ReSCORE: Label-free Iterative Retriever Training for Multi-hop Question Answering with Relevance-Consistency Supervision

TL;DR

ReSCORE introduces a label-free training method for dense retrievers in multi-hop question answering, leveraging large language models to improve retrieval accuracy without needing labeled data, leading to state-of-the-art results.

Contribution

The paper presents ReSCORE, a novel iterative training approach for dense retrievers in MHQA that does not require labeled query-document pairs, addressing variability in questions.

Findings

Significant improvements in retrieval performance on three benchmarks.

Achieved state-of-the-art multi-hop QA results.

Effective training without labeled data.

Abstract

Multi-hop question answering (MHQA) involves reasoning across multiple documents to answer complex questions. Dense retrievers typically outperform sparse methods like BM25 by leveraging semantic embeddings; however, they require labeled query-document pairs for fine-tuning. This poses a significant challenge in MHQA due to the high variability of queries (reformulated) questions throughout the reasoning steps. To overcome this limitation, we introduce Retriever Supervision with Consistency and Relevance (ReSCORE), a novel method for training dense retrievers for MHQA without labeled documents. ReSCORE leverages large language models to capture each documents relevance to the question and consistency with the correct answer and use them to train a retriever within an iterative question-answering framework. Experiments on three MHQA benchmarks demonstrate the effectiveness of ReSCORE, with significant improvements in retrieval, and in turn, the state-of-the-art MHQA performance. Our implementation is available at: https://leeds1219.github.io/ReSCORE.