arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2411.01271cs.LGcs.AIcs.ETcs.MAcs.SYeess.SY
收藏

交互式大型语言模型智能体:可解释模型与社会学习

Interacting Large Language Model Agents. Interpretable Models and Social Learning

School of Electrical and Computer Engineering, Cornell University(电气与计算机工程学院,康奈尔大学)

Adit Jain, Vikram Krishnamurthy

AI总结:

本文提出基于统计信号处理和微观经济学的可解释模型与算法,使交互式LLM智能体进行贝叶斯推断,并设计随机控制框架以缓解从众行为,在真实数据集上验证了有效性。

摘要:

本文讨论了利用统计信号处理和微观经济学方法,针对交互式大型语言模型智能体(LLMAs)的理论与算法。尽管这两个领域都已成熟,但它们在涉及交互式LLMAs的决策制定中的应用仍未得到探索。受在线平台上贝叶斯情感分析的启发,我们构建了可解释的模型和算法,使LLMAs能够进行交互并执行贝叶斯推断。由于交互式LLMAs同时从先前的决策和外部输入中学习,它们可能表现出偏见和从众行为。因此,开发可解释的模型和随机控制算法对于理解和缓解这些行为至关重要。本文有三个主要结果。首先,我们利用微观经济学中的贝叶斯显示偏好理论表明,单个LLMA满足理性疏忽(有限理性)贝叶斯效用最大化的必要和充分条件,并且在给定观测的情况下,LLMA会选择最大化正则化效用的行动。其次,我们利用贝叶斯社会学习来构建可解释的模型,使LLMAs能够依次与环境以及其他智能体交互,同时执行贝叶斯推断。我们提出的模型捕捉了交互式LLMAs所表现出的从众行为。第三,我们提出了一种随机控制框架,以延迟从众行为并在两种设置下提高状态估计精度:(a)集中控制的LLMAs;(b)具有激励的自主LLMAs。我们使用开源模型如LLaMA和闭源模型如ChatGPT,在仇恨言论分类和产品质量评估的真实数据集上证明了我们方法的有效性。本文基于实证分析和数学形式化的主要结论是,LLMAs作为理性受限的贝叶斯智能体,在交互时表现出社会学习行为。

英文摘要:

This paper discusses the theory and algorithms for interacting large language model agents (LLMAs) using methods from statistical signal processing and microeconomics. While both fields are mature, their application to decision-making involving interacting LLMAs remains unexplored. Motivated by Bayesian sentiment analysis on online platforms, we construct interpretable models and algorithms that enable LLMAs to interact and perform Bayesian inference. Because interacting LLMAs learn from both prior decisions and external inputs, they can exhibit bias and herding behavior. Thus, developing interpretable models and stochastic control algorithms is essential to understand and mitigate these behaviors. This paper has three main results. First, we show using Bayesian revealed preferences from microeconomics that an individual LLMA satisfies the necessary and sufficient conditions for rationally inattentive (bounded rationality) Bayesian utility maximization and, given an observation, the LLMA chooses an action that maximizes a regularized utility. Second, we utilize Bayesian social learning to construct interpretable models for LLMAs that interact sequentially with each other and the environment while performing Bayesian inference. Our proposed models capture the herding behavior exhibited by interacting LLMAs. Third, we propose a stochastic control framework to delay herding and improve state estimation accuracy under 2 settings: (a) centrally controlled LLMAs (b) autonomous LLMAs with incentives. We demonstrate the effectiveness of our methods on real datasets for hate speech classification and product quality assessment, using open-source models like LLaMA and closed-source models like ChatGPT. The main takeaway of this paper, based on empirical analysis and mathematical formalism, is that LLMAs act as rationally bounded Bayesian agents that exhibit social learning when interacting.

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。

↑