用主观图模型模拟课堂社交认知偏差，揭示信息不透明如何导致成绩误判。
Subjective-Graph LLM Agents for Simulating Uncertainty in Classroom Social Perception
- 每个学生基于个人化社交图获取信息，影响对他人成绩的判断。
- 六轮考试后集体排名误差从0.066升至0.124，说明认知偏差持续存在。
- 适合研究教育公平、群体认知偏差或社会感知建模的学者参考。
社交个体并不共享同一社会世界：每个人基于对周围网络的部分且可能失真的视角形成判断。我们研究图局部证据与可信度加权通信是否能在反复接收客观表现信号的情况下，引发持久的认知扭曲。提出一种数据受限的多智能体框架，其中大模型（LLM）代理通过个性化主观图决定同伴可见性、证据获取和互动机会。代理交换带不确定性的评估，评估消息可信度，并通过贝叶斯融合更新显式的高斯信念状态。在包含482名学生的12个中学班级上进行评估，使用问卷获取的社会信息和六次连续考试成绩。在社会观测子集（n=419）上，尽管有考试锚定，集体排名误差在六轮中从0.066±0.008增至0.124±0.009。消融实验表明，个性化可见性和基于LLM的信任门控带来更稳定长期行为，而受限检索主要防止全局信息泄露。相比测试的DeGroot模型，该框架最终排名误差更低；而后者终端意见多样性趋近于零。这些结果确立了主观图LLM代理作为数据受限社会感知仿真的机制导向框架。代码已公开于https://anonymous.4open.science/r/Rashomonomon-0126。
原文摘要 · Abstract (English)
Social actors do not observe a common social world: each individual forms judgments from a partial and potentially distorted view of the surrounding network. We study whether graph-local evidence and credibility-weighted communication can generate persistent distortions in perceived academic standing, even when agents repeatedly receive objective performance signals. We introduce a data-constrained multi-agent framework in which LLM agents operate through individualized subjective graphs that determine peer visibility, evidence access, and interaction opportunities. Agents exchange uncertainty-annotated assessments, evaluate message credibility, and maintain explicit Gaussian belief states updated through Bayesian fusion. We evaluate the framework on 12 middle-school classrooms comprising 482 students, using questionnaire-derived social information and six consecutive examinations. On the Social-Observed subset (n=419), collective ranking error increases from 0.066 \pm 0.008 to 0.124 \pm 0.009 across six epochs despite repeated exam-based anchoring. Ablations associate individualized visibility and LLM-based trust gating with more stable long-horizon behavior, while constrained retrieval primarily safeguards against global-information leakage. Compared with evaluated DeGroot configurations, the proposed framework achieves lower final ranking error; those DeGroot configurations exhibit near-zero terminal opinion diversity. These findings establish subjective-graph LLM agents as a mechanism-oriented framework for data-constrained simulated social perception. Code is available at https://anonymous.4open.science/r/Rashomonomon-0126.
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。