Anne Lauscher

Tilman Beck, Hendrik Schuff, Anne Lauscher et al.

Annotators' sociodemographic backgrounds (i.e., the individual compositions of their gender, age, educational background, etc.) have a strong impact on their decisions when working on subjective NLP tasks, such as toxic language detection. Often, heterogeneous backgrounds result in high disagreements. To model this variation, recent work has explored sociodemographic prompting, a technique, which steers the output of prompt-based models towards answers that humans with specific sociodemographic profiles would give. However, the available NLP literature disagrees on the efficacy of this technique - it remains unclear for which tasks and scenarios it can help, and the role of the individual factors in sociodemographic prompting is still unexplored. We address this research gap by presenting the largest and most comprehensive study of sociodemographic prompting today. We analyze its influence on model sensitivity, performance and robustness across seven datasets and six instruction-tuned model families. We show that sociodemographic information affects model predictions and can be beneficial for improving zero-shot learning in subjective NLP tasks. However, its outcomes largely vary for different model types, sizes, and datasets, and are subject to large variance with regards to prompt formulations. Most importantly, our results show that sociodemographic prompting should be used with care for sensitive applications, such as toxicity annotation or when studying LLM alignment. Code and data: https://github.com/UKPLab/arxiv2023-sociodemographic-prompting

Anne Lauscher, Federico Bianchi, Samuel Bowman et al. · stanford

Pre-trained language models (PLMs) have outperformed other NLP models on a wide range of tasks. Opting for a more thorough understanding of their capabilities and inner workings, researchers have established the extend to which they capture lower-level knowledge like grammaticality, and mid-level semantic knowledge like factual understanding. However, there is still little understanding of their knowledge of higher-level aspects of language. In particular, despite the importance of sociodemographic aspects in shaping our language, the questions of whether, where, and how PLMs encode these aspects, e.g., gender or age, is still unexplored. We address this research gap by probing the sociodemographic knowledge of different single-GPU PLMs on multiple English data sets via traditional classifier probing and information-theoretic minimum description length probing. Our results show that PLMs do encode these sociodemographics, and that this knowledge is sometimes spread across the layers of some of the tested PLMs. We further conduct a multilingual analysis and investigate the effect of supplementary training to further explore to what extent, where, and with what amount of pre-training data the knowledge is encoded. Our overall results indicate that sociodemographic knowledge is still a major challenge for NLP. PLMs require large amounts of pre-training data to acquire the knowledge and models that excel in general language understanding do not seem to own more knowledge about these aspects.

Carolin Holtermann, Anne Lauscher, Simone Paolo Ponzetto

Although much work in NLP has focused on measuring and mitigating stereotypical bias in semantic spaces, research addressing bias in computational argumentation is still in its infancy. In this paper, we address this research gap and conduct a thorough investigation of bias in argumentative language models. To this end, we introduce ABBA, a novel resource for bias measurement specifically tailored to argumentation. We employ our resource to assess the effect of argumentative fine-tuning and debiasing on the intrinsic bias found in transformer-based language models using a lightweight adapter-based approach that is more sustainable and parameter-efficient than full fine-tuning. Finally, we analyze the potential impact of language model debiasing on the performance in argument quality prediction, a downstream task of computational argumentation. Our results show that we are able to successfully and sustainably remove bias in general and argumentative language models while preserving (and sometimes improving) model performance in downstream tasks. We make all experimental code and data available at https://github.com/umanlp/FairArgumentativeLM.

Marco Antonio Stranisci, A Pranav, Rossana Damiano et al.

Modern language models rely on pretraining filters to remove undesirable content from training corpora and inference-time guardrails to suppress undesirable outputs during deployment. In this paper, we examine how these filtering and moderation decisions produce forms of epistemic erasure and reveal tensions both across automated systems and between these systems and human judgment. We audit four pretraining filters and three inference-time guardrails on Common Crawl sentences containing gender and regional-origin mentions, together with a manually annotated subset of 500 sentences. Our analysis shows that filtering and guardrail decisions are strongly associated with blocklist-based lexical cues, while frequently failing to flag content containing private information or explicit hate speech. At the same time, marginalized groups, particularly transgender people, women, and Central Americans, are significantly over-flagged across systems. Human annotators, by contrast, would retain 88.5\% of filter-flagged and 91.3\% of guardrail-flagged content, often recognizing representational harms arising from tensions of content removal that current systems fail to capture. Taken together, our findings document a form of epistemic erasure in which mentions of marginalized groups are disproportionately removed before pretraining and additionally suppressed again at inference time.

Chia-Chien Hung, Anne Lauscher, Ivan Vulić et al.

Research on (multi-domain) task-oriented dialog (TOD) has predominantly focused on the English language, primarily due to the shortage of robust TOD datasets in other languages, preventing the systematic investigation of cross-lingual transfer for this crucial NLP application area. In this work, we introduce Multi2WOZ, a new multilingual multi-domain TOD dataset, derived from the well-established English dataset MultiWOZ, that spans four typologically diverse languages: Chinese, German, Arabic, and Russian. In contrast to concurrent efforts, Multi2WOZ contains gold-standard dialogs in target languages that are directly comparable with development and test portions of the English dataset, enabling reliable and comparative estimates of cross-lingual transfer performance for TOD. We then introduce a new framework for multilingual conversational specialization of pretrained language models (PrLMs) that aims to facilitate cross-lingual transfer for arbitrary downstream TOD tasks. Using such conversational PrLMs specialized for concrete target languages, we systematically benchmark a number of zero-shot and few-shot cross-lingual transfer approaches on two standard TOD tasks: Dialog State Tracking and Response Retrieval. Our experiments show that, in most setups, the best performance entails the combination of (I) conversational specialization in the target language and (ii) few-shot transfer for the concrete TOD task. Most importantly, we show that our conversational specialization in the target language allows for an exceptionally sample-efficient few-shot transfer for downstream TOD tasks.

Jonas Belouadi, Anne Lauscher, Steffen Eger

Generating bitmap graphics from text has gained considerable attention, yet for scientific figures, vector graphics are often preferred. Given that vector graphics are typically encoded using low-level graphics primitives, generating them directly is difficult. To address this, we propose the use of TikZ, a well-known abstract graphics language that can be compiled to vector graphics, as an intermediate representation of scientific figures. TikZ offers human-oriented, high-level commands, thereby facilitating conditional language modeling with any large language model. To this end, we introduce DaTikZ, the first large-scale TikZ dataset consisting of 120k TikZ drawings aligned with captions. We fine-tune LLaMA on DaTikZ, as well as our new model CLiMA, which augments LLaMA with multimodal CLIP embeddings. In both human and automatic evaluation, CLiMA and LLaMA outperform commercial GPT-4 and Claude 2 in terms of similarity to human-created figures, with CLiMA additionally improving text-image alignment. Our detailed analysis shows that all models generalize well and are not susceptible to memorization. GPT-4 and Claude 2, however, tend to generate more simplistic figures compared to both humans and our models. We make our framework, AutomaTikZ, along with model weights and datasets, publicly available.

