发表机构
Institut Polytechnique de Paris; Télécom Paris; University of Salerno（巴黎综合理工学院; 巴黎电信学院; 萨莱诺大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过多智能体LLM交互实验，发现少数有偏智能体即可显著影响多数无偏智能体的观点，且Llama 3.2中偏移更快，修辞一致性与数值收敛部分解耦，揭示偏差与语言协同演化。
AI 中文摘要
大型语言模型（LLMs）越来越多地被部署在涉及智能体之间交互的应用中，其输出在集体推理和决策过程中发挥作用。尽管对LLMs在此类多智能体系统中的运作已有大量研究，但偏差在这些系统中的传播过程仍是一个挑战。本研究探讨了在有偏见的观点以文本交互形式在LLM环境中传播时的情况，其中少数智能体坚持极端的观点，而其余智能体通过结构化的文本交互迭代更新其信念。研究结果表明，即使在这样的系统中存在一小部分有偏见的智能体，也会导致无偏见智能体的观点发生显著偏移。这表明，对于相同比例的有偏智能体，Llama 3.2模型中的观点偏移比经典Friedkin-Johnsen（FJ）模型发生得更快。进一步的语义分析表明，文本解释中的修辞一致性随着有偏暴露的增加而系统性增强，并且重要的是，这种一致性与数值收敛部分解耦：即使在数值观点偏移保持温和的配置中，中性智能体也会采用有偏智能体所使用的词汇。这项研究有助于解释在多智能体语言模型生态系统中，偏差和语言如何共同发展。
英文摘要
Large language models (LLMs) are increasingly deployed in applications involving interaction between agents, where their output plays a role in collective reasoning and decision-making processes. Despite significant research into the functioning of LLMs in such multi-agent systems, the processes of bias propagation in such systems are still a challenge. This work studies how biased opinions are propagated in the form of textual interaction in an environment of LLMs, in which a minority of agents maintain persistent extreme opinions, while the remaining agents iteratively update their beliefs through structured textual interactions. The findings show that even the presence of a small percentage of biased agents in such a system leads to significant shifts in the opinions of non-biased agents. It suggests that for the same percentage of biased agents, the shifts occur more quickly for the Llama~3.2 model when compared to a classical Friedkin-Johnsen (FJ) model. Further semantic analysis demonstrates that rhetorical consistency in textual explanations increases systematically with biased exposure and, importantly, is partially decoupled from numerical convergenumericalutral agents adopt the vocabulary employed by the biased agents even in configurations where their numerical opinion shifts remain moderate. The research helps explain how bias and language develop together in multi-agent language model ecosystems.
CommentsAccepted at the 6th Workshop on Bias and Fairness in AI (BIAS 2026), ECML PKDD 2026, Naples, Italy
