$\texttt{MixGR}$: Enhancing Retriever Generalization for Scientific Domain through Complementary Granularity

TL;DR

This paper introduces $\texttt{MixGR}$, which improves dense retrievers' awareness of query-document matching across various levels of granularity in queries and documents using a zero-shot approach, and fuses various metrics based on these granularities to a united score that reflects a comprehensive query-document similarity.

Abstract

Recent studies show the growing significance of document retrieval in the generation of LLMs, i.e., RAG, within the scientific domain by bridging their knowledge gap. However, dense retrievers often struggle with domain-specific retrieval and complex query-document relationships, particularly when query segments correspond to various parts of a document. To alleviate such prevalent challenges, this paper introduces $\texttt{MixGR}$, which improves dense retrievers' awareness of query-document matching across various levels of granularity in queries and documents using a zero-shot approach. $\texttt{MixGR}$ fuses various metrics based on these granularities to a united score that reflects a comprehensive query-document similarity. Our experiments demonstrate that $\texttt{MixGR}$ outperforms previous document retrieval by 24.7%, 9.8%, and 6.9% on nDCG@5 with unsupervised, supervised, and LLM-based retrievers, respectively, averaged on queries containing multiple subqueries from five scientific retrieval datasets. Moreover, the efficacy of two downstream scientific question-answering tasks highlights the advantage of $\texttt{MixGR}$ to boost the application of LLMs in the scientific domain. The code and experimental datasets are available.

Figures (6)

• Figure 1: Scientific document retrieval is shown to be more complicated than general domains.
• Figure 2: The illustration of MixGR: Both queries and documents (e.g., the query-doc pair from SciFact in Figure \ref{['fig:query-doc']}) are decomposed into subqueries and propositions, respectively, each containing distinct semantic components. Starting from the original queries and documents along with their decomposed elements, metrics from various granularity combinations are fused into a single integrated score.
• Figure 3: Comparison between BM25 and Contriever (w/ and w/o MixGR) on nDCG@20: Contriever w/ MixGR outperforms BM25 in three out of five datasets.
• Figure 4: Ablation study of MixGR on the nDCG@20 metrics averaged on eight retrievers: MixGR achieves optimal performance when combining these three metrics, indicating their complementary nature.
• Figure 5: Distribution of proposition number within documents in two sets. There are more propositions within document when $r_{q\text{-}d} \prec r_{s\text{-}p}$ than $r_{q\text{-}d} \succ r_{s\text{-}p}$.