根据对话对象动态调整解释策略，让AI更懂你。
SNAPE-PM: Building and Utilizing Dynamic Partner Models for Adaptive Explanation Generation
- 用贝叶斯方法实时更新对对话者的认知模型。
- 在不同用户上生成差异化的解释策略，适应性强。
- 适合需要个性化解释的AI对话系统与可解释AI研究者。
解释生成需根据听众动态调整，但对对话系统构成挑战。本文将解释生成视为非平稳决策过程，其最优策略随对听者信念和交互上下文的变化而改变。我们解决两个问题：(1) 如何在计算层面构建形式化的伙伴模型以追踪交互上下文和听者特征；(2) 如何利用该模型实现动态调整的理性决策过程，确定当前最佳解释策略。提出基于贝叶斯推断的方法持续更新伙伴模型，并采用非平稳马尔可夫决策过程依据模型值调整决策。在五个模拟对话者上的实验表明，该框架能有效适应具有恒定或变化反馈行为的不同伙伴，产生明显差异的解释策略，验证了其在提升可解释AI系统与对话系统方面的潜力。
原文摘要 · Abstract (English)
Adapting to the addressee is crucial for successful explanations, yet poses significant challenges for dialogsystems. We adopt the approach of treating explanation generation as a non-stationary decision process, where the optimal strategy varies according to changing beliefs about the explainee and the interaction context. In this paper we address the questions of (1) how to track the interaction context and the relevant listener features in a formally defined computational partner model, and (2) how to utilize this model in the dynamically adjusted, rational decision process that determines the currently best explanation strategy. We propose a Bayesian inference-based approach to continuously update the partner model based on user feedback, and a non-stationary Markov Decision Process to adjust decision-making based on the partner model values. We evaluate an implementation of this framework with five simulated interlocutors, demonstrating its effectiveness in adapting to different partners with constant and even changing feedback behavior. The results show high adaptivity with distinct explanation strategies emerging for different partners, highlighting the potential of our approach to improve explainable AI systems and dialogsystems in general.
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。