Lune

EMNLP Findings2025

Scientific Paper Retrieval with LLM-Guided Semantic-Based Ranking

Yunyi Zhang, Ruozhen Yang, Siqi Jiao, SeongKu Kang, Jiawei Han

Abstract

Scientific paper retrieval is essential for supporting literature discovery and research. While dense retrieval methods demonstrate effectiveness in general-purpose tasks, they often fail to capture fine-grained scientific concepts that are essential for accurate understanding of scientific queries. Recent studies also use large language models (LLMs) for query understanding; however, these methods often lack grounding in corpus-specific knowledge and may generate unreliable or unfaithful content. To overcome these limitations, we propose SemRank, an effective and efficient paper retrieval framework that combines LLM-guided query understanding with a concept-based semantic index. Each paper is indexed offline using multigranular scientific concepts, including general research topics and detailed key phrases. At query time, an LLM identifies core concepts derived from the corpus to explicitly capture the query's information need. These identified concepts enable precise semantic matching, significantly enhancing retrieval accuracy. Experiments show that SemRank consistently improves the performance of various base retrievers, surpasses strong LLM-based baselines, and remains highly efficient. 1

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing cites Precise Zero-Shot Dense Retrieval without Relevance Labels
  • PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing cites Query Rewriting in Retrieval-Augmented Large Language Models
  • PairSem: LLM-Guided Pairwise Semantic Matching for Scientific Document Retrieval cites Precise Zero-Shot Dense Retrieval without Relevance Labels
  • PairSem: LLM-Guided Pairwise Semantic Matching for Scientific Document Retrieval cites Query Rewriting in Retrieval-Augmented Large Language Models
  • PairSem: LLM-Guided Pairwise Semantic Matching for Scientific Document Retrieval cites Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents
  • PairSem: LLM-Guided Pairwise Semantic Matching for Scientific Document Retrieval cites Optimizing Dense Retrieval Model Training with Hard Negatives
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register IndexingZhuoqun Li, Xuanang Chen, Hongyu Lin, Yaojie Lu et al.ACL 2026 · 1 citation
  2. PairSem: LLM-Guided Pairwise Semantic Matching for Scientific Document RetrievalWonbin Kweon, Runchu Tian, Seongku Kang, Pengcheng Jiang et al.WWW 2026

Builds on23

  1. Distilling Knowledge from Reader to Retriever for Question AnsweringGautier Izacard, Edouard GraveICLR 2021 · 317 citations
  2. Optimizing Dense Retrieval Model Training with Hard NegativesJingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo et al.SIGIR 2021 · 242 citations
  3. Precise Zero-Shot Dense Retrieval without Relevance LabelsLuyu Gao, Xueguang Ma, Jimmy Lin, Jamie CallanACL 2023 · 211 citations
  4. Query Rewriting in Retrieval-Augmented Large Language ModelsXinbei Ma, Yeyun Gong, Pengcheng He, Hai Zhao et al.EMNLP 2023 · 191 citations
  5. Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking AgentsWeiwei Sun, Lingyong Yan, Xinyu Ma, Shuaiqiang Wang et al.EMNLP 2023 · 182 citations

Related papers

  1. Taxonomy-guided Semantic Indexing for Academic Paper SearchSeongKu Kang, Yunyi Zhang, Pengcheng Jiang, Dongha Lee et al.EMNLP 2024 · 3 citations
  2. Navigating Through Paper Flood: Advancing LLM-Based Paper Evaluation Through Domain-Aware Retrieval and Latent ReasoningWuqiang Zheng, Yiyan Xu, Xinyu Lin, Chongming Gao et al.AAAI 2026
  3. CG-RAG: Research Question Answering by Citation Graph Retrieval-Augmented LLMsYuntong Hu, Zhihan Lei, Zhongjie Dai, Allen Zhang et al.SIGIR 2025 · 9 citations
  4. Leveraging LLMs for Unsupervised Dense Retriever RankingEkaterina Khramtsova, Shengyao Zhuang, Mahsa Baktashmotlagh, Guido ZucconSIGIR 2024 · 21 citations
  5. