Query Refinement Prompts for Closed-Book Long-Form Question Answering

TL;DR

This paper introduces query refinement prompts for large language models to improve long-form question answering by explicitly expressing question facets, leading to better performance in closed-book settings.

Contribution

It proposes a novel prompt design that enables LLMs to handle multifaceted questions and generate comprehensive long-form answers, outperforming finetuned models.

Findings

Outperforms fully finetuned models in closed-book QA

Achieves results comparable to retrieve-then-generate open-book models

Effective on datasets ASQA and AQuAMuSe

Abstract

Large language models (LLMs) have been shown to perform well in answering questions and in producing long-form texts, both in few-shot closed-book settings. While the former can be validated using well-known evaluation metrics, the latter is difficult to evaluate. We resolve the difficulties to evaluate long-form output by doing both tasks at once -- to do question answering that requires long-form answers. Such questions tend to be multifaceted, i.e., they may have ambiguities and/or require information from multiple sources. To this end, we define query refinement prompts that encourage LLMs to explicitly express the multifacetedness in questions and generate long-form answers covering multiple facets of the question. Our experiments on two long-form question answering datasets, ASQA and AQuAMuSe, show that using our prompts allows us to outperform fully finetuned models in the closed book setting, as well as achieve results comparable to retrieve-then-generate open-book models.