面向接地对话的符号规划与代码生成
Symbolic Planning and Code Generation for Grounded Dialogue
AI总结：
本文提出将LLM与符号规划器和接地代码执行相结合的模块化对话系统，在OneCommon任务上将成功率从56%提升至69%。
摘要：
大型语言模型（LLMs）在处理和生成文本与代码方面表现出色。然而，LLMs在接地任务导向对话中的适用性有限，因为难以将其引导至任务目标，且无法处理新颖的接地。我们提出一个模块化且可解释的接地对话系统，通过将LLMs与符号规划器和接地代码执行相结合来解决这些不足。我们的系统由一个读取器和一个规划器组成：读取器利用LLM将伙伴话语转换为可执行代码，调用执行接地的函数。翻译后代码的输出被存储以跟踪对话状态，而符号规划器决定下一个合适的响应。我们在要求严格的OneCommon对话任务上评估系统性能，该任务涉及在散点抽象图像上进行协作指代消解。我们的系统显著优于先前的最先进系统，包括在最具挑战性的设置中将人类评估中的任务成功率从56%提高到69%。
英文摘要：
Large language models (LLMs) excel at processing and generating both text and code. However, LLMs have had limited applicability in grounded task-oriented dialogue as they are difficult to steer toward task objectives and fail to handle novel grounding. We present a modular and interpretable grounded dialogue system that addresses these shortcomings by composing LLMs with a symbolic planner and grounded code execution. Our system consists of a reader and planner: the reader leverages an LLM to convert partner utterances into executable code, calling functions that perform grounding. The translated code's output is stored to track dialogue state, while a symbolic planner determines the next appropriate response. We evaluate our system's performance on the demanding OneCommon dialogue task, involving collaborative reference resolution on abstract images of scattered dots. Our system substantially outperforms the previous state-of-the-art, including improving task success in human evaluations from 56% to 69% in the most challenging setting.
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。