Chia-Chien Hung, Anne Lauscher, Dirk Hovy et al.

Demographic factors (e.g., gender or age) shape our language. Previous work showed that incorporating demographic factors can consistently improve performance for various NLP tasks with traditional NLP models. In this work, we investigate whether these previous findings still hold with state-of-the-art pretrained Transformer-based language models (PLMs). We use three common specialization methods proven effective for incorporating external knowledge into pretrained Transformers (e.g., domain-specific or geographic knowledge). We adapt the language representations for the demographic dimensions of gender and age, using continuous language modeling and dynamic multi-task learning for adaptation, where we couple language modeling objectives with the prediction of demographic classes. Our results, when employing a multilingual PLM, show substantial gains in task performance across four languages (English, German, French, and Danish), which is consistent with the results of previous work. However, controlling for confounding factors - primarily domain and language proficiency of Transformer-based PLMs - shows that downstream performance gains from our demographic adaptation do not actually stem from demographic knowledge. Our results indicate that demographic specialization of PLMs, while holding promise for positive societal impact, still represents an unsolved problem for (modern) NLP.

Marius Hessenthaler, Emma Strubell, Dirk Hovy et al.

Fairness and environmental impact are important research directions for the sustainable development of artificial intelligence. However, while each topic is an active research area in natural language processing (NLP), there is a surprising lack of research on the interplay between the two fields. This lacuna is highly problematic, since there is increasing evidence that an exclusive focus on fairness can actually hinder environmental sustainability, and vice versa. In this work, we shed light on this crucial intersection in NLP by (1) investigating the efficiency of current fairness approaches through surveying example methods for reducing unfair stereotypical bias from the literature, and (2) evaluating a common technique to reduce energy consumption (and thus environmental impact) of English NLP models, knowledge distillation (KD), for its impact on fairness. In this case study, we evaluate the effect of important KD factors, including layer and dimensionality reduction, with respect to: (a) performance on the distillation task (natural language inference and semantic similarity prediction), and (b) multiple measures and dimensions of stereotypical bias (e.g., gender bias measured via the Word Embedding Association Test). Our results lead us to clarify current assumptions regarding the effect of KD on unfair bias: contrary to other findings, we show that KD can actually decrease model fairness.

Giuseppe Attanasio, Flor Miriam Plaza-del-Arco, Debora Nozza et al.

Recent instruction fine-tuned models can solve multiple NLP tasks when prompted to do so, with machine translation (MT) being a prominent use case. However, current research often focuses on standard performance benchmarks, leaving compelling fairness and ethical considerations behind. In MT, this might lead to misgendered translations, resulting, among other harms, in the perpetuation of stereotypes and prejudices. In this work, we address this gap by investigating whether and to what extent such models exhibit gender bias in machine translation and how we can mitigate it. Concretely, we compute established gender bias metrics on the WinoMT corpus from English to German and Spanish. We discover that IFT models default to male-inflected translations, even disregarding female occupational stereotypes. Next, using interpretability methods, we unveil that models systematically overlook the pronoun indicating the gender of a target occupation in misgendered translations. Finally, based on this finding, we propose an easy-to-implement and effective bias mitigation solution based on few-shot learning that leads to significantly fairer translations.

Karina Vida, Judith Simon, Anne Lauscher

With language technology increasingly affecting individuals' lives, many recent works have investigated the ethical aspects of NLP. Among other topics, researchers focused on the notion of morality, investigating, for example, which moral judgements language models make. However, there has been little to no discussion of the terminology and the theories underpinning those efforts and their implications. This lack is highly problematic, as it hides the works' underlying assumptions and hinders a thorough and targeted scientific debate of morality in NLP. In this work, we address this research gap by (a) providing an overview of some important ethical concepts stemming from philosophy and (b) systematically surveying the existing literature on moral NLP w.r.t. their philosophical foundation, terminology, and data basis. For instance, we analyse what ethical theory an approach is based on, how this decision is justified, and what implications it entails. Our findings surveying 92 papers show that, for instance, most papers neither provide a clear definition of the terms they use nor adhere to definitions from philosophy. Finally, (c) we give three recommendations for future research in the field. We hope our work will lead to a more informed, careful, and sound discussion of morality in language technology.

Sukannya Purkayastha, Anne Lauscher, Iryna Gurevych

In many domains of argumentation, people's arguments are driven by so-called attitude roots, i.e., underlying beliefs and world views, and their corresponding attitude themes. Given the strength of these latent drivers of arguments, recent work in psychology suggests that instead of directly countering surface-level reasoning (e.g., falsifying given premises), one should follow an argumentation style inspired by the Jiu-Jitsu 'soft' combat system (Hornsey and Fielding, 2017): first, identify an arguer's attitude roots and themes, and then choose a prototypical rebuttal that is aligned with those drivers instead of invalidating those. In this work, we are the first to explore Jiu-Jitsu argumentation for peer review by proposing the novel task of attitude and theme-guided rebuttal generation. To this end, we enrich an existing dataset for discourse structure in peer reviews with attitude roots, attitude themes, and canonical rebuttals. To facilitate this process, we recast established annotation concepts from the domain of peer reviews (e.g., aspects a review sentence is relating to) and train domain-specific models. We then propose strong rebuttal generation strategies, which we benchmark on our novel dataset for the task of end-to-end attitude and theme-guided rebuttal generation and two subtasks.

Fabian Mewes, Anne Lauscher, Vagrant Gautam

Third-person singular pronouns have long been used to study stereotypical biases in language models and to test their abilities to reason about reference. More recently, the interplay between reasoning and bias has been investigated with the task of pronoun fidelity, which assesses models' abilities to correctly reuse a previously-specified pronoun for a discourse entity, independent of other potentially distracting discourse entities mentioned in between. However, such research focuses on English, which is a language with limited grammatical gender and almost no gender agreement. In this paper we contribute a novel, large-scale dataset, GRUFF, to measure pronoun fidelity in German, covering four different gender agreement systems in nouns, and four sets of pronouns. With this dataset, we show that LLMs show strong grammatical agreement for masculine and feminine entities in the absence of explicit context, but not for neopronouns xier and en. Models are generally not robust to distractors, but encoder-only models are more robust in German than in English, reflecting the importance of grammatical gender. Finally, we show that occupational stereotypes in this context are poorly correlated across grammatical cases, and across most models, except ones with closely related architectures. We release all code and data to encourage further work on gender-inclusive language and referential reasoning in German.

Musashi Hinck, Carolin Holtermann, Matthew Lyle Olson et al.

