Psy-CoT decomposes reasoning into Interaction Perception, Psychological Empathy, and Logical Construction while RAPO asymmetrically weights role-specific tokens during policy optimization, outperforming prior CoT and GRPO baselines on role-playing benchmarks.
InProceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, pages 14017–14046, Bangkok, Thailand
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
StratMem-Bench reveals that state-of-the-art LLMs distinguish required from irrelevant memories effectively but struggle to integrate supportive memories in character conversations.
Introduces PAS and FAS task abstractions plus the LLM-S^3 benchmark to evaluate LLMs on generating sociodemographic survey responses across 11 real datasets and multiple models.
LLMs exhibit persistent inertia in value orientations, with harm avoidance and fairness remaining skewed across persona prompts.
citing papers explorer
-
Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
Psy-CoT decomposes reasoning into Interaction Perception, Psychological Empathy, and Logical Construction while RAPO asymmetrically weights role-specific tokens during policy optimization, outperforming prior CoT and GRPO baselines on role-playing benchmarks.
-
StratMem-Bench: Evaluating Strategic Memory Use in Virtual Character Conversation Beyond Factual Recall
StratMem-Bench reveals that state-of-the-art LLMs distinguish required from irrelevant memories effectively but struggle to integrate supportive memories in character conversations.
-
Inertia in Moral and Value Judgments of Large Language Models
LLMs exhibit persistent inertia in value orientations, with harm avoidance and fairness remaining skewed across persona prompts.