UniFAR: A Unified Facet-Aware Retrieval Framework for Scientific Documents

TL;DR

UniFAR is a unified retrieval framework that effectively supports both document-to-document and question-driven scientific document retrieval by addressing granularity, semantic focus, and training signal mismatches.

Contribution

It introduces a novel unified architecture that jointly supports doc-doc and q-doc retrieval, aligning document structure with question intent and unifying training signals.

Findings

Outperforms prior methods across multiple retrieval tasks.

Demonstrates effectiveness and generality with various models.

Addresses key mismatches in current SDR approaches.

Abstract

Existing scientific document retrieval (SDR) methods primarily rely on document-centric representations learned from inter-document relationships for document-document (doc-doc) retrieval. However, the rise of LLMs and RAG has shifted SDR toward question-driven retrieval, where documents are retrieved in response to natural-language questions (q-doc). This change has led to systematic mismatches between document-centric models and question-driven retrieval, including (1) input granularity (long documents vs. short questions), (2) semantic focus (scientific discourse structure vs. specific question intent), and (3) training signals (citation-based similarity vs. question-oriented relevance). To this end, we propose UniFAR, a Unified Facet-Aware Retrieval framework to jointly support doc-doc and q-doc SDR within a single architecture. UniFAR reconciles granularity differences through adaptive multi-granularity aggregation, aligns document structure with question intent via learnable facet anchors, and unifies doc-doc and q-doc supervision through joint training. Experimental results show that UniFAR consistently outperforms prior methods across multiple retrieval tasks and base models, confirming its effectiveness and generality.