation patterns. Our findings show that computer science is a growing research field (approx. 15% annually), with an active and collaborative researcher community. While papers in recent years present more bibliographical entries in comparison to previous decades, the average number of citations has been declining. Investigating papers' abstracts reveals that recent topic trends are clearly reflected in D3. Finally, we list further applications of D3 and pose supplemental research questions. The D3 dataset, our findings, and source code are publicly available for research purposes.

Timo Spinde, Jan-David Krieger, Terry Ruas et al.

Media has a substantial impact on the public perception of events. A one-sided or polarizing perspective on any topic is usually described as media bias. One of the ways how bias in news articles can be introduced is by altering word choice. Biased word choices are not always obvious, nor do they exhibit high context-dependency. Hence, detecting bias is often difficult. We propose a Transformer-based deep learning architecture trained via Multi-Task Learning using six bias-related data sets to tackle the media bias detection problem. Our best-performing implementation achieves a macro $F_{1}$ of 0.776, a performance boost of 3\% compared to our baseline, outperforming existing methods. Our results indicate Multi-Task Learning as a promising alternative to improve existing baseline models in identifying slanted reporting.

Jan-David Krieger, Timo Spinde, Terry Ruas et al.

Media bias is a multi-faceted construct influencing individual behavior and collective decision-making. Slanted news reporting is the result of one-sided and polarized writing which can occur in various forms. In this work, we focus on an important form of media bias, i.e. bias by word choice. Detecting biased word choices is a challenging task due to its linguistic complexity and the lack of representative gold-standard corpora. We present DA-RoBERTa, a new state-of-the-art transformer-based model adapted to the media bias domain which identifies sentence-level bias with an F1 score of 0.814. In addition, we also train, DA-BERT and DA-BART, two more transformer models adapted to the bias domain. Our proposed domain-adapted models outperform prior bias detection approaches on the same data.

Malte Ostendorff, Till Blume, Terry Ruas et al.

Document embeddings and similarity measures underpin content-based recommender systems, whereby a document is commonly represented as a single generic embedding. However, similarity computed on single vector representations provides only one perspective on document similarity that ignores which aspects make two documents alike. To address this limitation, aspect-based similarity measures have been developed using document segmentation or pairwise multi-class document classification. While segmentation harms the document coherence, the pairwise classification approach scales poorly to large scale corpora. In this paper, we treat aspect-based similarity as a classical vector similarity problem in aspect-specific embedding spaces. We represent a document not as a single generic embedding but as multiple specialized embeddings. Our approach avoids document segmentation and scales linearly w.r.t.the corpus size. In an empirical study, we use the Papers with Code corpus containing 157,606 research papers and consider the task, method, and dataset of the respective research papers as their aspects. We compare and analyze three generic document embeddings, six specialized document embeddings and a pairwise classification baseline in the context of research paper recommendations. As generic document embeddings, we consider FastText, SciBERT, and SPECTER. To compute the specialized document embeddings, we compare three alternative methods inspired by retrofitting, fine-tuning, and Siamese networks. In our experiments, Siamese SciBERT achieved the highest scores. Additional analyses indicate an implicit bias of the generic document embeddings towards the dataset aspect and against the method aspect of each research paper. Our approach of aspect-based document embeddings mitigates potential risks arising from implicit biases by making them explicit.

Jonas Becker, Jan Philip Wahle, Terry Ruas et al.

The growing prominence of large language models, such as GPT-4 and ChatGPT, has led to increased concerns over academic integrity due to the potential for machine-generated content and paraphrasing. Although studies have explored the detection of human- and machine-paraphrased content, the comparison between these types of content remains underexplored. In this paper, we conduct a comprehensive analysis of various datasets commonly employed for paraphrase detection tasks and evaluate an array of detection methods. Our findings highlight the strengths and limitations of different detection methods in terms of performance on individual datasets, revealing a lack of suitable machine-generated datasets that can be aligned with human expectations. Our main finding is that human-authored paraphrases exceed machine-generated ones in terms of difficulty, diversity, and similarity implying that automatically generated texts are not yet on par with human-level performance. Transformers emerged as the most effective method across datasets with TF-IDF excelling on semantically diverse corpora. Additionally, we identify four datasets as the most diverse and challenging for paraphrase detection.

Anastasia Zhukova, Lukas von Sperl, Christian E. Matt et al.

User experience (UX) is a part of human-computer interaction (HCI) research and focuses on increasing intuitiveness, transparency, simplicity, and trust for the system users. Most UX research for machine learning (ML) or natural language processing (NLP) focuses on a data-driven methodology. It engages domain users mainly for usability evaluation. Moreover, more typical UX methods tailor the systems towards user usability, unlike learning about the user needs first. This paper proposes a new methodology for integrating generative UX research into developing domain NLP applications. Generative UX research employs domain users at the initial stages of prototype development, i.e., ideation and concept evaluation, and the last stage for evaluating system usefulness and user utility. The methodology emerged from and is evaluated on a case study about the full-cycle prototype development of a domain-specific semantic search for daily operations in the process industry. A key finding of our case study is that involving domain experts increases their interest and trust in the final NLP application. The combined UX+NLP research of the proposed method efficiently considers data- and user-driven opportunities and constraints, which can be crucial for developing NLP applications.

Frederic Kirstein, Jan Philip Wahle, Terry Ruas et al.

Despite the recent success of multi-task learning and pre-finetuning for natural language understanding, few works have studied the effects of task families on abstractive text summarization. Task families are a form of task grouping during the pre-finetuning stage to learn common skills, such as reading comprehension. To close this gap, we analyze the influence of multi-task learning strategies using task families for the English abstractive text summarization task. We group tasks into one of three strategies, i.e., sequential, simultaneous, and continual multi-task learning, and evaluate trained models through two downstream tasks. We find that certain combinations of task families (e.g., advanced reading comprehension and natural language inference) positively impact downstream performance. Further, we find that choice and combinations of task families influence downstream performance more than the training scheme, supporting the use of task families for abstractive text summarization.

Terry Ruas, Jan Philip Wahle, Lennart Küll et al.

