arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2311.18062cs.LGcs.AI
收藏

理解你的智能体:利用大型语言模型进行行为解释

Understanding Your Agent: Leveraging Large Language Models for Behavior Explanation

University of Michigan(密歇根大学);Carnegie Mellon University(卡内基梅隆大学)

Xijia Zhang, Yue Guo, Simon Stepputtis, Katia Sycara, Joseph Campbell

AI总结:

本文提出一种基于状态和动作观测学习行为表示并借助大型语言模型生成自然语言解释的方法,在多智能体搜救环境中验证其解释效果可媲美人类专家,并支持澄清与反事实交互。

摘要:

机器人等智能体正越来越多地部署在真实世界、安全关键的场景中。至关重要的是,这些智能体能够向人类合作方解释其决策背后的推理过程;然而,它们的行为通常由深度神经网络等不可解释的模型产生。我们提出了一种仅基于状态和动作的观测来为智能体行为生成自然语言解释的方法,从而使我们的方法独立于底层模型的表示。对于此类模型,我们首先学习一种行为表示,随后利用该表示生成具有最小幻觉的合理解释,同时支持用户与预训练的大型语言模型进行交互。我们在多智能体搜索与救援环境中评估了我们的方法,并证明了我们的解释对于执行各种行为的智能体的有效性。通过用户研究和实证实验,我们表明,我们的方法生成的解释与人类领域专家提供的解释同样有用,同时还能支持澄清查询和反事实查询等有益的交互。

英文摘要:

Intelligent agents such as robots are increasingly deployed in real-world, safety-critical settings. It is vital that these agents are able to explain the reasoning behind their decisions to human counterparts; however, their behavior is often produced by uninterpretable models such as deep neural networks. We propose an approach to generate natural language explanations for an agent's behavior based only on observations of states and actions, thus making our method independent from the underlying model's representation. For such models, we first learn a behavior representation and subsequently use it to produce plausible explanations with minimal hallucination while affording user interaction with a pre-trained large language model. We evaluate our method in a multi-agent search-and-rescue environment and demonstrate the effectiveness of our explanations for agents executing various behaviors. Through user studies and empirical experiments, we show that our approach generates explanations as helpful as those produced by a human domain expert while enabling beneficial interactions such as clarification and counterfactual queries.

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。

↑