We uncover a surprising multilingual bias occurring in a popular class of multimodal vision-language models (VLMs). Including an image in the query to a LLaVA-style VLM significantly increases the likelihood of the model returning an English response, regardless of the language of the query. This paper investigates the causes of this loss with a two-pronged approach that combines extensive ablation of the design space with a mechanistic analysis of the models' internal representations of image and text inputs. Both approaches indicate that the issue stems in the language modelling component of the LLaVA model. Statistically, we find that switching the language backbone for a bilingual language model has the strongest effect on reducing this error. Mechanistically, we provide compelling evidence that visual inputs are not mapped to a similar space as text ones, and that intervening on intermediary attention layers can reduce this bias. Our findings provide important insights to researchers and engineers seeking to understand the crossover between multimodal and multilingual spaces, and contribute to the goal of developing capable and inclusive VLMs for non-English contexts.

Karina Vida, Fabian Damken, Anne Lauscher

Large language models (LLMs) increasingly find their way into the most diverse areas of our everyday lives. They indirectly influence people's decisions or opinions through their daily use. Therefore, understanding how and which moral judgements these LLMs make is crucial. However, morality is not universal and depends on the cultural background. This raises the question of whether these cultural preferences are also reflected in LLMs when prompted in different languages or whether moral decision-making is consistent across different languages. So far, most research has focused on investigating the inherent values of LLMs in English. While a few works conduct multilingual analyses of moral bias in LLMs in a multilingual setting, these analyses do not go beyond atomic actions. To the best of our knowledge, a multilingual analysis of moral bias in dilemmas has not yet been conducted. To address this, our paper builds on the moral machine experiment (MME) to investigate the moral preferences of five LLMs, Falcon, Gemini, Llama, GPT, and MPT, in a multilingual setting and compares them with the preferences collected from humans belonging to different cultures. To accomplish this, we generate 6500 scenarios of the MME and prompt the models in ten languages on which action to take. Our analysis reveals that all LLMs inhibit different moral biases to some degree and that they not only differ from the human preferences but also across multiple languages within the models themselves. Moreover, we find that almost all models, particularly Llama 3, divert greatly from human values and, for instance, prefer saving fewer people over saving more.

Vagrant Gautam, Julius Steuer, Eileen Bingert et al.

While measuring bias and robustness in coreference resolution are important goals, such measurements are only as good as the tools we use to measure them. Winogender Schemas (Rudinger et al., 2018) are an influential dataset proposed to evaluate gender bias in coreference resolution, but a closer look reveals issues with the data that compromise its use for reliable evaluation, including treating different pronominal forms as equivalent, violations of template constraints, and typographical errors. We identify these issues and fix them, contributing a new dataset: WinoPron. Using WinoPron, we evaluate two state-of-the-art supervised coreference resolution systems, SpanBERT, and five sizes of FLAN-T5, and demonstrate that accusative pronouns are harder to resolve for all models. We also propose a new method to evaluate pronominal bias in coreference resolution that goes beyond the binary. With this method, we also show that bias characteristics vary not just across pronoun sets (e.g., he vs. she), but also across surface forms of those sets (e.g., him vs. his).

Andreas Waldis, Joel Birrer, Anne Lauscher et al.

Gender-fair language, an evolving German linguistic variation, fosters inclusion by addressing all genders or using neutral forms. Nevertheless, there is a significant lack of resources to assess the impact of this linguistic shift on classification using language models (LMs), which are probably not trained on such variations. To address this gap, we present Lou, the first dataset featuring high-quality reformulations for German text classification covering seven tasks, like stance detection and toxicity classification. Evaluating 16 mono- and multi-lingual LMs on Lou shows that gender-fair language substantially impacts predictions by flipping labels, reducing certainty, and altering attention patterns. However, existing evaluations remain valid, as LM rankings of original and reformulated instances do not significantly differ. While we offer initial insights on the effect on German text classification, the findings likely apply to other languages, as consistent patterns were observed in multi-lingual and English LMs.

Zeerak Talat, Anne Lauscher

Machine learning and NLP require the construction of datasets to train and fine-tune models. In this context, previous work has demonstrated the sensitivity of these data sets. For instance, potential societal biases in this data are likely to be encoded and to be amplified in the models we deploy. In this work, we draw from developments in the field of history and take a novel perspective on these problems: considering datasets and models through the lens of historical fiction surfaces their political nature, and affords re-configuring how we view the past, such that marginalized discourses are surfaced. Building on such insights, we argue that contemporary methods for machine learning are prejudiced towards dominant and hegemonic histories. Employing the example of neopronouns, we show that by surfacing marginalized histories within contemporary conditions, we can create models that better represent the lived realities of traditionally marginalized and excluded communities.

Chia-Chien Hung, Anne Lauscher, Dirk Hovy et al.

Sociodemographic factors (e.g., gender or age) shape our language. Previous work showed that incorporating specific sociodemographic factors can consistently improve performance for various NLP tasks in traditional NLP models. We investigate whether these previous findings still hold with state-of-the-art pretrained Transformers. We use three common specialization methods proven effective for incorporating external knowledge into pretrained Transformers (e.g., domain-specific or geographic knowledge). We adapt the language representations for the sociodemographic dimensions of gender and age, using continuous language modeling and dynamic multi-task learning for adaptation, where we couple language modeling with the prediction of a sociodemographic class. Our results when employing a multilingual model show substantial performance gains across four languages (English, German, French, and Danish). These findings are in line with the results of previous work and hold promise for successful sociodemographic specialization. However, controlling for confounding factors like domain and language shows that, while sociodemographic adaptation does improve downstream performance, the gains do not always solely stem from sociodemographic knowledge. Our results indicate that sociodemographic specialization, while very important, is still an unresolved problem in NLP.

Markus Frohmann, Carolin Holtermann, Shahed Masoudian et al.

Multi-task learning (MTL) has shown considerable practical benefits, particularly when using language models (LMs). While this is commonly achieved by learning $n$ tasks under a joint optimization procedure, some methods, such as AdapterFusion, divide the problem into two stages: (i) task learning, where knowledge specific to a task is encapsulated within sets of parameters (e.g., adapters), and (ii) transfer, where this already learned knowledge is leveraged for a target task. This separation of concerns provides numerous benefits (e.g., promoting reusability). However, current two-stage MTL introduces a substantial number of additional parameters. We address this issue by leveraging the usefulness of linearly scaling the output representations of source adapters for transfer learning. We introduce ScaLearn, a simple and highly parameter-efficient two-stage MTL method that capitalizes on the knowledge of the source tasks by learning a minimal set of scaling parameters that enable effective transfer to a target task. Our experiments on three benchmarks (GLUE, SuperGLUE, and HumSet) and two encoder LMs show that ScaLearn consistently outperforms strong baselines with a small number of transfer parameters (~ $0.35$% of those of AdapterFusion). Remarkably, we observe that ScaLearn maintains its strong abilities even when further reducing parameters, achieving competitive results with only $8$ transfer parameters per target task. Our proposed approach thus demonstrates the power of simple scaling as a promise for more efficient task transfer.

