Exploring Hint Generation Approaches in Open-Domain Question Answering

TL;DR

This paper introduces HINTQA, a novel approach that uses automatic hint generation with LLMs to improve open-domain question answering, outperforming traditional retrieval and generation methods by enhancing answer accuracy.

Contribution

HINTQA is a new context preparation method that prompts LLMs to generate hints about potential answers, improving QA performance over existing approaches.

Findings

HINTQA surpasses retrieval-based and generation-based methods in accuracy.

Hints improve answer correctness more than traditional context methods.

The number and order of hints influence QA performance.

Abstract

Automatic Question Answering (QA) systems rely on contextual information to provide accurate answers. Commonly, contexts are prepared through either retrieval-based or generation-based methods. The former involves retrieving relevant documents from a corpus like Wikipedia, whereas the latter uses generative models such as Large Language Models (LLMs) to generate the context. In this paper, we introduce a novel context preparation approach called HINTQA, which employs Automatic Hint Generation (HG) techniques. Unlike traditional methods, HINTQA prompts LLMs to produce hints about potential answers for the question rather than generating relevant context. We evaluate our approach across three QA datasets including TriviaQA, NaturalQuestions, and Web Questions, examining how the number and order of hints impact performance. Our findings show that the HINTQA surpasses both retrieval-based and generation-based approaches. We demonstrate that hints enhance the accuracy of answers more than retrieved and generated contexts.