让大模型像人一样社交思考，通过认知流程理解模糊情境
Think Socially via Cognitive Reasoning
- 构建树状思维结构模拟人类社会认知过程
- 在多个社交任务上显著提升推理与回应质量
- 适合需要共情与情境理解的对话系统研发
训练用于逻辑推理的大语言模型擅长逐步推导得出可验证答案，但这一范式不适用于处理社会情境——后者依赖对模糊线索的解读，通常无确定结论。为此，我们提出基于人类社会认知的‘认知推理’范式，将解释过程建模为相互关联的认知单元（如观察、归因）构成的结构化认知流，并自适应组合以实现有效社交思考。我们进一步提出 CogFlow 框架，通过树状规划生成认知流数据集，经监督微调赋予基础能力后，采用多目标强化学习让模型通过试错自我优化，奖励函数同时兼顾认知流合理性和回应质量。大量实验表明，CogFlow 显著增强大模型及人类的社交认知能力，提升社会决策有效性。
原文摘要 · Abstract (English)
LLMs trained for logical reasoning excel at step-by-step deduction to reach verifiable answers. However, this paradigm is ill-suited for navigating social situations, which induce an interpretive process of analyzing ambiguous cues that rarely yield a definitive outcome. To bridge this gap, we introduce Cognitive Reasoning, a paradigm modeled on human social cognition. It formulates the interpretive process into a structured cognitive flow of interconnected cognitive units (e.g., observation or attribution), which combine adaptively to enable effective social thinking and responses. We then propose CogFlow, a complete framework that instills this capability in LLMs. CogFlow first curates a dataset of cognitive flows by simulating the associative and progressive nature of human thought via tree-structured planning. After instilling the basic cognitive reasoning capability via supervised fine-tuning, CogFlow adopts reinforcement learning to enable the model to improve itself via trial and error, guided by a multi-objective reward that optimizes both cognitive flow and response quality. Extensive experiments show that CogFlow effectively enhances the social cognitive capabilities of LLMs, and even humans, leading to more effective social decision-making.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。