This paper presents CS-Insights, an interactive web application to analyze computer science publications from DBLP through multiple perspectives. The dedicated interfaces allow its users to identify trends in research activity, productivity, accessibility, author's productivity, venues' statistics, topics of interest, and the impact of computer science research on other fields. CS-Insightsis publicly available, and its modular architecture can be easily adapted to domains other than computer science.

Kia-Jüng Yang, Dominik Meier, Jiachen Zhao et al.

Large reasoning models (LRMs) generate chain-of-thought (CoT) traces before producing final outputs, introducing a dynamic internal state that may complicate control mechanisms such as refusal. Unlike instruction-tuned LLMs, where refusal is mediated by a single directional subspace, refusal in large reasoning models (LRMs) additionally depends on the CoT. In DeepSeek-R1-Distill-LLaMA-8B, activation steering reverses refusal in only 39% of cases when the CoT is kept fixed, but removing the CoT entirely increases this to 70%, indicating that the CoT actively reinforces refusal. In a two-stage intervention where the model regenerates its CoT under activation steering, refusal is reversed in 94% of cases, while the resulting CoT alone retains 48% of this effect even after steering is removed. This suggests that the CoT can carry and reconstruct the compliance signal independently. These findings indicate that refusal in LRMs is jointly encoded in residual stream activations and CoT. This joint activation makes LRM more robust against activation-level interventions alone, but exposes CoT to a possible alternative surface attack.

Philipp Scharpf, Moritz Schubotz, Howard S. Cohl et al.

Citation-based Information Retrieval (IR) methods for scientific documents have proven effective for IR applications, such as Plagiarism Detection or Literature Recommender Systems in academic disciplines that use many references. In science, technology, engineering, and mathematics, researchers often employ mathematical concepts through formula notation to refer to prior knowledge. Our long-term goal is to generalize citation-based IR methods and apply this generalized method to both classical references and mathematical concepts. In this paper, we suggest how mathematical formulas could be cited and define a Formula Concept Retrieval task with two subtasks: Formula Concept Discovery (FCD) and Formula Concept Recognition (FCR). While FCD aims at the definition and exploration of a 'Formula Concept' that names bundled equivalent representations of a formula, FCR is designed to match a given formula to a prior assigned unique mathematical concept identifier. We present machine learning-based approaches to address the FCD and FCR tasks. We then evaluate these approaches on a standardized test collection (NTCIR arXiv dataset). Our FCD approach yields a precision of 68% for retrieving equivalent representations of frequent formulas and a recall of 72% for extracting the formula name from the surrounding text. FCD and FCR enable the citation of formulas within mathematical documents and facilitate semantic search and question answering as well as document similarity assessments for plagiarism detection or recommender systems.

Moritz Schubotz, Ankit Satpute, Andre Greiner-Petter et al.

Small to medium-scale data science experiments often rely on research software developed ad-hoc by individual scientists or small teams. Often there is no time to make the research software fast, reusable, and open access. The consequence is twofold. First, subsequent researchers must spend significant work hours building upon the proposed hypotheses or experimental framework. In the worst case, others cannot reproduce the experiment and reuse the findings for subsequent research. Second, suppose the ad-hoc research software fails during often long-running computationally expensive experiments. In that case, the overall effort to iteratively improve the software and rerun the experiments creates significant time pressure on the researchers. We suggest making caching an integral part of the research software development process, even before the first line of code is written. This article outlines caching recommendations for developing research software in data science projects. Our recommendations provide a perspective to circumvent common problems such as propriety dependence, speed, etc. At the same time, caching contributes to the reproducibility of experiments in the open science workflow. Concerning the four guiding principles, i.e., Findability, Accessibility, Interoperability, and Reusability (FAIR), we foresee that including the proposed recommendation in a research software development will make the data related to that software FAIRer for both machines and humans. We exhibit the usefulness of some of the proposed recommendations on our recently completed research software project in mathematical information retrieval.

Florian Valentin Wunderlich, Lars Benedikt Kaesberg, Jan Philip Wahle et al.

Advances in inference methods have enabled language models to improve their predictions without additional training. These methods often prioritize raw performance over cost-effective compute usage. However, computational efficiency is key for real-world applications with resource constraints. We provide a systematic analysis of the inference scaling strategies self-consistency, self-refinement, multi-agent debate, and mixture-of-agents, to study their computational performance tradeoffs. We evaluate methods on two reasoning benchmarks (MMLU-Pro, BBH) and include extensive parameter configurations (e.g., scaling the number of parallel predictions, agents, and debate rounds) across different model sizes. Across 34 configurations and over 100 evaluations, we compute the Pareto-optimal front to select methods that achieve the best accuracy with the lowest computational budget. Notably, inference scaling improves accuracy by up to +7.1% points over chain-of-thought at the highest evaluated budgets (20x the CoT compute budget) on MMLU-Pro. With an equal computing budget, debate and mixture-of-agents outperform self-consistency by 1.3% and 2.7% points, respectively. While self-consistency saturates earlier, multi-agent gains persist, particularly on more complicated tasks. We identify a simple multi-agent design guideline: mixture-of-agents is most efficient when the number of parallel generations exceeds the number of sequential aggregations.

Jan Philip Wahle, Terry Ruas, Mohamed Abdalla et al.

Natural Language Processing (NLP) is poised to substantially influence the world. However, significant progress comes hand-in-hand with substantial risks. Addressing them requires broad engagement with various fields of study. Yet, little empirical work examines the state of such engagement (past or current). In this paper, we quantify the degree of influence between 23 fields of study and NLP (on each other). We analyzed ~77k NLP papers, ~3.1m citations from NLP papers to other papers, and ~1.8m citations from other papers to NLP papers. We show that, unlike most fields, the cross-field engagement of NLP, measured by our proposed Citation Field Diversity Index (CFDI), has declined from 0.58 in 1980 to 0.31 in 2022 (an all-time low). In addition, we find that NLP has grown more insular -- citing increasingly more NLP papers and having fewer papers that act as bridges between fields. NLP citations are dominated by computer science; Less than 8% of NLP citations are to linguistics, and less than 3% are to math and psychology. These findings underscore NLP's urgent need to reflect on its engagement with various fields.

Dennis Trautwein, Cornelius Ihle, Moritz Schubotz et al.