Carolin Holtermann, Minh Duc Bui, Kaitlyn Zhou et al.

Hundreds of millions of people rely on large language models (LLMs) for education, work, and even healthcare. Yet these models are known to reproduce and amplify social biases present in their training data. Moreover, text-based interfaces remain a barrier for many, for example, users with limited literacy, motor impairments, or mobile-only devices. Voice interaction promises to expand accessibility, but unlike text, speech carries identity cues that users cannot easily mask, raising concerns about whether accessibility gains may come at the cost of equitable treatment. Here we show that audio-enabled LLMs exhibit systematic gender discrimination, shifting responses toward gender-stereotyped adjectives and occupations solely on the basis of speaker voice, and amplifying bias beyond that observed in text-based interaction. Thus, voice interfaces do not merely extend text models to a new modality but introduce distinct bias mechanisms tied to paralinguistic cues. Complementary survey evidence ($n=1,000$) shows that infrequent chatbot users are most hesitant to undisclosed attribute inference and most likely to disengage when such practices are revealed. To demonstrate a potential mitigation strategy, we show that pitch manipulation can systematically regulate gender-discriminatory outputs. Overall, our findings reveal a critical tension in AI development: efforts to expand accessibility through voice interfaces simultaneously create new pathways for discrimination, demanding that fairness and accessibility be addressed in tandem.

Carolin Holtermann, Nina Krebs, Anne Lauscher

Time alters the visual appearance of entities in our world, like objects, places, and animals. Thus, for accurately generating contextually-relevant images, knowledge and reasoning about time can be crucial (e.g., for generating a landscape in spring vs. in winter). Yet, although substantial work exists on understanding and improving temporal knowledge in natural language processing, research on how temporal phenomena appear and are handled in text-to-image (T2I) models remains scarce. We address this gap with TempViz, the first data set to holistically evaluate temporal knowledge in image generation, consisting of 7.9k prompts and more than 600 reference images. Using TempViz, we study the capabilities of five T2I models across five temporal knowledge categories. Human evaluation shows that temporal competence is generally weak, with no model exceeding 75% accuracy across categories. Towards larger-scale studies, we also examine automated evaluation methods, comparing several established approaches against human judgments. However, none of these approaches provides a reliable assessment of temporal cues - further indicating the pressing need for future research on temporal knowledge in T2I.

Carolin Holtermann, Florian Schneider, Anne Lauscher

Text-to-image (T2I) models are increasingly employed by users worldwide. However, prior research has pointed to the high sensitivity of T2I towards particular input languages - when faced with languages other than English (i.e., different surface forms of the same prompt), T2I models often produce culturally stereotypical depictions, prioritizing the surface over the prompt's semantics. Yet a comprehensive analysis of this behavior, which we dub Surface-over-Semantics (SoS), is missing. We present the first analysis of T2I models' SoS tendencies. To this end, we create a set of prompts covering 171 cultural identities, translated into 14 languages, and use it to prompt seven T2I models. To quantify SoS tendencies across models, languages, and cultures, we introduce a novel measure and analyze how the tendencies we identify manifest visually. We show that all but one model exhibit strong surface-level tendency in at least two languages, with this effect intensifying across the layers of T2I text encoders. Moreover, these surface tendencies frequently correlate with stereotypical visual depictions.

Jae Hee Lee, Anne Lauscher, Stefano V. Albrecht

Large language models (LLMs) have been widely deployed in various applications, often functioning as autonomous agents that interact with each other in multi-agent systems. While these systems have shown promise in enhancing capabilities and enabling complex tasks, they also pose significant ethical challenges. This position paper outlines a research agenda aimed at ensuring the ethical behavior of multi-agent systems of LLMs (MALMs) from the perspective of mechanistic interpretability. We identify three key research challenges: (i) developing comprehensive evaluation frameworks to assess ethical behavior at individual, interactional, and systemic levels; (ii) elucidating the internal mechanisms that give rise to emergent behaviors through mechanistic interpretability; and (iii) implementing targeted parameter-efficient alignment techniques to steer MALMs towards ethical behaviors without compromising their performance.

Saad Obaid ul Islam, Anne Lauscher, Goran Glavaš

In the age of misinformation, hallucination -- the tendency of Large Language Models (LLMs) to generate non-factual or unfaithful responses -- represents the main risk for their global utility. Despite LLMs becoming increasingly multilingual, the vast majority of research on detecting and quantifying LLM hallucination are (a) English-centric and (b) focus on machine translation (MT) and summarization, tasks that are less common ``in the wild'' than open information seeking. In contrast, we aim to quantify the extent of LLM hallucination across languages in knowledge-intensive long-form question answering. To this end, we train a multilingual hallucination detection model and conduct a large-scale study across 30 languages and 6 open-source LLM families. We start from an English hallucination detection dataset and rely on MT to generate (noisy) training data in other languages. We also manually annotate gold data for five high-resource languages; we then demonstrate, for these languages, that the estimates of hallucination rates are similar between silver (LLM-generated) and gold test sets, validating the use of silver data for estimating hallucination rates for other languages. For the final rates estimation, we build a knowledge-intensive QA dataset for 30 languages with LLM-generated prompts and Wikipedia articles as references. We find that, while LLMs generate longer responses with more hallucinated tokens for higher-resource languages, there is no correlation between length-normalized hallucination rates of languages and their digital representation. Further, we find that smaller LLMs exhibit larger hallucination rates than larger models.

Sukannya Purkayastha, Zhuang Li, Anne Lauscher et al.

