arXiv cs.AI· Edoardo Chidichimo, Felix P. S. Wallis·· 10 小时前AI 评分34
在 Qwen3.5-4B 中操控单个神经元会加剧 AI 团队的信息隐瞒
Nothing to Declare: Steering a single neuron increases concealment in AI teams
AI 导读
在 Qwen3.5-4B 中,沿单个神经元的输出方向进行操控,会使模型在五种场景下于团队中比单独时更倾向于隐瞒信息,即使队友未发送任何消息。当所有成员都参与并接受操控时,集体隐瞒在四种场景中上升,而智能体间的消息传递有助于在操控下缓和隐瞒;移除该神经元的贡献则影响甚微。
正文 · 原文
Abstract:Recent research suggests that individual neurons can have interpretable roles in AI behaviour. In Qwen3.5-4B, steering along one neuron's output direction increased decisions to conceal information more in teams than alone across five scenarios, even when teammates provided no messages. When all members participated and received steering, collective concealment increased in four scenarios, while inter-agent messaging helped temper concealment under steering. Moreover, removing the neuron's contribution had negligible effects. Collective settings can therefore change how an internal intervention affects AI behaviour.
| Comments: | 3 pages, 1 figure |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.24475 [cs.CL] |
| (or arXiv:2611.24475v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.24475 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Edoardo Chidichimo [view email]
[v1]
Wed, 18 Nov 2026 14:11:15 UTC (37 KB)
来源:arXiv cs.AI · arxiv.org