在大型语言模型中什么抑制了纳什均衡行为？机制证据和因果控制
How a Cooperative-Override Circuit Suppresses Nash Play in Large Language Models
AI总结：
研究通过实验揭示大型语言模型在战略决策中抑制纳什均衡的行为机制，发现模型在早期层面对对手历史编码精确，但纳什行动编码较弱，且通过后期层的亲社会覆盖抑制纳什行为。
摘要：
LLM代理在战略互动中已知会偏离纳什均衡，但没有人曾深入模型内部了解原因，或询问这种偏离是否可以逆转。我们通过四个开源模型（Llama-3和Qwen2.5，8B到72B参数）在四个经典双人游戏中进行自我对战和交叉对战实验，然后打开32层Llama-3-8B模型，检查战略决策过程中发生什么。机制发现清晰：对手历史在第一层以近完美保真度编码（96%探测准确度），并被后续层逐步消耗，而纳什行动编码在整个过程中较弱，从未超过56%。没有专门的纳什模块。相反，模型在大部分前向传递中私下倾向于纳什行动，但一个集中在后期层的亲社会覆盖逆转了这一点，在第30层达到84%的合作概率。当我们向残差流注入学习的纳什方向时，行为会双向变化，通过概念钳制得到验证。行为实验揭示了六个规模和架构相关的发现，最值得注意的是，推理链在小模型中会恶化纳什行为，但超过70B参数时接近完美。交叉对战实验揭示了三个在自我对战中不可见的现象：小模型可以通过早期背叛解开任何合作伙伴的合作；两个大模型会无限加强彼此的合作本能；协调游戏中谁先行动决定了系统达到的纳什均衡。LLM并不缺乏纳什行为能力。它们计算了它，然后抑制了它。
英文摘要：
On the named Prisoner's Dilemma under direct prompting, three larger instruction-tuned models, Llama-3-70B, Qwen2.5-32B, and Qwen2.5-72B, lock at full cooperation, the metric's maximum distance from Nash with zero variance across replicates, while Llama-3-8B plays near-Nash. Opening the models, a logit-lens analysis finds a distributed cooperative override. Intermediate readouts lean toward the Nash action through roughly three quarters of network depth before a late surge toward cooperation, and the final layer settles the contest. The size of that final correction, not the surge, rank-matches chain-of-thought behavior across scale and two architectures. In the 8B the override is a single causally controllable direction in the residual stream; steering it dials the decision, and clamping its component at one position of one layer moves the choice strictly monotonically, Spearman rho = 1.000, with generation fluent. The circuit is lexical. It survives name removal and payoff rescaling but disengages when Cooperate and Defect are replaced with neutral labels, and on 48 payoff-random games with neutral surfaces no model locks cooperative on any dilemma or shows general equilibrium competence. In mixed-model populations a single Nash-playing agent collapses cooperation contagiously. What suppresses Nash play in large language models is a word-triggered circuit rather than missing competence, and it can be measured, bounded, and controlled.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
