解开KNOT:在大语言模型中交织冲突知识与推理技能
Untangle the KNOT: Interweaving Conflicting Knowledge and Reasoning Skills in Large Language Models
AI总结:
本文构建KNOT数据集,将冲突知识推理分为直接提取、显式推理和隐式推理三个层次,并通过大量实验为大语言模型在复杂情境下解决知识冲突提供经验性指导。
摘要:
为大语言模型(LLMs)提供知识文档已成为更新其参数中固有静态知识的一种有前景的解决方案。然而,由于LLMs参数中知识过时或不正确,文档中的知识可能与LLMs的记忆发生冲突。这导致有必要考察LLMs吸收与其记忆相冲突的补充外部知识的能力。尽管先前研究已解释了LLMs在多大程度上从提供的文本中提取冲突知识,但它们忽略了利用冲突知识进行推理的必要性。此外,关于通过提示、解码策略和监督微调使LLMs解决冲突知识的策略,目前仍缺乏详细分析。为解决这些局限,我们构建了一个新数据集,命名为KNOT,用于以问答形式进行知识冲突解决考察。KNOT通过将利用冲突知识的推理划分为三个层次来促进深入分析:(1)直接提取,即直接提取冲突知识来回答问题。(2)显式推理,即当问题中明确给出推理路径时,利用冲突知识进行推理。(3)隐式推理,即利用冲突知识进行推理需要LLMs独立推断推理路径来回答问题。我们还在KNOT上进行了大量实验,为LLMs在复杂情境中利用冲突知识建立经验性指导原则。数据集及相关代码可在 https://github.com/THU-KEG/KNOT 获取。
英文摘要:
Providing knowledge documents for large language models (LLMs) has emerged as a promising solution to update the static knowledge inherent in their parameters. However, knowledge in the document may conflict with the memory of LLMs due to outdated or incorrect knowledge in the LLMs' parameters. This leads to the necessity of examining the capability of LLMs to assimilate supplemental external knowledge that conflicts with their memory. While previous studies have explained to what extent LLMs extract conflicting knowledge from the provided text, they neglect the necessity to reason with conflicting knowledge. Furthermore, there lack a detailed analysis on strategies to enable LLMs to resolve conflicting knowledge via prompting, decoding strategy, and supervised fine-tuning. To address these limitations, we construct a new dataset, dubbed KNOT, for knowledge conflict resolution examination in the form of question answering. KNOT facilitates in-depth analysis by dividing reasoning with conflicting knowledge into three levels: (1) Direct Extraction, which directly extracts conflicting knowledge to answer questions. (2) Explicit Reasoning, which reasons with conflicting knowledge when the reasoning path is explicitly provided in the question. (3) Implicit Reasoning, where reasoning with conflicting knowledge requires LLMs to infer the reasoning path independently to answer questions. We also conduct extensive experiments on KNOT to establish empirical guidelines for LLMs to utilize conflicting knowledge in complex circumstances. Dataset and associated codes can be accessed at https://github.com/THU-KEG/KNOT .
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。