34 citations · 103 across the 67 of their papers we have counts for
72 papers
Bias Mitigation in Audio-Enabled LLMs through Adversarial Training and Distillation Methods
Adnan Al Ali, Jindřich Libovický, Anne Lauscher
Audio-enabled large language models (AuLLMs) allow users to interact with them simply by talking to them, without the need for an intermediate transcription. This expands the model…
Making a Name for Myself: On Academic Naming Policies and their Impact
A Pranav, Vagrant Gautam, Martin Mundt +6
In academic publishing, names connect scholars to their work. When scholars change their names, including for marriage, academic recognition, or gender transition, they may lose cr…
PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models
Gianluca Barmina, Federico Torrielli, Sven Harms +7
Large language models (LLMs) routinely face requests that should be refused, creating a trade-off between helpfulness and harm prevention. However, refusals themselves can be helpf…
Epistemic Injustice in Language Models: An Audit of Pretraining Filters and Guardrails
Marco Antonio Stranisci, A Pranav, Rossana Damiano +2
Modern language models rely on pretraining filters to remove undesirable content from training corpora and inference-time guardrails to suppress undesirable outputs during deployme…
GRUFF: LLM Pronoun Fidelity, Reasoning, and Biases in German
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 interp…
Greater accessibility can amplify discrimination in generative AI
Carolin Holtermann, Minh Duc Bui, Kaitlyn Zhou +3
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 pres…
Reviewing the Reviewer: LLM-Assisted Reviewer Feedback Generation for Guideline Compliance
Sukannya Purkayastha, Qile Wan, Anne Lauscher +2
Peer review is central to scientific quality, yet reliance on simple heuristics, namely lazy thinking and non-specific critiques, has threatened review quality. Prior work frames l…
SoS: Analysis of Surface over Semantics in Multilingual Text-To-Image Generation
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 - whe…
TempViz: On the Evaluation of Temporal Knowledge in Text-to-Image Models
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…
Towards Ethical Multi-Agent Systems of Large Language Models: A Mechanistic Interpretability Perspective
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 t…
The Curious Case of Factual (Mis)Alignment between LLMs' Short- and Long-Form Answers
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 inconsisten…
Detecting Hallucinations in Authentic LLM-Human Interactions
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 benchm…
Large Language Models Discriminate Against Speakers of German Dialects
Minh Duc Bui, Carolin Holtermann, Valentin Hofmann +2
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 (Ad…
Agents of Discovery
Sascha Diefenbacher, Anna Hallin, Gregor Kasieczka +3
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 analy…
Decision-Making with Deliberation: Meta-reviewing as a Document-grounded Dialogue
Sukannya Purkayastha, Nils Dycke, Anne Lauscher +1
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-reviewi…
Around the World in 24 Hours: Probing LLM Knowledge of Time and Place
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 th…
LazyReview A Dataset for Uncovering Lazy Thinking in NLP Peer Reviews
Sukannya Purkayastha, Zhuang Li, Anne Lauscher +2
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…
Aligned Probing: Relating Toxic Behavior and Model Internals
Andreas Waldis, Vagrant Gautam, Anne Lauscher +2
We introduce aligned probing, a novel interpretability framework that aligns the behavior of language models (LMs), based on their outputs, and their internal representations (inte…
GIMMICK -- Globally Inclusive Multimodal Multitask Cultural Knowledge Benchmarking
Florian Schneider, Carolin Holtermann, Chris Biemann +1
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 effi…
How Much Do LLMs Hallucinate across Languages? On Realistic Multilingual Estimation of LLM Hallucination
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 glob…
Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation
Steffen Eger, Yong Cao, Jennifer D'Souza +11
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 su…
Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model
Gregor Geigle, Florian Schneider, Carolin Holtermann +4
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 i…
Mind the Inclusivity Gap: Multilingual Gender-Neutral Translation Evaluation with mGeNTE
Beatrice Savoldi, Giuseppe Attanasio, Eleonora Cupin +7
Avoiding the propagation of undue (binary) gender inferences and default masculine language remains a key challenge towards inclusive multilingual technologies, particularly when t…
Ethical Concern Identification in NLP: A Corpus of ACL Anthology Ethics Statements
Antonia Karamolegkou, Sandrine Schiller Hansen, Ariadni Christopoulou +3
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 Ant…