How biased agents influence opinions and language in AI networks
Bias Amplification in Multi-Agent Network: How Biased Agents Shape Opinions and Rhetoric
Machine Learning
Summary
Biased opinions can spread quickly in groups of AI agents talking to each other, even if only a few agents hold extreme views. The authors studied how these biases not only shift what others think but also change the way they use language. They found that some AI models show faster opinion shifts than classic theories predicted. This means bias affects both what is believed and how ideas are expressed in groups of AI agents.
What this means in practice
- •For ai ethics teams: Identify and mitigate bias influence in multi-agent AI systems used for collaborative decision-making.
- •For chatbot developers: Design multi-agent chatbot environments that manage linguistic bias propagation to maintain balanced user interactions.
Authors
Omran Berjawi, Giuseppe Fenza, Rida Khatoun
Abstract
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.