将大型语言模型与逻辑编程耦合以实现从文本出发的鲁棒通用推理
Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text
AI总结:
本文提出将 LLM 作为少样本语义解析器并与可复用的 ASP 逻辑模块耦合,在多个 NLP 基准及机器人规划任务上实现鲁棒通用推理。
摘要:
尽管 GPT-3 等大型语言模型(LLM)看起来具有鲁棒性和通用性,但其推理能力尚未达到可与针对特定自然语言推理问题训练的最佳模型相竞争的水平。在本研究中,我们观察到大型语言模型可以充当高效的少样本语义解析器。它能够将自然语言句子转换为逻辑形式,作为 answer set programs(ASP,一种基于逻辑的声明式知识表示形式)的输入。这种结合产生了一个鲁棒且通用的系统,可处理多个问答任务,而无需针对每个新任务重新训练。它只需少量示例来引导 LLM 适应特定任务,并配合可跨多个任务复用的 ASP 知识模块。我们证明,该方法在 bAbI、StepGame、CLUTRR 和 gSCAN 等多个 NLP 基准上达到了最先进性能。此外,它还成功解决了单独使用 LLM 无法完成的机器人规划任务。
英文摘要:
While large language models (LLMs), such as GPT-3, appear to be robust and general, their reasoning ability is not at a level to compete with the best models trained for specific natural language reasoning problems. In this study, we observe that a large language model can serve as a highly effective few-shot semantic parser. It can convert natural language sentences into a logical form that serves as input for answer set programs, a logic-based declarative knowledge representation formalism. The combination results in a robust and general system that can handle multiple question-answering tasks without requiring retraining for each new task. It only needs a few examples to guide the LLM's adaptation to a specific task, along with reusable ASP knowledge modules that can be applied to multiple tasks. We demonstrate that this method achieves state-of-the-art performance on several NLP benchmarks, including bAbI, StepGame, CLUTRR, and gSCAN. Additionally, it successfully tackles robot planning tasks that an LLM alone fails to solve.
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。