The promise of decentralized peer-to-peer (P2P) systems is fundamentally gated by the challenge of Network Address Translation (NAT) traversal, with existing solutions often reintroducing the very centralization they seek to avoid. This paper presents the first large-scale measurement study of a fully decentralized NAT traversal protocol, Direct Connection Upgrade through Relay (DCUtR), within the production libp2p-based InterPlanetary File System (IPFS) network. Drawing on over 4.4 million traversal attempts from 85,000+ distinct networks across 167 countries, we provide an empirical analysis of modern P2P connectivity. We establish a conditional success rate of $70\% \pm 7.1\%$ for the hole-punching stage, given that prerequisite relay reservation and public address discovery succeed, providing a crucial new benchmark for the field. Critically, we empirically challenge the long-held belief of UDP's superiority for NAT traversal, demonstrating that DCUtR's high-precision, RTT-based synchronization yields statistically indistinguishable success rates for both TCP and QUIC ($\sim70\%$). Our analysis further validates the protocol's design for permissionless environments by showing that success is independent of relay characteristics and that the mechanism is highly efficient, with $97.6\%$ of successful connections established on the first attempt. Building on this analysis, we propose a concrete roadmap of protocol enhancements aimed at achieving universal connectivity and contribute our complete dataset to foster further research in this domain.

Finn Schmidt, Jan Philip Wahle, Terry Ruas et al.

Automatic evaluation metrics are central to the development of machine translation systems, yet their robustness under domain shift remains unclear. Most metrics are developed on the Workshop on Machine Translation (WMT) benchmarks, raising concerns about their robustness to unseen domains. Prior studies that analyze unseen domains vary translation systems, annotators, or evaluation conditions, confounding domain effects with human annotation noise. To address these biases, we introduce a systematic multi-annotator Cross-Domain Error-Span-Annotation dataset (CD-ESA), comprising 18.8k human error span annotations across three language pairs, where we fix annotators within each language pair and evaluate translations of the same six translation systems across one seen news domain and two unseen technical domains. Using this dataset, we first find that automatic metrics appear surprisingly robust to domain-shifts at the segment level (up to 0.69 agreement), but this robustness largely disappears once we account for human label variation. Averaging annotations increases inter-annotator agreement by up to +0.11. Metrics struggle on the unseen chemical domain compared to humans (inter-annotator agreement of 0.78-0.83 vs. 0.96). We recommend comparing metric-human agreement against inter-annotator agreement, rather than comparing raw metric-human agreement alone, when evaluating across different domains.

Jan Philip Wahle, Bela Gipp, Terry Ruas

Current approaches in paraphrase generation and detection heavily rely on a single general similarity score, ignoring the intricate linguistic properties of language. This paper introduces two new tasks to address this shortcoming by considering paraphrase types - specific linguistic perturbations at particular text positions. We name these tasks Paraphrase Type Generation and Paraphrase Type Detection. Our results suggest that while current techniques perform well in a binary classification scenario, i.e., paraphrased or not, the inclusion of fine-grained paraphrase types poses a significant challenge. While most approaches are good at generating and detecting general semantic similar content, they fail to understand the intrinsic linguistic variables they manipulate. Models trained in generating and identifying paraphrase types also show improvements in tasks without them. In addition, scaling these models further improves their ability to understand paraphrase types. We believe paraphrase types can unlock a new paradigm for developing paraphrase models and solving tasks in the future.

Ivan Pluzhnikov, Ankit Satpute, Moritz Schubotz et al.

This paper presents a specialized methodology for digitizing and segmenting mathematical documents from zbMATH Open, a comprehensive database of mathematical literature, to enhance machine processing capabilities. Currently, approximately 831,000 documents exist only in scanned volumes, which makes them not machine-processable. Furthermore, these scans often span multiple pages or share pages with other documents and incorporate diverse typesetting techniques, posing challenges for automated processing. To address these issues, we evaluate various Optical Character Recognition (OCR) tools and document separation techniques, proposing an optimized pipeline that outperforms existing approaches. Our study identifies Mathpix as the most effective OCR tool for LaTeX conversion, demonstrating superior performance based on BLEU and Edit Distance metrics. For document separation, we fine-tune generative Large Language Models (LLMs) and integrate them into a Majority Voting framework, achieving 97.5% accuracy when providing the text of the document. Additionally, our method identifies the start and end indexes for 90.6% of the test dataset, with an accuracy of 98.4% on applicable cases, resulting in an overall accuracy of 89.1% on the entire dataset. This approach surpasses traditional baselines, including regular expressions, ChatGPT-4o, and computer vision-based techniques. As a practical outcome, we process 810,977 mathematical documents into machine-readable text and extract precise document boundaries for 721,288 documents in LaTeX format. These contributions significantly improve accessibility for mathematical information retrieval systems, machine learning models, and related applications.

Lars Benedikt Kaesberg, Terry Ruas, Jan Philip Wahle et al.

We present CiteAssist, a system to automate the generation of BibTeX entries for preprints, streamlining the process of bibliographic annotation. Our system extracts metadata, such as author names, titles, publication dates, and keywords, to create standardized annotations within the document. CiteAssist automatically attaches the BibTeX citation to the end of a PDF and links it on the first page of the document so other researchers gain immediate access to the correct citation of the article. This method promotes platform flexibility by ensuring that annotations remain accessible regardless of the repository used to publish or access the preprint. The annotations remain available even if the preprint is viewed externally to CiteAssist. Additionally, the system adds relevant related papers based on extracted keywords to the preprint, providing researchers with additional publications besides those in related work for further reading. Researchers can enhance their preprints organization and reference management workflows through a free and publicly available web interface.

Frederic Kirstein, Terry Ruas, Bela Gipp

Meeting summarization has become a critical task since digital encounters have become a common practice. Large language models (LLMs) show great potential in summarization, offering enhanced coherence and context understanding compared to traditional methods. However, they still struggle to maintain relevance and avoid hallucination. We introduce a multi-LLM correction approach for meeting summarization using a two-phase process that mimics the human review process: mistake identification and summary refinement. We release QMSum Mistake, a dataset of 200 automatically generated meeting summaries annotated by humans on nine error types, including structural, omission, and irrelevance errors. Our experiments show that these errors can be identified with high accuracy by an LLM. We transform identified mistakes into actionable feedback to improve the quality of a given summary measured by relevance, informativeness, conciseness, and coherence. This post-hoc refinement effectively improves summary quality by leveraging multiple LLMs to validate output quality. Our multi-LLM approach for meeting summarization shows potential for similar complex text generation tasks requiring robustness, action planning, and discussion towards a goal.

