HiGenQA: Exploring Hint Generation Approaches for Open Domain Question Answering
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 HiGenQA, which employs Automatic Hint Generation (HG) systems. Unlike traditional methods, HiGenQA 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, Natural Questions, and Web Questions, examining how the number and order of hints impact performance. Our findings show that HiGenQA surpasses both retrieval-based and generation-based approaches. We demonstrate that hints enhance the accuracy of answers more than retrieved and generated contexts.
Paper Type: Long
Research Area: Question Answering
Research Area Keywords: open-domain QA, generative models, prompting, retrieval-augmented models
Contribution Types: Model analysis & interpretability, NLP engineering experiment, Data resources
Languages Studied: English
Submission Number: 1793
Loading