Peer review is a cornerstone of quality control in scientific publishing. With the increasing workload, the unintended use of `quick' heuristics, referred to as lazy thinking, has emerged as a recurring issue compromising review quality. Automated methods to detect such heuristics can help improve the peer-reviewing process. However, there is limited NLP research on this issue, and no real-world dataset exists to support the development of detection tools. This work introduces LazyReview, a dataset of peer-review sentences annotated with fine-grained lazy thinking categories. Our analysis reveals that Large Language Models (LLMs) struggle to detect these instances in a zero-shot setting. However, instruction-based fine-tuning on our dataset significantly boosts performance by 10-20 performance points, highlighting the importance of high-quality training data. Furthermore, a controlled experiment demonstrates that reviews revised with lazy thinking feedback are more comprehensive and actionable than those written without such feedback. We will release our dataset and the enhanced guidelines that can be used to train junior reviewers in the community. (Code available here: https://github.com/UKPLab/acl2025-lazy-review)

Minh Duc Bui, Katharina von der Wense, Anne Lauscher

Warning: this paper contains content that may be offensive or upsetting Hate speech moderation on global platforms poses unique challenges due to the multimodal and multilingual nature of content, along with the varying cultural perceptions. How well do current vision-language models (VLMs) navigate these nuances? To investigate this, we create the first multimodal and multilingual parallel hate speech dataset, annotated by a multicultural set of annotators, called Multi3Hate. It contains 300 parallel meme samples across 5 languages: English, German, Spanish, Hindi, and Mandarin. We demonstrate that cultural background significantly affects multimodal hate speech annotation in our dataset. The average pairwise agreement among countries is just 74%, significantly lower than that of randomly selected annotator groups. Our qualitative analysis indicates that the lowest pairwise label agreement-only 67% between the USA and India-can be attributed to cultural factors. We then conduct experiments with 5 large VLMs in a zero-shot setting, finding that these models align more closely with annotations from the US than with those from other cultures, even when the memes and prompts are presented in the dominant language of the other culture. Code and dataset are available at https://github.com/MinhDucBui/Multi3Hate.

Sukannya Purkayastha, Nils Dycke, Anne Lauscher et al.

Meta-reviewing is a pivotal stage in the peer-review process, serving as the final step in determining whether a paper is recommended for acceptance. Prior research on meta-reviewing has treated this as a summarization problem over review reports. However, complementary to this perspective, meta-reviewing is a decision-making process that requires weighing reviewer arguments and placing them within a broader context. Prior research has demonstrated that decision-makers can be effectively assisted in such scenarios via dialogue agents. In line with this framing, we explore the practical challenges for realizing dialog agents that can effectively assist meta-reviewers. Concretely, we first address the issue of data scarcity for training dialogue agents by generating synthetic data using Large Language Models (LLMs) based on a self-refinement strategy to improve the relevance of these dialogues to expert domains. Our experiments demonstrate that this method produces higher-quality synthetic data and can serve as a valuable resource towards training meta-reviewing assistants. Subsequently, we utilize this data to train dialogue agents tailored for meta-reviewing and find that these agents outperform \emph{off-the-shelf} LLM-based assistants for this task. Finally, we apply our agents in real-world meta-reviewing scenarios and confirm their effectiveness in enhancing the efficiency of meta-reviewing.\footnote{Code and Data: https://github.com/UKPLab/arxiv2025-meta-review-as-dialog

Manuel Lardelli, Giuseppe Attanasio, Anne Lauscher

The translation of gender-neutral person-referring terms (e.g., the students) is often non-trivial. Translating from English into German poses an interesting case -- in German, person-referring nouns are usually gender-specific, and if the gender of the referent(s) is unknown or diverse, the generic masculine (die Studenten (m.)) is commonly used. This solution, however, reduces the visibility of other genders, such as women and non-binary people. To counteract gender discrimination, a societal movement towards using gender-fair language exists (e.g., by adopting neosystems). However, gender-fair German is currently barely supported in machine translation (MT), requiring post-editing or manual translations. We address this research gap by studying gender-fair language in English-to-German MT. Concretely, we enrich a community-created gender-fair language dictionary and sample multi-sentence test instances from encyclopedic text and parliamentary speeches. Using these novel resources, we conduct the first benchmark study involving two commercial systems and six neural MT models for translating words in isolation and natural contexts across two domains. Our findings show that most systems produce mainly masculine forms and rarely gender-neutral variants, highlighting the need for future research. We release code and data at https://github.com/g8a9/building-bridges-gender-fair-german-mt.

Anne Lauscher, Brandon Ko, Bailey Kuehl et al.

Citation context analysis (CCA) is an important task in natural language processing that studies how and why scholars discuss each others' work. Despite decades of study, traditional frameworks for CCA have largely relied on overly-simplistic assumptions of how authors cite, which ignore several important phenomena. For instance, scholarly papers often contain rich discussions of cited work that span multiple sentences and express multiple intents concurrently. Yet, CCA is typically approached as a single-sentence, single-label classification task, and thus existing datasets fail to capture this interesting discourse. In our work, we address this research gap by proposing a novel framework for CCA as a document-level context extraction and labeling task. We release MultiCite, a new dataset of 12,653 citation contexts from over 1,200 computational linguistics papers. Not only is it the largest collection of expert-annotated citation contexts to-date, MultiCite contains multi-sentence, multi-label citation contexts within full paper texts. Finally, we demonstrate how our dataset, while still usable for training classic CCA models, also supports the development of new types of models for CCA beyond fixed-width text classification. We release our code and dataset at https://github.com/allenai/multicite.

Anne Lauscher, Olga Majewska, Leonardo F. R. Ribeiro et al.

Following the major success of neural language models (LMs) such as BERT or GPT-2 on a variety of language understanding tasks, recent work focused on injecting (structured) knowledge from external resources into these models. While on the one hand, joint pretraining (i.e., training from scratch, adding objectives based on external knowledge to the primary LM objective) may be prohibitively computationally expensive, post-hoc fine-tuning on external knowledge, on the other hand, may lead to the catastrophic forgetting of distributional knowledge. In this work, we investigate models for complementing the distributional knowledge of BERT with conceptual knowledge from ConceptNet and its corresponding Open Mind Common Sense (OMCS) corpus, respectively, using adapter training. While overall results on the GLUE benchmark paint an inconclusive picture, a deeper analysis reveals that our adapter-based models substantially outperform BERT (up to 15-20 performance points) on inference tasks that require the type of conceptual knowledge explicitly present in ConceptNet and OMCS. All code and experiments are open sourced under: https://github.com/wluper/retrograph .

Carolin Holtermann, Paul Röttger, Timm Dill et al.

Large language models (LLMs) need to serve everyone, including a global majority of non-English speakers. However, most LLMs today, and open LLMs in particular, are often intended for use in just English (e.g. Llama2, Mistral) or a small handful of high-resource languages (e.g. Mixtral, Qwen). Recent research shows that, despite limits in their intended use, people prompt LLMs in many different languages. Therefore, in this paper, we investigate the basic multilingual capabilities of state-of-the-art open LLMs beyond their intended use. For this purpose, we introduce MultiQ, a new silver standard benchmark for basic open-ended question answering with 27.4k test questions across a typologically diverse set of 137 languages. With MultiQ, we evaluate language fidelity, i.e. whether models respond in the prompted language, and question answering accuracy. All LLMs we test respond faithfully and/or accurately for at least some languages beyond their intended use. Most models are more accurate when they respond faithfully. However, differences across models are large, and there is a long tail of languages where models are neither accurate nor faithful. We explore differences in tokenization as a potential explanation for our findings, identifying possible correlations that warrant further investigation.

Steffen Eger, Yong Cao, Jennifer D'Souza et al.

