Corank: Llm-based Compact Reranking With Document Features For Scientific Retrieval

Abstract

Scientific retrieval is essential for advancing scientific knowledge discovery. Within this process, document reranking plays a critical role in refining first-stage retrieval results. However, standard LLM listwise reranking faces challenges in the scientific domain. First-stage retrieval is often suboptimal in the scientific domain, so relevant documents are ranked lower. Meanwhile, conventional listwise reranking places the full text of candidates into the context window, limiting the number of candidates that can be considered. As a result, many relevant documents are excluded before reranking, constraining overall retrieval performance. To address these challenges, we explore semantic-feature-based compact document representations (e.g., categories, sections, and keywords) and propose CoRank, a training-free, model-agnostic reranking framework for scientific retrieval. It presents a three-stage solution: (i) offline extraction of document features, (ii) coarse-grained reranking us

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytian2025corank

Related papers

• Rebol: Retrieval Via Bayesian Optimization With Batched LLM Relevance Observations And Query Reformulation (2026)0.00
• Drowning In Documents: Consequences Of Scaling Reranker Inference (2024)0.00
• Unifar: A Unified Facet-aware Retrieval Framework For Scientific Documents (2026)0.00
• CODER: An Efficient Framework For Improving Retrieval Through Contextual Document Embedding Reranking (2021)7.16
• Rank-k: Test-time Reasoning For Listwise Reranking (2025)0.00
• Chain-of-thought Re-ranking For Image Retrieval Tasks (2025)1.81
• Pairsem: Llm-guided Pairwise Semantic Matching For Scientific Document Retrieval (2025)0.00
• Enhancing The Ranking Context Of Dense Retrieval Methods Through Reciprocal Nearest Neighbors (2023)4.52