用日本对话文化启发多智能体框架，提升情感分析的公平性与可解释性。
A Multi-Agent Probabilistic Inference Framework Inspired by Kairanban-Style CoT System with IdoBata Conversation for Debiasing
- 多智能体协作模拟日本社区对话，融合正式推理与个体观点。
- 推理后期熵降低、方差上升，体现预测多样性与聚合平衡。
- 适合关注模型公平性与可解释性的研究人员参考。
日本的‘会議板’文化与‘いどばた’对话长期作为促进社区成员间细腻交流的传统方式，有助于社会平衡的形成。受此信息交换机制启发，本文提出一种多智能体推理框架（KCS+IBC），整合多个大语言模型，在情感分析中实现去偏、提升可解释性及概率化预测。该方法不仅顺序共享预测结果，还引入中期非正式对话环节，使正式推理与个体视角自然融合，并支持概率情感预测。实验表明，KCS在各数据集上的准确率与单个LLM相当；而KCS+IBC在推理后期呈现熵持续下降、方差逐步上升的趋势，表明框架具备平衡预测聚合与多样性的能力。未来工作将定量评估这些特性对去偏效果的影响，并致力于构建更先进的情感分析系统。
原文摘要 · Abstract (English)
Japan's kairanban culture and idobata conversations have long functioned as traditional communication practices that foster nuanced dialogue among community members and contribute to the formation of social balance. Inspired by these information exchange processes, this study proposes a multi-agent inference framework (KCS+IBC) that integrates multiple large language models (LLMs) to achieve bias mitigation, improved explainability, and probabilistic prediction in sentiment analysis. In addition to sequentially sharing prediction results, the proposed method incorporates a mid-phase casual dialogue session to blend formal inference with individual perspectives and introduces probabilistic sentiment prediction. Experimental results show that KCS achieves accuracy comparable to that of a single LLM across datasets, while KCS+IBC exhibits a consistent decrease in entropy and a gradual increase in variance during the latter stages of inference, suggesting the framework's ability to balance aggregation and diversity of predictions. Future work will quantitatively assess the impact of these characteristics on bias correction and aim to develop more advanced sentiment analysis systems.
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。