arXiv cs.MA· Cl\'ea Chataigner, Mina Arzaghi, Florian Carichon, Pablo Piantanida, Golnoosh Farnadi·· 9 小时前AI 评分31
多智能体网络拓扑如何影响偏见注入的传播:一项鲁棒性研究
Corrupting Ties: Investigating Robustness to Bias Injection Across Multi-Agent Network Topologies
AI 导读
研究提出受控偏见注入框架,将选定智能体的回复替换为预设偏见回复,并在 Qwen 与 Gemma 系列 LLM 上对三种二分类任务、五种拓扑结构进行干预分析。顺序网络出现最大决策分歧,全连接与网状网络分歧较小;星型网络中注入中心智能体的影响大于外围智能体。模型间在分歧是否跟随注入偏见上也存在差异,表明网络结构在偏见信息传播中起关键作用。
正文 · 原文
Abstract:AI systems are increasingly deployed in high-stakes decision-making contexts, where interactions among components can introduce fairness risks that remain undetected when auditing components or collective outcomes in isolation. As LLM-based multi-agent systems become more prevalent, understanding how biased information propagates through agent interactions is essential for assessing their fairness. We introduce a controlled bias injection framework that replaces selected agent responses with predefined biased ones, enabling an intervention-based analysis of how network topology and injection configurations shape system behavior. We propose decision divergence metrics that quantify the effects of these interventions at the agent, network, and system levels, and evaluate five topologies on three binary classification tasks using LLMs from the Qwen and Gemma families. Sequential networks show the greatest divergence, whereas fully connected and mesh networks show less. Injection position also matters: in star networks, injecting the central agent has larger effects than injecting peripheral agents. Models further differ in whether divergence follows the injected bias. These findings highlight the role of network structure in the propagation of biased information and motivate topology-aware auditing of fairness risks in multi-agent systems.
| Subjects: | Computation and Language (cs.CL); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2611.21804 [cs.CL] |
| (or arXiv:2611.21804v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.21804 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Cléa Chataigner [view email]
[v1]
Mon, 16 Nov 2026 19:20:05 UTC (1,100 KB)
来源:arXiv cs.MA · arxiv.org