Anastasia Zhukova, Felix Hamborg, Karsten Donnay et al.

Cross-document coreference resolution (CDCR) identifies and links mentions of the same entities and events across related documents, enabling content analysis that aggregates information at the level of discourse participants. However, existing datasets primarily focus on event resolution and employ a narrow definition of coreference, which limits their effectiveness in analyzing diverse and polarized news coverage where wording varies widely. This paper proposes a revised CDCR annotation scheme of the NewsWCL50 dataset, treating coreference chains as discourse elements (DEs) and conceptual units of analysis. The approach accommodates both identity and near-identity relations, e.g., by linking "the caravan" - "asylum seekers" - "those contemplating illegal entry", allowing models to capture lexical diversity and framing variation in media discourse, while maintaining the fine-grained annotation of DEs. We reannotate the NewsWCL50 and a subset of ECB+ using a unified codebook and evaluate the new datasets through lexical diversity metrics and a same-head-lemma baseline. The results show that the reannotated datasets align closely, falling between the original ECB+ and NewsWCL50, thereby supporting balanced and discourse-aware CDCR research in the news domain.

Jonas Becker, Liang-Chih Yu, Shamsuddeen Hassan Muhammad et al.

Stance detection is an established task that classifies an author's attitude toward a specific target into categories such as Favor, Neutral, and Against. Beyond categorical stance labels, we leverage a long-established affective science framework to model stance along real-valued dimensions of valence (negative-positive) and arousal (calm-active). This dimensional approach captures nuanced affective states underlying stance expressions, enabling fine-grained stance analysis. To this end, we introduce DimStance, the first dimensional stance resource with valence-arousal (VA) annotations. This resource comprises 11,746 target aspects in 7,365 texts across five languages (English, German, Chinese, Nigerian Pidgin, and Swahili) and two domains (politics and environmental protection). To facilitate the evaluation of stance VA prediction, we formulate the dimensional stance regression task, analyze cross-lingual VA patterns, and benchmark pretrained and large language models under regression and prompting settings. Results show competitive performance of fine-tuned LLM regressors, persistent challenges in low-resource languages, and limitations of token-based generation. DimStance provides a foundation for multilingual, emotion-aware, stance analysis and benchmarking.

Ankit Satpute, Noah Giessing, Andre Greiner-Petter et al.

Large Language Models (LLMs) have demonstrated exceptional capabilities in various natural language tasks, often achieving performances that surpass those of humans. Despite these advancements, the domain of mathematics presents a distinctive challenge, primarily due to its specialized structure and the precision it demands. In this study, we adopted a two-step approach for investigating the proficiency of LLMs in answering mathematical questions. First, we employ the most effective LLMs, as identified by their performance on math question-answer benchmarks, to generate answers to 78 questions from the Math Stack Exchange (MSE). Second, a case analysis is conducted on the LLM that showed the highest performance, focusing on the quality and accuracy of its answers through manual evaluation. We found that GPT-4 performs best (nDCG of 0.48 and P@10 of 0.37) amongst existing LLMs fine-tuned for answering mathematics questions and outperforms the current best approach on ArqMATH3 Task1, considering P@10. Our Case analysis indicates that while the GPT-4 can generate relevant responses in certain instances, it does not consistently answer all questions accurately. This paper explores the current limitations of LLMs in navigating complex mathematical problem-solving. Through case analysis, we shed light on the gaps in LLM capabilities within mathematics, thereby setting the stage for future research and advancements in AI-driven mathematical reasoning. We make our code and findings publicly available for research: \url{https://github.com/gipplab/LLM-Investig-MathStackExchange}

Jan Philip Wahle, Krishnapriya Vishnubhotla, Bela Gipp et al.

Work in Computational Affective Science and Computational Social Science explores a wide variety of research questions about people, emotions, behavior, and health. Such work often relies on language data that is first labeled with relevant information, such as the use of emotion words or the age of the speaker. Although many resources and algorithms exist to enable this type of labeling, discovering, accessing, and using them remains a substantial impediment, particularly for practitioners outside of computer science. Here, we present the ABCDE dataset (Affect, Body, Cognition, Demographics, and Emotion), a large-scale collection of over 400 million text utterances drawn from social media, blogs, books, and AI-generated sources. The dataset is annotated with a wide range of features relevant to computational affective and social science. ABCDE facilitates interdisciplinary research across numerous fields, including affective science, cognitive science, the digital humanities, sociology, political science, and computational linguistics.

Dominik Meier, Jan Philip Wahle, Terry Ruas et al.

Paraphrases represent a human's intuitive ability to understand expressions presented in various different ways. Current paraphrase evaluations of language models primarily use binary approaches, offering limited interpretability of specific text changes. Atomic paraphrase types (APT) decompose paraphrases into different linguistic changes and offer a granular view of the flexibility in linguistic expression (e.g., a shift in syntax or vocabulary used). In this study, we assess the human preferences towards ChatGPT in generating English paraphrases with ten APTs and five prompting techniques. We introduce APTY (Atomic Paraphrase TYpes), a dataset of 800 sentence-level and word-level annotations by 15 annotators. The dataset also provides a human preference ranking of paraphrases with different types that can be used to fine-tune models with RLHF and DPO methods. Our results reveal that ChatGPT and a DPO-trained LLama 7B model can generate simple APTs, such as additions and deletions, but struggle with complex structures (e.g., subordination changes). This study contributes to understanding which aspects of paraphrasing language models have already succeeded at understanding and what remains elusive. In addition, we show how our curated datasets can be used to develop language models with specific linguistic capabilities.

