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 2302.05128cs.CLcs.AIcs.RO
收藏

使用大语言模型将自然语言转换为规划目标

Translating Natural Language to Planning Goals with Large-Language Models

National University of Singapore(新加坡国立大学)

Yaqi Xie, Chen Yu, Tongyao Zhu, Jinbin Bai, Ze Gong, Harold Soh

摘要:

最近的大语言模型(LLM)在各种自然语言处理(NLP)任务上表现出了卓越的性能,导致人们对它们在各个领域的适用性感到非常兴奋。不幸的是,最近的工作也表明,LLM无法执行准确的推理,也无法解决规划问题,这可能会限制它们对机器人相关任务的有用性。在这项工作中,我们的中心问题是LLM是否能够将自然语言中指定的目标转换为结构化的规划语言。如果是这样的话,LLM可以作为规划者和人类用户之间的自然接口;翻译后的目标可以交给在规划方面非常有效的独立于领域的AI规划者。我们对GPT 3.5变体的实证结果表明,LLM更适合翻译而不是规划。我们发现,LLM能够利用常识知识和推理,从未指定的目标中提供缺失的细节(自然语言中经常出现这种情况)。然而,我们的实验也表明,LLM可能无法在涉及数字或物理的任务中生成目标(例如,空间)推理,并且LLM对所使用的提示敏感。因此,这些模型很有希望翻译成结构化规划语言,但在使用时应注意。

英文摘要:

Recent large language models (LLMs) have demonstrated remarkable performance on a variety of natural language processing (NLP) tasks, leading to intense excitement about their applicability across various domains. Unfortunately, recent work has also shown that LLMs are unable to perform accurate reasoning nor solve planning problems, which may limit their usefulness for robotics-related tasks. In this work, our central question is whether LLMs are able to translate goals specified in natural language to a structured planning language. If so, LLM can act as a natural interface between the planner and human users; the translated goal can be handed to domain-independent AI planners that are very effective at planning. Our empirical results on GPT 3.5 variants show that LLMs are much better suited towards translation rather than planning. We find that LLMs are able to leverage commonsense knowledge and reasoning to furnish missing details from under-specified goals (as is often the case in natural language). However, our experiments also reveal that LLMs can fail to generate goals in tasks that involve numerical or physical (e.g., spatial) reasoning, and that LLMs are sensitive to the prompts used. As such, these models are promising for translation to structured planning languages, but care should be taken in their use.

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。

↑