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

• URL: http://arxiv.org/abs/2602.23766v1
• Date: Fri, 27 Feb 2026 07:44:02 GMT
• Title: UniFAR: A Unified Facet-Aware Retrieval Framework for Scientific Documents
• Authors: Zheng Dou, Zhao Zhang, Deqing Wang, Yikun Ban, Fuzhen Zhuang,
• Abstract summary: We propose a Unified Facet-Aware Retrieval framework to support doc-doc and q-doc SDR within a single architecture.<n>UniFAR reconciles document structure with question intent via learnable facet anchors, and unifies doc-doc and q-doc supervision through joint training.
• Score: 35.00880322661589
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• CMRAG: Co-modality-based visual document retrieval and question answering [21.016544020685668]
  Co-Modality-based RAG (RAG) framework can leverage texts and images for more accurate retrieval and generation.<n>Our framework consistently outperforms single-modality-based RAG in multiple visual document question-answering (VDQA) benchmarks.
  arXiv  Detail & Related papers  (2025-09-02T09:17:57Z)
• ABCD-LINK: Annotation Bootstrapping for Cross-Document Fine-Grained Links [57.514511353084565]
  We introduce a new domain-agnostic framework for selecting a best-performing approach and annotating cross-document links.<n>We apply our framework in two distinct domains -- peer review and news.<n>The resulting novel datasets lay foundation for numerous cross-document tasks like media framing and peer review.
  arXiv  Detail & Related papers  (2025-09-01T11:32:24Z)
• Improving Document Retrieval Coherence for Semantically Equivalent Queries [63.97649988164166]
  We propose a variation of the Multi-Negative Ranking loss for training DR that improves the coherence of models in retrieving the same documents.<n>The loss penalizes discrepancies between the top-k ranked documents retrieved for diverse but semantic equivalent queries.
  arXiv  Detail & Related papers  (2025-08-11T13:34:59Z)
• Extracting Document Relations from Search Corpus by Marginalizing over User Queries [0.0]
  We propose a novel framework that discovers document relationships through query marginalization.<n>Extracting Document Relations by Marginalizing over User queries is based on the insight that strongly related documents often co-occur in diverse user queries.<n>Our query-driven framework offers a practical approach to document organization that adapts to different user perspectives and information needs.
  arXiv  Detail & Related papers  (2025-07-14T18:47:13Z)
• Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering [51.7493726399073]
  We present a discourse-aware hierarchical framework to enhance long document question answering.<n>The framework involves three key innovations: specialized discourse parsing for lengthy documents, LLM-based enhancement of discourse relation nodes, and structure-guided hierarchical retrieval.
  arXiv  Detail & Related papers  (2025-05-26T14:45:12Z)
• CDER: Collaborative Evidence Retrieval for Document-level Relation Extraction [3.9499087751190243]
  Document-level Relation Extraction (DocRE) involves identifying relations between entities across multiple sentences in a document.<n>Existing evidence retrieval systems often overlook the collaborative nature among semantically similar entity pairs in the same document, hindering the effectiveness of the evidence retrieval task.<n>We propose a novel evidence retrieval framework, namely CDER. CDER employs an attentional graph-based architecture to capture collaborative patterns and incorporates a dynamic sub-structure for additional robustness in evidence retrieval.
  arXiv  Detail & Related papers  (2025-04-09T02:10:21Z)
• DOGR: Leveraging Document-Oriented Contrastive Learning in Generative Retrieval [10.770281363775148]
  We propose a novel and general generative retrieval framework, namely Leveraging Document-Oriented Contrastive Learning in Generative Retrieval (DOGR)<n>It adopts a two-stage learning strategy that captures the relationship between queries and documents comprehensively through direct interactions.<n>Negative sampling methods and corresponding contrastive learning objectives are implemented to enhance the learning of semantic representations.
  arXiv  Detail & Related papers  (2025-02-11T03:25:42Z)
• Generative Retrieval Meets Multi-Graded Relevance [104.75244721442756]
  We introduce a framework called GRaded Generative Retrieval (GR$2$) GR$2$ focuses on two key components: ensuring relevant and distinct identifiers, and implementing multi-graded constrained contrastive training. Experiments on datasets with both multi-graded and binary relevance demonstrate the effectiveness of GR$2$.
  arXiv  Detail & Related papers  (2024-09-27T02:55:53Z)
• Knowledge-Driven Cross-Document Relation Extraction [3.868708275322908]
  Relation extraction (RE) is a well-known NLP application often treated as a sentence- or document-level task. We propose a novel approach, KXDocRE, that embed domain knowledge of entities with input text for cross-document RE.
  arXiv  Detail & Related papers  (2024-05-22T11:30:59Z)
• Unified Pretraining Framework for Document Understanding [52.224359498792836]
  We present UDoc, a new unified pretraining framework for document understanding. UDoc is designed to support most document understanding tasks, extending the Transformer to take multimodal embeddings as input. An important feature of UDoc is that it learns a generic representation by making use of three self-supervised losses.
  arXiv  Detail & Related papers  (2022-04-22T21:47:04Z)
• GERE: Generative Evidence Retrieval for Fact Verification [57.78768817972026]
  We propose GERE, the first system that retrieves evidences in a generative fashion. The experimental results on the FEVER dataset show that GERE achieves significant improvements over the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-04-12T03:49:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.