Baraa Hikal, Jonas Becker, Bela Gipp

This paper describes LogSigma, our system for SemEval-2026 Task 3: Dimensional Aspect-Based Sentiment Analysis (DimABSA). Unlike traditional Aspect-Based Sentiment Analysis (ABSA), which predicts discrete sentiment labels, DimABSA requires predicting continuous Valence and Arousal (VA) scores on a 1-9 scale. A central challenge is that Valence and Arousal differ in prediction difficulty across languages and domains. We address this using learned homoscedastic uncertainty, where the model learns task-specific log-variance parameters to automatically balance each regression objective during training. Combined with language-specific encoders and multi-seed ensembling, LogSigma achieves 1st place on five datasets across both tracks. The learned variance weights vary substantially across languages due to differing Valence-Arousal difficulty profiles-from 0.66x for German to 2.18x for English-demonstrating that optimal task balancing is language-dependent and cannot be determined a priori.

Jonas Becker, Lars Benedikt Kaesberg, Niklas Bauer et al.

Multi-agent debate (MAD) has demonstrated the ability to augment collective intelligence by scaling test-time compute and leveraging expertise. Current frameworks for multi-agent debate are often designed towards tool use, lack integrated evaluation, or provide limited configurability of agent personas, response generators, discussion paradigms, and decision protocols. We introduce MALLM (Multi-Agent Large Language Models), an open-source framework that enables systematic analysis of MAD components. MALLM offers more than 144 unique configurations of MAD, including (1) agent personas (e.g., Expert, Personality), (2) response generators (e.g., Critical, Reasoning), (3) discussion paradigms (e.g., Memory, Relay), and (4) decision protocols (e.g., Voting, Consensus). MALLM uses simple configuration files to define a debate. Furthermore, MALLM can load any textual Hugging Face dataset (e.g., MMLU-Pro, WinoGrande) and provides an evaluation pipeline for easy comparison of MAD configurations. MALLM enables researchers to systematically configure, run, and evaluate debates for their problems, facilitating the understanding of the components and their interplay.

Tianyu Yang, Terry Ruas, Yijun Tian et al.

Vision-language models (VLMs) excel at interpreting text-rich images but struggle with long, visually complex documents that demand analysis and integration of information spread across multiple pages. Existing approaches typically rely on fixed reasoning templates or rigid pipelines, which force VLMs into a passive role and hinder both efficiency and generalization. We present Active Long-DocumEnt Navigation (ALDEN), a multi-turn reinforcement learning framework that fine-tunes VLMs as interactive agents capable of actively navigating long, visually rich documents. ALDEN introduces a novel fetch action that directly accesses the page by index, complementing the classic search action and better exploiting document structure. For dense process supervision and efficient training, we propose a rule-based cross-level reward that provides both turn- and token-level signals. To address the empirically observed training instability caused by numerous visual tokens from long documents, we further propose a visual-semantic anchoring mechanism that applies a dual-path KL-divergence constraint to stabilize visual and textual representations separately during training. Trained on a corpus constructed from three open-source datasets, ALDEN achieves state-of-the-art performance on five long-document benchmarks. Overall, ALDEN marks a step beyond passive document reading toward agents that autonomously navigate and reason across long, visually rich documents, offering a robust path to more accurate and efficient long-document understanding.

Timo Spinde, Kanishka Sinha, Norman Meuschke et al.

We present a free and open-source tool for creating web-based surveys that include text annotation tasks. Existing tools offer either text annotation or survey functionality but not both. Combining the two input types is particularly relevant for investigating a reader's perception of a text which also depends on the reader's background, such as age, gender, and education. Our tool caters primarily to the needs of researchers in the Library and Information Sciences, the Social Sciences, and the Humanities who apply Content Analysis to investigate, e.g., media bias, political communication, or fake news.

Malte Ostendorff, Elliott Ash, Terry Ruas et al.

Recommender systems assist legal professionals in finding relevant literature for supporting their case. Despite its importance for the profession, legal applications do not reflect the latest advances in recommender systems and representation learning research. Simultaneously, legal recommender systems are typically evaluated in small-scale user study without any public available benchmark datasets. Thus, these studies have limited reproducibility. To address the gap between research and practice, we explore a set of state-of-the-art document representation methods for the task of retrieving semantically related US case law. We evaluate text-based (e.g., fastText, Transformers), citation-based (e.g., DeepWalk, Poincaré), and hybrid methods. We compare in total 27 methods using two silver standards with annotations for 2,964 documents. The silver standards are newly created from Open Case Book and Wikisource and can be reused under an open license facilitating reproducibility. Our experiments show that document representations from averaged fastText word vectors (trained on legal corpora) yield the best results, closely followed by Poincaré citation embeddings. Combining fastText and Poincaré in a hybrid manner further improves the overall result. Besides the overall performance, we analyze the methods depending on document length, citation count, and the coverage of their recommendations. We make our source code, models, and datasets publicly available at https://github.com/malteos/legal-document-similarity/.

Jan Philip Wahle, Terry Ruas, Tomáš Foltýnek et al.

Employing paraphrasing tools to conceal plagiarized text is a severe threat to academic integrity. To enable the detection of machine-paraphrased text, we evaluate the effectiveness of five pre-trained word embedding models combined with machine-learning classifiers and eight state-of-the-art neural language models. We analyzed preprints of research papers, graduation theses, and Wikipedia articles, which we paraphrased using different configurations of the tools SpinBot and SpinnerChief. The best-performing technique, Longformer, achieved an average F1 score of 81.0% (F1=99.7% for SpinBot and F1=71.6% for SpinnerChief cases), while human evaluators achieved F1=78.4% for SpinBot and F1=65.6% for SpinnerChief cases. We show that the automated classification alleviates shortcomings of widely-used text-matching systems, such as Turnitin and PlagScan. To facilitate future research, all data, code, and two web applications showcasing our contributions are openly available at https://github.com/jpwahle/iconf22-paraphrase.

Felix Hamborg, Corinna Breitinger, Bela Gipp

Event extraction from news articles is a commonly required prerequisite for various tasks, such as article summarization, article clustering, and news aggregation. Due to the lack of universally applicable and publicly available methods tailored to news datasets, many researchers redundantly implement event extraction methods for their own projects. The journalistic 5W1H questions are capable of describing the main event of an article, i.e., by answering who did what, when, where, why, and how. We provide an in-depth description of an improved version of Giveme5W1H, a system that uses syntactic and domain-specific rules to automatically extract the relevant phrases from English news articles to provide answers to these 5W1H questions. Given the answers to these questions, the system determines an article's main event. In an expert evaluation with three assessors and 120 articles, we determined an overall precision of p=0.73, and p=0.82 for answering the first four W questions, which alone can sufficiently summarize the main event reported on in a news article. We recently made our system publicly available, and it remains the only universal open-source 5W1H extractor capable of being applied to a wide range of use cases in news analysis.

