11 citations · 26 across the 45 of their papers we have counts for
51 papers
Personality Anchoring for Social Simulation: Linking Personality, Social Behavior, and Interaction Success with LLM Agents
Vahid Sadiri Javadi, Aksa Aksa, Fryderyk Róg +2
Social interactions are shaped by the interplay of dispositional traits and situational context, yet systematically investigating how personality configurations between individuals…
Reinforcement Learning Can Amplify Emergent Misalignment from Harmless Rewards
Magnus Jørgenvåg, David Kaczér, Lasse Ruttert +3
Emergent misalignment (EM) is the surprising tendency of language models to become broadly misaligned after fine-tuning on narrowly misaligned examples. While EM has been extensive…
Shapes are not enough: CONSERVAttack and its use for finding vulnerabilities and uncertainties in machine learning applications
Philip Bechtle, Lucie Flek, Philipp Alexander Jung +7
In High Energy Physics, as in many other fields of science, the application of machine learning techniques has been crucial in advancing our understanding of fundamental phenomena.…
Plausible but Wrong: A case study on Agentic Failures in Astrophysical Workflows
Shivam Rawat, Lucie Flek
Agentic AI systems are increasingly being integrated into scientific workflows, yet their behavior under realistic conditions remains insufficiently understood. We evaluate CMBAgen…
Can LLM Agents Identify Spoken Dialects like a Linguist?
Tobias Bystrich, Lukas Hamm, Maria Hassan +3
Due to the scarcity of labeled dialectal speech, audio dialect classification is a challenging task for most languages, including Swiss German. In this work, we explore the ability…
Conspiracy Frame: a Semiotically-Driven Approach for Conspiracy Theories Detection
Heidi Campana Piva, Shaina Ashraf, Maziar Kianimoghadam Jouneghani +4
Conspiracy theories are anti-authoritarian narratives that lead to social conflict, impacting how people perceive political information. To help in understanding this issue, we int…
Label-Consistent Data Generation for Aspect-Based Sentiment Analysis Using LLM Agents
Mohammad H. A. Monfared, Lucie Flek, Akbar Karimi
We propose an agentic data augmentation method for Aspect-Based Sentiment Analysis (ABSA) that uses iterative generation and verification to produce high quality synthetic training…
PERSPECTRA: A Scalable and Configurable Pluralist Benchmark of Perspectives from Arguments
Shangrui Nie, Kian Omoomi, Lucie Flek +2
Pluralism, the capacity to engage with diverse perspectives without collapsing them into a single viewpoint, is critical for developing large language models that faithfully reflec…
Encoder Fine-tuning with Stochastic Sampling Outperforms Open-weight GPT in Astronomy Knowledge Extraction
Shivam Rawat, Lucie Flek, Akbar Karimi
Scientific literature in astronomy is rapidly expanding, making it increasingly important to automate the extraction of key entities and contextual information from research papers…
More Agents Improve Math Problem Solving but Adversarial Robustness Gap Persists
Khashayar Alavi, Zhastay Yeltay, Lucie Flek +1
When LLM agents work together, they seem to be more powerful than a single LLM in mathematical question answering. However, are they also more robust to adversarial inputs? We inve…
MiniFool -- Physics-Constraint-Aware Minimizer-Based Adversarial Attacks in Deep Neural Networks
Lucie Flek, Oliver Janik, Philipp Alexander Jung +8
In this paper, we present a new algorithm, MiniFool, that implements physics-inspired adversarial attacks for testing neural network-based classification tasks in particle and astr…
Zoom In Disparities in Healthcare LLM Q&A
Ipek Baris Schlicht, Burcu Sayin, Zhixue Zhao +5
Equitable access to reliable health information is vital when integrating AI into healthcare. Yet, information quality varies across languages, raising concerns about the reliabili…
ISCA: A Framework for Interview-Style Conversational Agents
Charles Welch, Allison Lahnala, Vasudha Varadarajan +4
We present a low-compute non-generative system for implementing interview-style conversational agents which can be used to facilitate qualitative data collection through controlled…
From Value Conditioning to Behavioral Shift: Lightweight Value Alignment of LLMs
Shangrui Nie, Florian Mai, David Kaczér +3
Large language models exhibit value-related preferences in their outputs, yet steering such behavior often requires large training datasets or paired preference annotations. In thi…
Improving Low-Resource Dialect Classification Using Retrieval-based Voice Conversion
Lea Fischbach, Akbar Karimi, Caroline Kleen +2
Deep learning models for dialect identification are often limited by the scarcity of dialectal data. To address this challenge, we propose to use Retrieval-based Voice Conversion (…
Multi-Hop Reasoning for Question Answering with Hyperbolic Representations
Simon Welz, Lucie Flek, Akbar Karimi
Hyperbolic representations are effective in modeling knowledge graph data which is prevalently used to facilitate multi-hop reasoning. However, a rigorous and detailed comparison o…
Superalignment with Dynamic Human Values
Florian Mai, David Kaczér, Nicholas Kluge Corrêa +1
Two core challenges of alignment are 1) scalable oversight and 2) accounting for the dynamic nature of human values. While solutions like recursive reward modeling address 1), they…
The Muddy Waters of Modeling Empathy in Language: The Practical Impacts of Theoretical Constructs
Allison Lahnala, Charles Welch, David Jurgens +1
Conceptual operationalizations of empathy in NLP are varied, with some having specific behaviors and properties, while others are more abstract. How these variations relate to one…
Do LLMs Provide Consistent Answers to Health-Related Questions across Languages?
Ipek Baris Schlicht, Zhixue Zhao, Burcu Sayin +2
Equitable access to reliable health information is vital for public health, but the quality of online health resources varies by language, raising concerns about inconsistencies in…
Funzac at CoMeDi Shared Task: Modeling Annotator Disagreement from Word-In-Context Perspectives
Olufunke O. Sarumi, Charles Welch, Lucie Flek +1
In this work, we evaluate annotator disagreement in Word-in-Context (WiC) tasks exploring the relationship between contextual meaning and disagreement as part of the CoMeDi shared…
Exploring Robustness of Multilingual LLMs on Real-World Noisy Data
Amirhossein Aliakbarzadeh, Lucie Flek, Akbar Karimi
Large Language Models (LLMs) are trained on Web data that might contain spelling errors made by humans. But do they become robust to similar real-world noise? In this paper, we inv…
Enforcing Fundamental Relations via Adversarial Attacks on Input Parameter Correlations
Timo Saala, Lucie Flek, Alexander Jung +5
Correlations between input parameters play a crucial role in many scientific classification tasks, since these are often related to fundamental laws of nature. For example, in high…
Exploring Robustness of LLMs to Paraphrasing Based on Sociodemographic Factors
Pulkit Arora, Akbar Karimi, Lucie Flek
Despite their linguistic prowess, LLMs have been shown to be vulnerable to small input perturbations. While robustness to local adversarial changes has been studied, robustness to…
ArithmAttack: Evaluating Robustness of LLMs to Noisy Context in Math Problem Solving
Zain Ul Abedin, Shahzeb Qamar, Lucie Flek +1
While Large Language Models (LLMs) have shown impressive capabilities in math problem-solving tasks, their robustness to noisy inputs is not well-studied. We propose ArithmAttack t…