A Multi-Agent Probabilistic Inference Framework Inspired by Kairanban-Style CoT System with IdoBata Conversation for Debiasing

TL;DR

This paper introduces a multi-agent inference framework inspired by Japanese cultural communication practices, combining multiple large language models to enhance sentiment analysis through bias mitigation, explainability, and probabilistic prediction.

Contribution

It presents a novel multi-agent framework (KCS+IBC) that integrates LLMs with casual dialogue to improve sentiment analysis and reduce bias, inspired by traditional Japanese communication methods.

Findings

KCS achieves accuracy comparable to single LLMs.

KCS+IBC reduces entropy and increases variance during inference.

The framework demonstrates potential for bias correction and improved explainability.

Abstract

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.