Semi-Structured Chain-of-Thought: Integrating Multiple Sources of Knowledge for Improved Language Model Reasoning

arXiv:2311.08505v2 Announce Type: replace
Abstract: An important open question in 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 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 …

abstract arxiv cs.cl knowledge language language model language models large language large language models memory multiple parametric prompting question reasoning tasks thought type unstructured