研究情绪如何影响大模型的连续决策，发现愤怒会降低其探索意愿。
Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?
- 用想象诱导情绪+爱荷华赌博任务测试模型决策
- 平均而言情绪不显著改变模型决策，但愤怒削弱对惩罚敏感度
- 适合关注AI行为心理机制或人机交互的研究者
随着大语言模型（LLMs）在高风险领域作为自主代理部署，理解可能调节其决策的情境因素变得至关重要。尽管LLMs经过训练能感知并回应用户情绪，但诱导情绪是否会影响其连续决策仍不明确。本文结合经典的爱荷华赌博任务（IGT）与基于想象的情绪诱导方法进行研究。首先验证该范式可行性：确认LLMs可从上下文中感知强烈且可区分的情绪，且其代理能在人类类似节奏下通过序列互动学习。在此基础上发现，与人类不同，总体上诱导情绪对LLM代理的决策动态无显著偏差。然而，愤怒的影响具有条件性：诱发愤怒会使模型对错误决策的惩罚不敏感；在游戏早期，愤怒会降低探索性，导致过早锁定少数选择。这些结果揭示了诱导情绪对LLM决策的微妙而独特的影响，不同于人类行为，为未来研究情感对LLM代理的调节作用提供了工具。
原文摘要 · Abstract (English)
As Large Language Models (LLMs) are increasingly deployed as autonomous agents in high-stakes domains, understanding contextual factors that may modulate their decision-making becomes critical. While LLMs are trained to perceive and resonate with users' emotions, it remains unclear whether induced emotion can influence their sequential decision-making. We investigate this question using the Iowa Gambling Task (IGT), a classic psychological paradigm for studying decision-making under uncertainty, combined with an imagination-based emotion induction procedure. We first validate the feasibility of this paradigm by confirming that LLMs can sense strong, distinguishable emotions from context and that LLM agents can learn from sequential interactions in a human-like pace. With the validated setup, we find that, different from humans, induced emotion does not significantly bias the decision dynamics of LLM agents on average. However, the effects of anger are conditioned: inducing anger makes LLM agents less sensitive to penalties for bad decisions, and in early stages of the game, anger can lower exploration, locking decisions into a few choices early. These findings reveal the subtle yet distinct effects of induced emotion on LLM decision-making compared to human behavior, and provide a tool for future research on affective modulation of LLM agents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。