Scholarlink

In adversarial contexts, success often hinges on understanding not just what the opponent knows, but what they believe and how they revise those beliefs. This study investigates how large language models can be made more resilient and strategically capable by modeling the opponent’s reasoning using Bayesian belief revision. By formalizing negotiations as Bayesian games of incomplete information, it is shown that models equipped with belief revision are better able to counter deceptive or willful-thinking adversaries. The findings underscore the role of second-order reasoning in adversarial settings, with implications for social manipulation in the context of, for example, online communication and intelligence gathering.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Outsmarting Willful-Thinking Opponents: Bayesian Belief Revision for Adversarial Reasoning in Large Language Models

  • 会议论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年

查看全文
  • Madeleine Lindström,
  • Joel Brynielsson,
  • Mika Cohen,
  • Farzad Kamrani,
  • Samuel Lavebrink,
  • Christoffer Limér,
  • Marius Vangeli

摘要

In adversarial contexts, success often hinges on understanding not just what the opponent knows, but what they believe and how they revise those beliefs. This study investigates how large language models can be made more resilient and strategically capable by modeling the opponent’s reasoning using Bayesian belief revision. By formalizing negotiations as Bayesian games of incomplete information, it is shown that models equipped with belief revision are better able to counter deceptive or willful-thinking adversaries. The findings underscore the role of second-order reasoning in adversarial settings, with implications for social manipulation in the context of, for example, online communication and intelligence gathering.