From Stimuli to Minds: Enhancing Psychological Reasoning in LLMs via Bilateral Reinforcement Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911260408283136 |
|---|---|
| author | Feng, Yichao Luo, Haoran Feng, Lang Zhao, Shuai Luu, Anh Tuan |
| author_facet | Feng, Yichao Luo, Haoran Feng, Lang Zhao, Shuai Luu, Anh Tuan |
| contents | Large Language Models show promise in emotion understanding, social reasoning, and empathy, yet they struggle with psychologically grounded tasks that require inferring implicit mental states in context-rich, ambiguous settings. These limitations arise from the absence of theory-aligned supervision and the difficulty of capturing nuanced mental processes in real-world narratives. To address this gap, we leverage expert-labeled, psychologically rich scenarios and propose a trajectory-aware reinforcement learning framework that explicitly imitates expert psychological thought patterns. By integrating real-world stimuli with structured reasoning guidance, our approach enables compact models to internalize social-cognitive principles, perform nuanced psychological inference, and support continual self-improvement. Comprehensive experiments across multiple benchmarks further demonstrate that our models achieve expert-level interpretive capabilities, exhibiting strong out-of-distribution generalization and robust continual learning across diverse, challenging, and psychologically grounded tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_02458 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Stimuli to Minds: Enhancing Psychological Reasoning in LLMs via Bilateral Reinforcement Learning Feng, Yichao Luo, Haoran Feng, Lang Zhao, Shuai Luu, Anh Tuan Databases Large Language Models show promise in emotion understanding, social reasoning, and empathy, yet they struggle with psychologically grounded tasks that require inferring implicit mental states in context-rich, ambiguous settings. These limitations arise from the absence of theory-aligned supervision and the difficulty of capturing nuanced mental processes in real-world narratives. To address this gap, we leverage expert-labeled, psychologically rich scenarios and propose a trajectory-aware reinforcement learning framework that explicitly imitates expert psychological thought patterns. By integrating real-world stimuli with structured reasoning guidance, our approach enables compact models to internalize social-cognitive principles, perform nuanced psychological inference, and support continual self-improvement. Comprehensive experiments across multiple benchmarks further demonstrate that our models achieve expert-level interpretive capabilities, exhibiting strong out-of-distribution generalization and robust continual learning across diverse, challenging, and psychologically grounded tasks. |
| title | From Stimuli to Minds: Enhancing Psychological Reasoning in LLMs via Bilateral Reinforcement Learning |
| topic | Databases |
| url | https://arxiv.org/abs/2508.02458 |