With the advent of large multimodal language models, science is now at a threshold of an AI-based technological transformation. Recently, a plethora of new AI models and tools has been proposed, promising to empower researchers and academics worldwide to conduct their research more effectively and efficiently. This includes all aspects of the research cycle, especially (1) searching for relevant literature; (2) generating research ideas and conducting experimentation; generating (3) text-based and (4) multimodal content (e.g., scientific figures and diagrams); and (5) AI-based automatic peer review. In this survey, we provide an in-depth overview over these exciting recent developments, which promise to fundamentally alter the scientific research process for good. Our survey covers the five aspects outlined above, indicating relevant datasets, methods and results (including evaluation) as well as limitations and scope for future research. Ethical concerns regarding shortcomings of these tools and potential for misuse (fake science, plagiarism, harms to research integrity) take a particularly prominent place in our discussion. We hope that our survey will not only become a reference guide for newcomers to the field but also a catalyst for new AI-based initiatives in the area of "AI4Science".

Ilia Kuznetsov, Osama Mohammed Afzal, Koen Dercksen et al.

The number of scientific articles produced every year is growing rapidly. Providing quality control over them is crucial for scientists and, ultimately, for the public good. In modern science, this process is largely delegated to peer review -- a distributed procedure in which each submission is evaluated by several independent experts in the field. Peer review is widely used, yet it is hard, time-consuming, and prone to error. Since the artifacts involved in peer review -- manuscripts, reviews, discussions -- are largely text-based, Natural Language Processing has great potential to improve reviewing. As the emergence of large language models (LLMs) has enabled NLP assistance for many new tasks, the discussion on machine-assisted peer review is picking up the pace. Yet, where exactly is help needed, where can NLP help, and where should it stand aside? The goal of our paper is to provide a foundation for the future efforts in NLP for peer-reviewing assistance. We discuss peer review as a general process, exemplified by reviewing at AI conferences. We detail each step of the process from manuscript submission to camera-ready revision, and discuss the associated challenges and opportunities for NLP assistance, illustrated by existing work. We then turn to the big challenges in NLP for peer review as a whole, including data acquisition and licensing, operationalization and experimentation, and ethical issues. To help consolidate community efforts, we create a companion repository that aggregates key datasets pertaining to peer review. Finally, we issue a detailed call for action for the scientific community, NLP and AI researchers, policymakers, and funding bodies to help bring the research in NLP for peer review forward. We hope that our work will help set the agenda for research in machine-assisted scientific quality control in the age of AI, within the NLP community and beyond.

Vagrant Gautam, Eileen Bingert, Dawei Zhu et al.

Robust, faithful and harm-free pronoun use for individuals is an important goal for language model development as their use increases, but prior work tends to study only one or two of these characteristics at a time. To measure progress towards the combined goal, we introduce the task of pronoun fidelity: given a context introducing a co-referring entity and pronoun, the task is to reuse the correct pronoun later. We present RUFF, a carefully-designed dataset of over 5 million instances to measure robust pronoun fidelity in English, and we evaluate 37 model variants from nine popular families, across architectures (encoder-only, decoder-only and encoder-decoder) and scales (11M-70B parameters). When an individual is introduced with a pronoun, models can mostly faithfully reuse this pronoun in the next sentence, but they are significantly worse with she/her/her, singular they and neopronouns. Moreover, models are easily distracted by non-adversarial sentences discussing other people; even one sentence with a distractor pronoun causes accuracy to drop on average by 34 percentage points. Our results show that pronoun fidelity is not robust, in a simple, naturalistic setting where humans achieve nearly 100% accuracy. We encourage researchers to bridge the gaps we find and to carefully evaluate reasoning in settings where superficial repetition might inflate perceptions of model performance.

Jan Kaiser, Annika Eichler, Anne Lauscher

Autonomous tuning of particle accelerators is an active and challenging field of research with the goal of enabling novel accelerator technologies cutting-edge high-impact applications, such as physics discovery, cancer research and material sciences. A key challenge with autonomous accelerator tuning remains that the most capable algorithms require an expert in optimisation, machine learning or a similar field to implement the algorithm for every new tuning task. In this work, we propose the use of large language models (LLMs) to tune particle accelerators. We demonstrate on a proof-of-principle example the ability of LLMs to successfully and autonomously tune a particle accelerator subsystem based on nothing more than a natural language prompt from the operator, and compare the performance of our LLM-based solution to state-of-the-art optimisation algorithms, such as Bayesian optimisation (BO) and reinforcement learning-trained optimisation (RLO). In doing so, we also show how LLMs can perform numerical optimisation of a highly non-linear real-world objective function. Ultimately, this work represents yet another complex task that LLMs are capable of solving and promises to help accelerate the deployment of autonomous tuning algorithms to the day-to-day operations of particle accelerators.

Rochelle Choenni, Anne Lauscher, Ekaterina Shutova

Texts written in different languages reflect different culturally-dependent beliefs of their writers. Thus, we expect multilingual LMs (MLMs), that are jointly trained on a concatenation of text in multiple languages, to encode different cultural values for each language. Yet, as the 'multilinguality' of these LMs is driven by cross-lingual sharing, we also have reason to belief that cultural values bleed over from one language into another. This limits the use of MLMs in practice, as apart from being proficient in generating text in multiple languages, creating language technology that can serve a community also requires the output of LMs to be sensitive to their biases (Naous et al., 2023). Yet, little is known about how cultural values emerge and evolve in MLMs (Hershcovich et al., 2022a). We are the first to study how languages can exert influence on the cultural values encoded for different test languages, by studying how such values are revised during fine-tuning. Focusing on the fine-tuning stage allows us to study the interplay between value shifts when exposed to new linguistic experience from different data sources and languages. Lastly, we use a training data attribution method to find patterns in the fine-tuning examples, and the languages that they come from, that tend to instigate value shifts.

Florian Schneider, Carolin Holtermann, Chris Biemann et al.

Large Vision-Language Models (LVLMs) have recently gained attention due to their distinctive performance and broad applicability. While it has been previously shown that their efficacy in usage scenarios involving non-Western contexts falls short, existing studies are limited in scope, covering just a narrow range of cultures, focusing exclusively on a small number of cultural aspects, or evaluating a limited selection of models on a single task only. Towards globally inclusive LVLM research, we introduce GIMMICK, an extensive multimodal benchmark designed to assess a broad spectrum of cultural knowledge across 144 countries representing six global macro-regions. GIMMICK comprises six tasks built upon three new datasets that span 728 unique cultural events or facets on which we evaluated 20 LVLMs and 11 LLMs, including five proprietary and 26 open-weight models of all sizes. We systematically examine (1) regional cultural biases, (2) the influence of model size, (3) input modalities, and (4) external cues. Our analyses reveal strong biases toward Western cultures across models and tasks and highlight strong correlations between model size and performance, as well as the effectiveness of multimodal input and external geographic cues. We further find that models have more knowledge of tangible than intangible aspects (e.g., food vs. rituals) and that they excel in recognizing broad cultural origins but struggle with a more nuanced understanding.

