5 papers · 1 filter
Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations
Mingqian Zheng, Malia Morgan, Liwei Jiang +2
Current LLM safety alignment techniques improve model robustness against adversarial attacks, but overlook whether and how LLMs can recover helpfulness when benign users clarify th…
SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions
Xianzhe Fan, Xuhui Zhou, Chuanyang Jin +3
Humans continuously infer the states, goals, and behaviors of others by perceiving their surroundings in dynamic, real-world social interactions. However, most Theory of Mind (ToM)…
Words Like Knives: Backstory-Personalized Modeling and Detection of Violent Communication
Jocelyn Shen, Akhila Yerukola, Xuhui Zhou +3
Conversational breakdowns in close relationships are deeply shaped by personal histories and emotional context, yet most NLP research treats conflict detection as a general task, o…
Breaking mBad! Supervised Fine-tuning for Cross-Lingual Detoxification
Himanshu Beniwal, Youngwoo Kim, Maarten Sap +2
As large language models (LLMs) become increasingly prevalent in global applications, ensuring that they are toxicity-free across diverse linguistic contexts remains a critical cha…
Medical Hallucinations in Foundation Models and Their Impact on Healthcare
Yubin Kim, Hyewon Jeong, Shan Chen +24
Hallucinations in foundation models arise from autoregressive training objectives that prioritize token-likelihood optimization over epistemic accuracy, fostering overconfidence an…