32 papers
When Debiasing Backfires: Counterintuitive Side Effects of Preprocessing-Based Stereotype Mitigation
Yahan Zheng, John Guerrerio, Soroush Vosoughi +1
Preprocessing-based methods for stereotype mitigation, such as pre-/post-training on debiased corpora, are widely used in NLP. While these approaches reduce measurable stereotypes…
Scalable and Culturally Specific Stereotype Dataset Construction via Human-LLM Collaboration
Weicheng Ma, John Guerrerio, Soroush Vosoughi
Research on stereotypes in large language models (LLMs) has largely focused on English-speaking contexts, due to the lack of datasets in other languages and the high cost of manual…
Memory Makes the Difference: Evaluating How Different Memory Roles Shape Conversational Agents
Yuxin Wang, Paul Thomas, Zhiwei Yu +5
Prior research on memory mechanism in RAG-based conversational system has emphasized how memory is stored and retrieved. However, far less is known about how memories with differen…
The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering
Yefan Zhou, Yilun Zhou, Austin Xu +3
Generative verifiers have emerged as a promising paradigm for step-wise verification, but their verification behavior is often poorly calibrated: they may be under-critical and mis…
Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner
Chunhui Zhang, Zhongyu Ouyang, Kwonjoon Lee +4
Theory-of-Mind (ToM) enables humans to infer mental states-such as beliefs, desires, and intentions-forming the foundation of social cognition. However, existing computational ToM…
What Makes LLMs Effective Sequential Recommenders? A Study on Preference Intensity and Temporal Context
Zhongyu Ouyang, Qianlong Wen, Chunhui Zhang +2
What enables large language models (LLMs) to effectively model user preferences in sequential recommendation? Our investigation reveals that existing preference-alignment approache…