27 papers
StabilityBench: Benchmarking Instability in LLMs
Emma Kondrup, Zachary Yang, Anne Imouza +1
AI Assistants are increasingly deployed in high-stakes settings, such as healthcare or government services. Yet their real-world behavior remains poorly understood due to strong co…
CrediBench: Building Web-Scale Network Datasets for Information Integrity
Emma Kondrup, Sebastian Sabry, Hussein Abdallah +9
Automatically assessing the credibility of online sources presents an invaluable tool for navigating today's information ecosystem. However, existing approaches either depend on sc…
EASE Configuration Facilitates A Reproducible Science of LLM Social Simulations
Sneheel Sarangi, Maximilian Puelma Touzel, Aurélien Bück-Kaeffer +3
LLMs are increasingly deployed to simulate social interactions, yet many of the existing simulators remain ad hoc and monolithic. This lack of architectural standardization prevent…
RL Fine-Tuning Heals OOD Forgetting in SFT
Hangzhan Jin, Sitao Luan, Tianwei Ni +5
Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) is a standard post-training recipe for improving Large Language Models (LLM) reasoning, but why it works remain…
Kurtosis-Guided Denoising Score Matching for Tabular Anomaly Detection
Victor Livernoche, Jie Zan, Reihaneh Rabbany
Denoising score matching (DSM) provides a way to learn data distributions by training a neural network to recover the score function, defined as the gradient of the log density, fr…
ControBench: An Interaction-Aware Benchmark for Controversial Discourse Analysis on Social Networks
Ta Thanh Thuy, Jiaqi Zhu, Xuan Liu +6
Understanding how people argue across ideological divides online is important for studying political polarization, misinformation, and content moderation. Existing datasets capture…