Salvato in:
Dettagli Bibliografici
Autori principali: Su, Xin, Le, Tiep, Bethard, Steven, Howard, Phillip
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2311.08505
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917628135604224
author Su, Xin
Le, Tiep
Bethard, Steven
Howard, Phillip
author_facet Su, Xin
Le, Tiep
Bethard, Steven
Howard, Phillip
contents 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 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 that require fine-tuning.
format Preprint
id arxiv_https___arxiv_org_abs_2311_08505
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Semi-Structured Chain-of-Thought: Integrating Multiple Sources of Knowledge for Improved Language Model Reasoning
Su, Xin
Le, Tiep
Bethard, Steven
Howard, Phillip
Computation and Language
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 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 that require fine-tuning.
title Semi-Structured Chain-of-Thought: Integrating Multiple Sources of Knowledge for Improved Language Model Reasoning
topic Computation and Language
url https://arxiv.org/abs/2311.08505