跳到主要导航 跳到搜索 跳到主要内容

Enhancing belief consistency of large language model agents in decision-making process based on attribution theory

  • Guoxiu He*
  • , Meicong Zhang
  • , Tiancheng Su
  • , Li Ma
  • , Xiaomin Zhu
  • *此作品的通讯作者
  • East China Normal University
  • AMS

科研成果: 期刊稿件 › 文章 › 同行评审

摘要

In social simulation, maintaining consistent beliefs (e.g., core cognition, position, and goal) is crucial for Large Language Model (LLM) agents to effectively assume specific roles and make coherent decisions. However, LLMs generate responses incrementally through next-token predictions based on preceding words, making them vulnerable to context ambiguity. This can cause their decision-making behavior to deviate from initial goals. To address this issue, we propose the Attribution-based Decision-Making Approach (ADMA), inspired by human attribution processes. ADMA comprises three modules: generation, evaluation, and attribution. Rather than making impulsive decisions, ADMA encourages LLMs to systematically attribute the underlying beliefs associated with each potential choice, and then adjust their decisions accordingly. Through iterative application, ADMA promotes better alignment between generated decisions and predefined goals. We evaluate ADMA in a debate scenario, where beliefs are continuously challenged by opposing arguments, influencing both stance and rebuttal strength. Empirical results show that the attribution process enhances belief consistency, as well as fluency, persuasiveness, and confidence. ADMA also improves LLM agents’ resistance to persuasive language. Furthermore, belief consistency increases with more attribution iterations, albeit with diminishing returns. These findings underscore the potential of attribution theory to strengthen belief stability in LLM agents.

源语言英语
期刊论文编号129273
期刊Expert Systems with Applications
卷297
DOI
出版状态已出版 - 1 2月 2026

学术指纹

探究 'Enhancing belief consistency of large language model agents in decision-making process based on attribution theory' 的科研主题。它们共同构成独一无二的学术指纹。

引用此