用大型语言模型评估程序化策略的可解释性
Assessing the Interpretability of Programmatic Policies with Large Language Models
AI总结：
本文提出一种基于大型语言模型的度量方法，通过自然语言解释与程序重建的行为相似性评估程序化策略的可解释性，并在实时策略游戏策略上验证其有效性。
摘要：
尽管编码策略的程序的合成通常带有可解释性的承诺，但从未进行过系统性评估来评判这些策略的可解释性，这很可能是因为此类评估的复杂性。在本文中，我们提出了一种新颖的度量方法，该方法使用大型语言模型（LLM）来评估程序化策略的可解释性。在我们的度量方法中，向一个LLM同时提供一个程序及其相关编程语言的描述。然后，该LLM生成该程序的自然语言解释。随后，将该解释输入第二个LLM，后者尝试从自然语言解释中重建程序。我们的度量方法随后衡量重建程序与原始程序之间的行为相似性。我们使用用于玩实时策略游戏的合成和人工编写的程序化策略验证了我们的方法，将这些程序化策略的可解释性得分与相同程序的混淆版本进行了比较。我们基于LLM的可解释性得分始终将可解释性较低的程序排在较低位置，将可解释性较高的程序排在较高位置。这些发现表明，我们的度量方法可以作为一种可靠且廉价的工具，用于评估程序化策略的可解释性。
英文摘要：
Although the synthesis of programs encoding policies often carries the promise of interpretability, systematic evaluations were never performed to assess the interpretability of these policies, likely because of the complexity of such an evaluation. In this paper, we introduce a novel metric that uses large-language models (LLM) to assess the interpretability of programmatic policies. For our metric, an LLM is given both a program and a description of its associated programming language. The LLM then formulates a natural language explanation of the program. This explanation is subsequently fed into a second LLM, which tries to reconstruct the program from the natural-language explanation. Our metric then measures the behavioral similarity between the reconstructed program and the original. We validate our approach with synthesized and human-crafted programmatic policies for playing a real-time strategy game, comparing the interpretability scores of these programmatic policies to obfuscated versions of the same programs. Our LLM-based interpretability score consistently ranks less interpretable programs lower and more interpretable ones higher. These findings suggest that our metric could serve as a reliable and inexpensive tool for evaluating the interpretability of programmatic policies.
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。
