Word2Passage : Word-level Importance Re-weighting for Query Expansion

ACL ARR 2025 February Submission790 Authors

Abstract: Retrieval-augmented generation (RAG) enhances the quality of LLM generation by providing relevant chunks, but retrieving accurately from external knowledge remains challenging due to missing contextually important words in query. We present \textbf{Word2Passage}, a novel approach that improves retrieval accuracy by optimizing word importance in query expansion. Our method generates references at word, sentence, and passage levels for query expansion, then determines word importance by considering both their reference level origin and characteristics derived from query types and corpus analysis. Specifically, our method assigns distinct importance scores to words based on whether they originate from word, sentence, or passage-level references. Extensive experiments demonstrate that Word2Passage outperforms existing methods across various datasets and LLM configurations, effectively enhancing both retrieval accuracy and generation quality. The code will be released publicly.

Paper Type: Long

Research Area: Information Retrieval and Text Mining

Research Area Keywords: rag, query expansion, qa, ir, information retrieval, alignment

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Publicly available software and/or pre-trained models, Data analysis

Languages Studied: English

Submission Number: 790