Carolin Holtermann, Markus Frohmann, Navid Rekabsaz et al.

The knowledge encapsulated in a model is the core factor determining its final performance on downstream tasks. Much research in NLP has focused on efficient methods for storing and adapting different types of knowledge, e.g., in dedicated modularized structures, and on how to effectively combine these, e.g., by learning additional parameters. However, given the many possible options, a thorough understanding of the mechanisms involved in these compositions is missing, and hence it remains unclear which strategies to utilize. To address this research gap, we propose a novel framework for zero-shot module composition, which encompasses existing and some novel variations for selecting, weighting, and combining parameter modules under a single unified notion. Focusing on the scenario of domain knowledge and adapter layers, our framework provides a systematic unification of concepts, allowing us to conduct the first comprehensive benchmarking study of various zero-shot knowledge composition strategies. In particular, we test two module combination methods and five selection and weighting strategies for their effectiveness and efficiency in an extensive experimental setup. Our results highlight the efficacy of ensembling but also hint at the power of simple though often-ignored weighting methods. Further in-depth analyses allow us to understand the role of weighting vs. top-k selection, and show that, to a certain extent, the performance of adapter composition can even be predicted.

Carolin Holtermann, Paul Röttger, Anne Lauscher

Reasoning over time and space is essential for understanding our world. However, the abilities of language models in this area are largely unexplored as previous work has tested their abilities for logical reasoning in terms of time and space in isolation or only in simple or artificial environments. In this paper, we present the first evaluation of the ability of language models to jointly reason over time and space. To enable our analysis, we create GeoTemp, a dataset of 320k prompts covering 289 cities in 217 countries and 37 time zones. Using GeoTemp, we evaluate eight open chat models of three different model families for different combinations of temporal and geographic knowledge. We find that most models perform well on reasoning tasks involving only temporal knowledge and that overall performance improves with scale. However, performance remains constrained in tasks that require connecting temporal and geographical information. We do not find clear correlations of performance with specific geographic regions. Instead, we find a significant performance increase for location names with low model perplexity, suggesting their repeated occurrence during model training. We further demonstrate that their performance is heavily influenced by prompt formulation - a direct injection of geographical knowledge leads to performance gains, whereas, surprisingly, techniques like chain-of-thought prompting decrease performance on simpler tasks.

Beatrice Savoldi, Giuseppe Attanasio, Eleonora Cupin et al.

Avoiding the propagation of undue (binary) gender inferences and default masculine language remains a key challenge towards inclusive multilingual technologies, particularly when translating into languages with extensive gendered morphology. Gender-neutral translation (GNT) represents a linguistic strategy towards fairer communication across languages. However, research on GNT is limited to a few resources and language pairs. To address this gap, we introduce mGeNTE, an expert-curated resource, and use it to conduct the first systematic multilingual evaluation of inclusive translation with state-of-the-art instruction-following language models (LMs). Experiments on en-es/de/it/el reveal that while models can recognize when neutrality is appropriate, they cannot consistently produce neutral translations, limiting their usability. To probe this behavior, we enrich our evaluation with interpretability analyses that identify task-relevant features and offer initial insights into the internal dynamics of LM-based GNT.

Henning Wachsmuth, Gabriella Lapesa, Elena Cabrio et al.

The computational treatment of arguments on controversial issues has been subject to extensive NLP research, due to its envisioned impact on opinion formation, decision making, writing education, and the like. A critical task in any such application is the assessment of an argument's quality - but it is also particularly challenging. In this position paper, we start from a brief survey of argument quality research, where we identify the diversity of quality notions and the subjectiveness of their perception as the main hurdles towards substantial progress on argument quality assessment. We argue that the capabilities of instruction-following large language models (LLMs) to leverage knowledge across contexts enable a much more reliable assessment. Rather than just fine-tuning LLMs towards leaderboard chasing on assessment tasks, they need to be instructed systematically with argumentation theories and scenarios as well as with ways to solve argument-related problems. We discuss the real-world opportunities and ethical issues emerging thereby.

Andreas Waldis, Vagrant Gautam, Anne Lauscher et al.

We introduce aligned probing, a novel interpretability framework that aligns the behavior of language models (LMs), based on their outputs, and their internal representations (internals). Using this framework, we examine over 20 OLMo, Llama, and Mistral models, bridging behavioral and internal perspectives for toxicity for the first time. Our results show that LMs strongly encode information about the toxicity level of inputs and subsequent outputs, particularly in lower layers. Focusing on how unique LMs differ offers both correlative and causal evidence that they generate less toxic output when strongly encoding information about the input toxicity. We also highlight the heterogeneity of toxicity, as model behavior and internals vary across unique attributes such as Threat. Finally, four case studies analyzing detoxification, multi-prompt evaluations, model quantization, and pre-training dynamics underline the practical impact of aligned probing with further concrete insights. Our findings contribute to a more holistic understanding of LMs, both within and beyond the context of toxicity.

Gregor Geigle, Florian Schneider, Carolin Holtermann et al.

Most Large Vision-Language Models (LVLMs) to date are trained predominantly on English data, which makes them struggle to understand non-English input and fail to generate output in the desired target language. Existing efforts mitigate these issues by adding multilingual training data, but do so in a largely ad-hoc manner, lacking insight into how different training mixes tip the scale for different groups of languages. In this work, we present a comprehensive investigation into the training strategies for massively multilingual LVLMs. First, we conduct a series of multi-stage experiments spanning 13 downstream vision-language tasks and 43 languages, systematically examining: (1) the number of training languages that can be included without degrading English performance and (2) optimal language distributions of pre-training as well as (3) instruction-tuning data. Further, we (4) investigate how to improve multilingual text-in-image understanding, and introduce a new benchmark for the task. Surprisingly, our analysis reveals that one can (i) include as many as 100 training languages simultaneously (ii) with as little as 25-50\% of non-English data, to greatly improve multilingual performance while retaining strong English performance. We further find that (iii) including non-English OCR data in pre-training and instruction-tuning is paramount for improving multilingual text-in-image understanding. Finally, we put all our findings together and train Centurio, a 100-language LVLM, offering state-of-the-art performance in an evaluation covering 14 tasks and 56 languages.

Marlene Lutz, Rochelle Choenni, Markus Strohmaier et al.

