Semi-Structured Chain-of-Thought: Integrating Multiple Sources of Knowledge for Improved Language Model Reasoning
Xin SuTiep LeSteven BethardPhillip Howard
Xin SuTiep LeSteven BethardPhillip Howard
Nov 2023
0被引用
2笔记
摘要原文
An important open question pertaining to the use of large language models for knowledge-intensive tasks is how to effectively integrate knowledge from three sources: the model's parametric memory, external structured knowledge, and external unstructured knowledge. Most existing prompting methods either rely solely on one or two of these sources, or require repeatedly invoking large language models to generate similar or identical content. In this work, we overcome these limitations by introducing a novel semi-structured prompting approach that seamlessly integrates the model's parametric memory with unstructured knowledge from text documents and structured knowledge from knowledge graphs. Experimental results on open-domain multi-hop question answering datasets demonstrate that our prompting method significantly surpasses existing techniques, even exceeding those which require fine-tuning.
