Anne Lauscher
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Anne Lauscher has a total of 94 co-authors. Here are the top co-authors by number of shared publications:
Simone Paolo Ponzetto
Data and Web Science Group University of Mannheim Germany
6 shared publications- Dirk Hovy
Bocconi University Milan Italy
5 shared publications Goran Glavaš
5 shared publicationsKai Eckert
Stuttgart Media University, Stuttgart, Germany
4 shared publications- Karina Vida
Data Science Group, University of Hamburg
4 shared publications - Rochelle Choenni
University of Amsterdam University of Edinburgh
4 shared publications
Latest Publications
- Open Access
- 29 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 59 (1) , 1-36
Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation
With the advent of large multimodal language models, science is now at a threshold of an AI-based technological transformation. An emerging ecosystem of models and tools aims to support researchers throughout the scientific lifecycle, including (1) searching for relevant literature, (2) generating research ideas and conducting experiments, (3) producing text-based content, (4) creating multimodal artifacts such as figures and diagrams, and (5) evaluating scientific work, as in peer review. In this survey, we provide a curated overview of literature representative of the core techniques, evaluation practices, and emerging trends in AI-assisted scientific discovery. Across the five tasks outlined above, we discuss datasets, methods, results, evaluation strategies, limitations, and ethical concerns, including risks to research integrity through the misuse of generative models. We aim for this survey to serve both as an accessible, structured orientation for newcomers to the field, as well as a catalyst for new AI-based initiatives and their integration into future “AI4Science” systems.
- 29 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 59 (1) , 1-36
Open AccessTransforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation
With the advent of large multimodal language models, science is now at a threshold of an AI-based technological transformation. An emerging ecosystem of models and tools aims to support researchers throughout the scientific lifecycle, including (1) searching for relevant literature, (2) generating research ideas and conducting experiments, (3) producing text-based content, (4) creating multimodal artifacts such as figures and diagrams, and (5) evaluating scientific work, as in peer review. In this survey, we provide a curated overview of literature representative of the core techniques, evaluation practices, and emerging trends in AI-assisted scientific discovery. Across the five tasks outlined above, we discuss datasets, methods, results, evaluation strategies, limitations, and ethical concerns, including risks to research integrity through the misuse of generative models. We aim for this survey to serve both as an accessible, structured orientation for newcomers to the field, as well as a catalyst for new AI-based initiatives and their integration into future “AI4Science” systems.
- Open Access
- 25 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 6254-6279
Making a Name for Myself : On Academic Naming Policies and their Impact
- 25 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 6254-6279
Open AccessMaking a Name for Myself : On Academic Naming Policies and their Impact
- Open Access
Towards Ethical Multi-Agent Systems of Large Language Models: A Mechanistic Interpretability Perspective
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.
Open AccessTowards Ethical Multi-Agent Systems of Large Language Models: A Mechanistic Interpretability Perspective
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.
- Open Access
- 3 January 2025
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 11 (1) , eadr4173
Large language models for human-machine collaborative particle accelerator tuning through natural language
Autonomous tuning of particle accelerators is an active and challenging research field with the goal of enabling advanced accelerator technologies and cutting-edge high-impact applications, such as physics discovery, cancer research, and material sciences. A challenge with autonomous accelerator tuning remains that the most capable algorithms require experts in optimization and machine learning to implement them for every new tuning task. Here, 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 tune an accelerator subsystem based on only a natural language prompt from the operator, and compare their performance to state-of-the-art optimization algorithms, such as Bayesian optimization and reinforcement learning–trained optimization. In doing so, we also show how LLMs can perform numerical optimization of a nonlinear real-world objective. Ultimately, this work represents another complex task that LLMs can solve and promises to help accelerate the deployment of autonomous tuning algorithms to day-to-day particle accelerator operations.
- 3 January 2025
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 11 (1) , eadr4173
Open AccessLarge language models for human-machine collaborative particle accelerator tuning through natural language
Autonomous tuning of particle accelerators is an active and challenging research field with the goal of enabling advanced accelerator technologies and cutting-edge high-impact applications, such as physics discovery, cancer research, and material sciences. A challenge with autonomous accelerator tuning remains that the most capable algorithms require experts in optimization and machine learning to implement them for every new tuning task. Here, 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 tune an accelerator subsystem based on only a natural language prompt from the operator, and compare their performance to state-of-the-art optimization algorithms, such as Bayesian optimization and reinforcement learning–trained optimization. In doing so, we also show how LLMs can perform numerical optimization of a nonlinear real-world objective. Ultimately, this work represents another complex task that LLMs can solve and promises to help accelerate the deployment of autonomous tuning algorithms to day-to-day particle accelerator operations.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 29065-29086
How Much Do LLMs Hallucinate across Languages? On Realistic Multilingual Estimation of LLM Hallucination
Saad Obaid Ul Islam, Anne Lauscher, Goran Glavaš. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 29065-29086
Open AccessHow Much Do LLMs Hallucinate across Languages? On Realistic Multilingual Estimation of LLM Hallucination
Saad Obaid Ul Islam, Anne Lauscher, Goran Glavaš. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 18450-18477
Glitter: A Multi-Sentence, Multi-Reference Benchmark for Gender-Fair German Machine Translation
A Pranav, Janiça Hackenbuchner, Giuseppe Attanasio, Manuel Lardelli, Anne Lauscher. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 18450-18477
Open AccessGlitter: A Multi-Sentence, Multi-Reference Benchmark for Gender-Fair German Machine Translation
A Pranav, Janiça Hackenbuchner, Giuseppe Attanasio, Manuel Lardelli, Anne Lauscher. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 24525-24542
FineCite: A Novel Approach For Fine-Grained Citation Context Analysis
Lasse M. Jantsch, Dong-Jae Koh, Seonghwan Yoon, Jisu Lee, Anne Lauscher, Young-Kyoon Suh. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 24525-24542
Open AccessFineCite: A Novel Approach For Fine-Grained Citation Context Analysis
Lasse M. Jantsch, Dong-Jae Koh, Seonghwan Yoon, Jisu Lee, Anne Lauscher, Young-Kyoon Suh. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- Top Cited PapersOpen Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 9714-9731
Multi3Hate: Multimodal, Multilingual, and Multicultural Hate Speech Detection with Vision–Language Models
Minh Duc Bui, Katharina Von Der Wense, Anne Lauscher. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 9714-9731
Top Cited PapersOpen AccessMulti3Hate: Multimodal, Multilingual, and Multicultural Hate Speech Detection with Vision–Language Models
Minh Duc Bui, Katharina Von Der Wense, Anne Lauscher. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.
- Open Access
Local Contrastive Editing of Gender Stereotypes
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.
Open AccessLocal Contrastive Editing of Gender Stereotypes
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.
- Open Access
- 16 October 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society
- Vol. 7, 1490-1501
Decoding Multilingual Moral Preferences: Unveiling LLM's Biases through the Moral Machine Experiment
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.
- 16 October 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society
- Vol. 7, 1490-1501
Open AccessDecoding Multilingual Moral Preferences: Unveiling LLM's Biases through the Moral Machine Experiment
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.