Moritz Schubotz, Philipp Scharpf, Kaushal Dudhat et al.

We present an open source math-aware Question Answering System based on Ask Platypus. Our system returns as a single mathematical formula for a natural language question in English or Hindi. This formulae originate from the knowledge-base Wikidata. We translate these formulae to computable data by integrating the calculation engine sympy into our system. This way, users can enter numeric values for the variables occurring in the formula. Moreover, the system loads numeric values for constants occurring in the formula from Wikidata. In a user study, our system outperformed a commercial computational mathematical knowledge engine by 13%. However, the performance of our system heavily depends on the size and quality of the formula data available in Wikidata. Since only a few items in Wikidata contained formulae when we started the project, we facilitated the import process by suggesting formula edits to Wikidata editors. With the simple heuristic that the first formula is significant for the article, 80% of the suggestions were correct.

Moritz Schubotz, Norman Meuschke, Thomas Hepp et al.

Mathematical expressions can be represented as a tree consisting of terminal symbols, such as identifiers or numbers (leaf nodes), and functions or operators (non-leaf nodes). Expression trees are an important mechanism for storing and processing mathematical expressions as well as the most frequently used visualization of the structure of mathematical expressions. Typically, researchers and practitioners manually visualize expression trees using general-purpose tools. This approach is laborious, redundant, and error-prone. Manual visualizations represent a user's notion of what the markup of an expression should be, but not necessarily what the actual markup is. This paper presents VMEXT - a free and open source tool to directly visualize expression trees from parallel MathML. VMEXT simultaneously visualizes the presentation elements and the semantic structure of mathematical expressions to enable users to quickly spot deficiencies in the Content MathML markup that does not affect the presentation of the expression. Identifying such discrepancies previously required reading the verbose and complex MathML markup. VMEXT also allows one to visualize similar and identical elements of two expressions. Visualizing expression similarity can support support developers in designing retrieval approaches and enable improved interaction concepts for users of mathematical information retrieval systems. We demonstrate VMEXT's visualizations in two web-based applications. The first application presents the visualizations alone. The second application shows a possible integration of the visualizations in systems for mathematical knowledge management and mathematical information retrieval. The application converts LaTeX input to parallel MathML, computes basic similarity measures for mathematical expressions, and visualizes the results using VMEXT.

Shamsuddeen Hassan Muhammad, Nedjma Ousidhoum, Idris Abdulmumin et al.

People worldwide use language in subtle and complex ways to express emotions. Although emotion recognition--an umbrella term for several NLP tasks--impacts various applications within NLP and beyond, most work in this area has focused on high-resource languages. This has led to significant disparities in research efforts and proposed solutions, particularly for under-resourced languages, which often lack high-quality annotated datasets. In this paper, we present BRIGHTER--a collection of multi-labeled, emotion-annotated datasets in 28 different languages and across several domains. BRIGHTER primarily covers low-resource languages from Africa, Asia, Eastern Europe, and Latin America, with instances labeled by fluent speakers. We highlight the challenges related to the data collection and annotation processes, and then report experimental results for monolingual and crosslingual multi-label emotion identification, as well as emotion intensity recognition. We analyse the variability in performance across languages and text domains, both with and without the use of LLMs, and show that the BRIGHTER datasets represent a meaningful step towards addressing the gap in text-based emotion recognition.

Ankit Satpute, André Greiner-Petter, Noah Gießing et al.

Content-based research paper recommendation (CbRPR) has seen advances in computer science and biomedicine, but remains unexplored for mathematics, where paper relatedness is more conceptual than explicit textual or citation-based similarity. Mathematics papers may be connected through shared proof techniques, logical implications, or natural generalizations, yet exhibit minimal textual or citation overlap, rendering existing CbRPR ineffective. To address this gap, we first conduct an expert-driven study characterizing mathematical recommendations, revealing that relevance is inherently \textit{aspect}-driven. Grounded in this insight, we introduce GoldRiM (small, expert-annotated) and SilverRiM (large, automatically derived), the first datasets for \textit{aspect}-aware CbRPR in mathematics. Recognizing that LLM embeddings of mathematical content alone yield suboptimal representation, we propose AchGNN, an \textit{aspect}-conditioned heterogeneous GNN that jointly models textual semantics, citation structure, and author lineage. Across GoldRiM and SilverRiM, AchGNN consistently outperforms prior \textit{aspect}-based CbRPR methods, achieving substantial gains across all evaluated \textit{aspects}. We conduct ablation studies to analyze the contributions of individual \textit{aspect} supervision, authorship lineage, and graph-structural signals to AchGNN's performance. To assess domain generality, we further evaluate AchGNN on the \textit{Papers with Code} dataset of machine learning publications, demonstrating that our \textit{aspect}-aware approach effectively transfers beyond mathematics. We deploy our system on the MaRDI platform to help mathematicians with recommendations and release datasets and code publicly for reproducibility.

Lars Benedikt Kaesberg, Jonas Becker, Jan Philip Wahle et al.

Much of the success of multi-agent debates depends on carefully choosing the right parameters. The decision-making protocol stands out as it can highly impact final model answers, depending on how decisions are reached. Systematic comparison of decision protocols is difficult because many studies alter multiple discussion parameters beyond the protocol. So far, it has been largely unknown how decision-making influences different tasks. This work systematically evaluates the impact of seven decision protocols (e.g., majority voting, unanimity consensus). We change only one variable at a time - the decision protocol - to analyze how different methods affect the collaboration between agents and measure differences in knowledge and reasoning tasks. Our results show that voting protocols improve performance by 13.2% in reasoning tasks and consensus protocols by 2.8% in knowledge tasks compared to other decision protocols. Increasing the number of agents improves performance, while more discussion rounds before voting reduce it. To improve decision-making by increasing answer diversity, we propose two new methods, All-Agents Drafting (AAD) and Collective Improvement (CI). Our methods improve task performance by up to 3.3% with AAD and up to 7.4% with CI. This work demonstrates the importance of decision-making in multi-agent debates beyond scaling.