Stereotypical bias encoded in language models (LMs) poses a threat to safe language technology, yet our understanding of how bias manifests in the parameters of LMs remains incomplete. We introduce local contrastive editing that enables the localization and editing of a subset of weights in a target model in relation to a reference model. We deploy this approach to identify and modify subsets of weights that are associated with gender stereotypes in LMs. Through a series of experiments, we demonstrate that local contrastive editing can precisely localize and control a small subset (< 0.5%) of weights that encode gender bias. Our work (i) advances our understanding of how stereotypical biases can manifest in the parameter space of LMs and (ii) opens up new avenues for developing parameter-efficient strategies for controlling model properties in a contrastive manner.

Saad Obaid ul Islam, Anne Lauscher, Goran Glavaš

Large language models (LLMs) can correctly answer "When was Einstein born?" yet fail to provide the same date when writing about Einstein's life revealing a fundamental inconsistency in how models access factual knowledge across task complexities. While models display impressive accuracy on factual question-answering benchmarks, the reliability gap between simple and complex queries remains poorly understood, eroding their trustworthiness. In this work, we introduce Short-Long Form Alignment for Factual Question Answering (SLAQ), a controlled evaluation framework that compares LLMs' answers to the same factual questions asked (a) in isolation (short) vs. (b) integrated into complex queries (long). Looking at 16 LLMs across 600 queries, we find a systematic misalignment of answers to the corresponding short and long queries. We further uncover position-dependent accuracy loss and momentum effects where consecutive correct or incorrect answers create self-reinforcing patterns. Through mechanistic analysis, we find that aligned facts activate overlapping model internals, and that metrics based on mechanistic similarity can predict short-long answer alignment with up to 78% accuracy. Our work establishes factual consistency over query complexity as an important aspect of LLMs' trustworthiness and challenges current evaluation practices, which implicitly assume that good performance for simple factual queries implies reliability in more complex knowledge-seeking tasks too.

Yujie Ren, Niklas Gruhlke, Anne Lauscher

As large language models (LLMs) are increasingly applied in sensitive domains such as medicine and law, hallucination detection has become a critical task. Although numerous benchmarks have been proposed to advance research in this area, most of them are artificially constructed--either through deliberate hallucination induction or simulated interactions--rather than derived from genuine LLM-human dialogues. Consequently, these benchmarks fail to fully capture the characteristics of hallucinations that occur in real-world usage. To address this limitation, we introduce AuthenHallu, the first hallucination detection benchmark built entirely from authentic LLM-human interactions. For AuthenHallu, we select and annotate samples from genuine LLM-human dialogues, thereby providing a faithful reflection of how LLMs hallucinate in everyday user interactions. Statistical analysis shows that hallucinations occur in 31.4% of the query-response pairs in our benchmark, and this proportion increases dramatically to 60.0% in challenging domains such as Math & Number Problems. Furthermore, we explore the potential of using vanilla LLMs themselves as hallucination detectors and find that, despite some promise, their current performance remains insufficient in real-world scenarios.

Minh Duc Bui, Carolin Holtermann, Valentin Hofmann et al.

Dialects represent a significant component of human culture and are found across all regions of the world. In Germany, more than 40% of the population speaks a regional dialect (Adler and Hansen, 2022). However, despite cultural importance, individuals speaking dialects often face negative societal stereotypes. We examine whether such stereotypes are mirrored by large language models (LLMs). We draw on the sociolinguistic literature on dialect perception to analyze traits commonly associated with dialect speakers. Based on these traits, we assess the dialect naming bias and dialect usage bias expressed by LLMs in two tasks: an association task and a decision task. To assess a model's dialect usage bias, we construct a novel evaluation corpus that pairs sentences from seven regional German dialects (e.g., Alemannic and Bavarian) with their standard German counterparts. We find that: (1) in the association task, all evaluated LLMs exhibit significant dialect naming and dialect usage bias against German dialect speakers, reflected in negative adjective associations; (2) all models reproduce these dialect naming and dialect usage biases in their decision making; and (3) contrary to prior work showing minimal bias with explicit demographic mentions, we find that explicitly labeling linguistic demographics--German dialect speakers--amplifies bias more than implicit cues like dialect usage.

Sascha Diefenbacher, Anna Hallin, Gregor Kasieczka et al.

The substantial data volumes encountered in modern particle physics and other domains of fundamental physics research allow (and require) the use of increasingly complex data analysis tools and workflows. While the use of machine learning (ML) tools for data analysis has recently proliferated, these tools are typically special-purpose algorithms that rely, for example, on encoded physics knowledge to reach optimal performance. In this work, we investigate a new and orthogonal direction: Using recent progress in large language models (LLMs) to create a team of agents -- instances of LLMs with specific subtasks -- that jointly solve data analysis-based research problems in a way similar to how a human researcher might: by creating code to operate standard tools and libraries (including ML systems) and by building on results of previous iterations. If successful, such agent-based systems could be deployed to automate routine analysis components to counteract the increasing complexity of modern tool chains. To investigate the capabilities of current-generation commercial LLMs, we consider the task of anomaly detection via the publicly available and highly-studied LHC Olympics dataset. Several current models by OpenAI (GPT-4o, o4-mini, GPT-4.1, and GPT-5) are investigated and their stability tested. Overall, we observe the capacity of the agent-based system to solve this data analysis problem. The best agent-created solutions mirror the performance of human state-of-the-art results.

Antonia Karamolegkou, Sandrine Schiller Hansen, Ariadni Christopoulou et al.

What ethical concerns, if any, do LLM researchers have? We introduce EthiCon, a corpus of 1,580 ethical concern statements extracted from scientific papers published in the ACL Anthology. We extract ethical concern keywords from the statements and show promising results in automating the concern identification process. Through a survey, we compare the ethical concerns of the corpus to the concerns listed by the general public and professionals in the field. Finally, we compare our retrieved ethical concerns with existing taxonomies pointing to gaps and future research directions.

Eddie L. Ungless, Björn Ross, Anne Lauscher

Cutting-edge image generation has been praised for producing high-quality images, suggesting a ubiquitous future in a variety of applications. However, initial studies have pointed to the potential for harm due to predictive bias, reflecting and potentially reinforcing cultural stereotypes. In this work, we are the first to investigate how multimodal models handle diverse gender identities. Concretely, we conduct a thorough analysis in which we compare the output of three image generation models for prompts containing cisgender vs. non-cisgender identity terms. Our findings demonstrate that certain non-cisgender identities are consistently (mis)represented as less human, more stereotyped and more sexualised. We complement our experimental analysis with (a)~a survey among non-cisgender individuals and (b) a series of interviews, to establish which harms affected individuals anticipate, and how they would like to be represented. We find respondents are particularly concerned about misrepresentation, and the potential to drive harmful behaviours and beliefs. Simple heuristics to limit offensive content are widely rejected, and instead respondents call for community involvement, curated training data and the ability to customise. These improvements could pave the way for a future where change is led by the affected community, and technology is used to positively ``[portray] queerness in ways that we haven't even thought of'' rather than reproducing stale, offensive stereotypes.