Jonas Becker, Jan Philip Wahle, Bela Gipp et al.

Text generation has become more accessible than ever, and the increasing interest in these systems, especially those using large language models, has spurred an increasing number of related publications. We provide a systematic literature review comprising 244 selected papers between 2017 and 2024. This review categorizes works in text generation into five main tasks: open-ended text generation, summarization, translation, paraphrasing, and question answering. For each task, we review their relevant characteristics, sub-tasks, and specific challenges (e.g., missing datasets for multi-document summarization, coherence in story generation, and complex reasoning for question answering). Additionally, we assess current approaches for evaluating text generation systems and ascertain problems with current metrics. Our investigation shows nine prominent challenges common to all tasks and sub-tasks in recent text generation publications: bias, reasoning, hallucinations, misuse, privacy, interpretability, transparency, datasets, and computing. We provide a detailed analysis of these challenges, their potential solutions, and which gaps still require further engagement from the community. This systematic literature review targets two main audiences: early career researchers in natural language processing looking for an overview of the field and promising research directions, as well as experienced researchers seeking a detailed view of tasks, evaluation methodologies, open challenges, and recent mitigation strategies.

Timo Spinde, Smi Hinterreiter, Fabian Haak et al.

The way the media presents events can significantly affect public perception, which in turn can alter people's beliefs and views. Media bias describes a one-sided or polarizing perspective on a topic. This article summarizes the research on computational methods to detect media bias by systematically reviewing 3140 research papers published between 2019 and 2022. To structure our review and support a mutual understanding of bias across research domains, we introduce the Media Bias Taxonomy, which provides a coherent overview of the current state of research on media bias from different perspectives. We show that media bias detection is a highly active research field, in which transformer-based classification approaches have led to significant improvements in recent years. These improvements include higher classification accuracy and the ability to detect more fine-granular types of bias. However, we have identified a lack of interdisciplinarity in existing projects, and a need for more awareness of the various types of media bias to support methodologically thorough performance evaluations of media bias detection systems. Concluding from our analysis, we see the integration of recent machine learning advancements with reliable and diverse bias assessment strategies from other research areas as the most promising area for future research contributions in the field.

Tomas Horych, Christoph Mandl, Terry Ruas et al.

High annotation costs from hiring or crowdsourcing complicate the creation of large, high-quality datasets needed for training reliable text classifiers. Recent research suggests using Large Language Models (LLMs) to automate the annotation process, reducing these costs while maintaining data quality. LLMs have shown promising results in annotating downstream tasks like hate speech detection and political framing. Building on the success in these areas, this study investigates whether LLMs are viable for annotating the complex task of media bias detection and whether a downstream media bias classifier can be trained on such data. We create annolexical, the first large-scale dataset for media bias classification with over 48000 synthetically annotated examples. Our classifier, fine-tuned on this dataset, surpasses all of the annotator LLMs by 5-9 percent in Matthews Correlation Coefficient (MCC) and performs close to or outperforms the model trained on human-labeled data when evaluated on two media bias benchmark datasets (BABE and BASIL). This study demonstrates how our approach significantly reduces the cost of dataset creation in the media bias domain and, by extension, the development of classifiers, while our subsequent behavioral stress-testing reveals some of its current limitations and trade-offs.

Andreas Stephan, Lukas Miklautz, Kevin Sidak et al.

Image clustering divides a collection of images into meaningful groups, typically interpreted post-hoc via human-given annotations. Those are usually in the form of text, begging the question of using text as an abstraction for image clustering. Current image clustering methods, however, neglect the use of generated textual descriptions. We, therefore, propose Text-Guided Image Clustering, i.e., generating text using image captioning and visual question-answering (VQA) models and subsequently clustering the generated text. Further, we introduce a novel approach to inject task- or domain knowledge for clustering by prompting VQA models. Across eight diverse image clustering datasets, our results show that the obtained text representations often outperform image features. Additionally, we propose a counting-based cluster explainability method. Our evaluations show that the derived keyword-based explanations describe clusters better than the respective cluster accuracy suggests. Overall, this research challenges traditional approaches and paves the way for a paradigm shift in image clustering, using generated text.

Jonas Becker, Lars Benedikt Kaesberg, Andreas Stephan et al.

Multi-agent debate - multiple instances of large language models discussing problems in turn-based interaction - has shown promise for solving knowledge and reasoning tasks. However, these methods show limitations when solving complex problems that require longer reasoning chains. We analyze how multi-agent debate over multiple turns drifts away from the initial problem, thus harming task performance. We define this phenomenon as problem drift and quantify its presence across ten tasks (i.e., three generative, three knowledge, three reasoning, and one instruction-following task). To identify the reasons for this issue, eight human experts analyze 170 multi-agent discussions suffering from problem drift. We find the most common issues related to this drift are the lack of progress (35% of cases), low-quality feedback (26% of cases), and a lack of clarity (25% of cases). To address problem drift, we propose DRIFTJudge, an LLM-as-a-judge method, to detect problem drift at test-time. We also propose DRIFTPolicy, a method that mitigates problem drift cases to improve task performance. Our study is a step toward understanding a key limitation of multi-agent debate, highlighting why longer debates can harm task performance and how problem drift could be addressed.

Frederic Kirstein, Jan Philip Wahle, Terry Ruas et al.

Meeting summarization has become a critical task considering the increase in online interactions. While new techniques are introduced regularly, their evaluation uses metrics not designed to capture meeting-specific errors, undermining effective evaluation. This paper investigates what the frequently used automatic metrics capture and which errors they mask by correlating automatic metric scores with human evaluations across a broad error taxonomy. We commence with a comprehensive literature review on English meeting summarization to define key challenges like speaker dynamics and contextual turn-taking and error types such as missing information and linguistic inaccuracy, concepts previously loosely defined in the field. We examine the relationship between characteristic challenges and errors by using annotated transcripts and summaries from Transformer-based sequence-to-sequence and autoregressive models from the general summary QMSum dataset. Through experimental validation, we find that different model architectures respond variably to challenges in meeting transcripts, resulting in different pronounced links between challenges and errors. Current default-used metrics struggle to capture observable errors, showing weak to mid-correlations, while a third of the correlations show trends of error masking. Only a subset reacts accurately to specific errors, while most correlations show either unresponsiveness or failure to reflect the error's impact on summary quality.

Frederic Kirstein, Terry Ruas, Robert Kratel et al.

Meeting summarization is crucial in digital communication, but existing solutions struggle with salience identification to generate personalized, workable summaries, and context understanding to fully comprehend the meetings' content. Previous attempts to address these issues by considering related supplementary resources (e.g., presentation slides) alongside transcripts are hindered by models' limited context sizes and handling the additional complexities of the multi-source tasks, such as identifying relevant information in additional files and seamlessly aligning it with the meeting content. This work explores multi-source meeting summarization considering supplementary materials through a three-stage large language model approach: identifying transcript passages needing additional context, inferring relevant details from supplementary materials and inserting them into the transcript, and generating a summary from this enriched transcript. Our multi-source approach enhances model understanding, increasing summary relevance by ~9% and producing more content-rich outputs. We introduce a personalization protocol that extracts participant characteristics and tailors summaries accordingly, improving informativeness by ~10%. This work further provides insights on performance-cost trade-offs across four leading model families, including edge-device capable options. Our approach can be extended to similar complex generative tasks benefitting from additional resources and personalization, such as dialogue systems and action planning.

Liang-Chih Yu, Jonas Becker, Shamsuddeen Hassan Muhammad et al.

We present the SemEval-2026 shared task on Dimensional Aspect-Based Sentiment Analysis (DimABSA), which improves traditional ABSA by modeling sentiment along valence-arousal (VA) dimensions rather than using categorical polarity labels. To extend ABSA beyond consumer reviews to public-issue discourse (e.g., political, energy, and climate issues), we introduce an additional task, Dimensional Stance Analysis (DimStance), which treats stance targets as aspects and reformulates stance detection as regression in the VA space. The task consists of two tracks: Track A (DimABSA) and Track B (DimStance). Track A includes three subtasks: (1) dimensional aspect sentiment regression, (2) dimensional aspect sentiment triplet extraction, and (3) dimensional aspect sentiment quadruplet extraction, while Track B includes only the regression subtask for stance targets. We also introduce a continuous F1 (cF1) metric to jointly evaluate structured extraction and VA regression. The task attracted more than 400 participants, resulting in 112 final submissions and 42 system description papers. We report baseline results, discuss top-performing systems, and analyze key design choices to provide insights into dimensional sentiment analysis at the aspect and stance-target levels. All resources are available on our GitHub repository.

Anastasia Zhukova, Christian E. Matt, Bela Gipp

Domain-specific languages that use a lot of specific terminology often fall into the category of low-resource languages. Collecting test datasets in a narrow domain is time-consuming and requires skilled human resources with domain knowledge and training for the annotation task. This study addresses the challenge of automated collecting test datasets to evaluate semantic search in low-resource domain-specific German language of the process industry. Our approach proposes an end-to-end annotation pipeline for automated query generation to the score reassessment of query-document pairs. To overcome the lack of text encoders trained in the German chemistry domain, we explore a principle of an ensemble of "weak" text encoders trained on common knowledge datasets. We combine individual relevance scores from diverse models to retrieve document candidates and relevance scores generated by an LLM, aiming to achieve consensus on query-document alignment. Evaluation results demonstrate that the ensemble method significantly improves alignment with human-assigned relevance scores, outperforming individual models in both inter-coder agreement and accuracy metrics. These findings suggest that ensemble learning can effectively adapt semantic search systems for specialized, low-resource languages, offering a practical solution to resource limitations in domain-specific contexts.

Tomáš Horych, Martin Wessel, Jan Philip Wahle et al.

Media bias detection poses a complex, multifaceted problem traditionally tackled using single-task models and small in-domain datasets, consequently lacking generalizability. To address this, we introduce MAGPIE, the first large-scale multi-task pre-training approach explicitly tailored for media bias detection. To enable pre-training at scale, we present Large Bias Mixture (LBM), a compilation of 59 bias-related tasks. MAGPIE outperforms previous approaches in media bias detection on the Bias Annotation By Experts (BABE) dataset, with a relative improvement of 3.3% F1-score. MAGPIE also performs better than previous models on 5 out of 8 tasks in the Media Bias Identification Benchmark (MBIB). Using a RoBERTa encoder, MAGPIE needs only 15% of finetuning steps compared to single-task approaches. Our evaluation shows, for instance, that tasks like sentiment and emotionality boost all learning, all tasks enhance fake news detection, and scaling tasks leads to the best results. MAGPIE confirms that MTL is a promising approach for addressing media bias detection, enhancing the accuracy and efficiency of existing models. Furthermore, LBM is the first available resource collection focused on media bias MTL.

Lars Benedikt Kaesberg, Tianyu Yang, Niklas Bauer et al.

Spatial reasoning is central to navigation and robotics, yet measuring model capabilities on these tasks remains difficult. Existing benchmarks evaluate models in a one-shot setting, requiring full solution generation in a single response, unlike humans, who work in interactive environments step-by-step. We introduce Spatial-Gym, a Gymnasium environment that isolates spatial constraint reasoning by testing pathfinding in 2D-grid puzzles as a sequential decision task with optional backtracking. We evaluate eight models in three settings (one-shot, step-by-step, step-by-step with backtracking) against human, random, and A* baselines on 500 episodes. The best model, GPT-OSS 120B, achieves a solve rate of 16.0%, 82 points below the human baseline (98.0%). Step-by-step format helps weaker models (up to +5.4%) by removing formatting errors, but hurts stronger models (up to 5.6%) by constraining global planning. Backtracking improves episode completion, but increases solve rate only for weaker models; stronger models rarely backtrack and do not benefit from it. Our experiments have three key findings: (1) models fail to scale reasoning effort with difficulty, (2) vision models receiving images of the spatial environment reduce solve rate by 73%, and (3) extended chain-of-thought reasoning retains a 3-5x accuracy advantage over standard inference even in the step-by-step setting. Spatial-Gym enables diagnosis of model limitations and provides a framework for improving spatial reasoning through reinforcement learning.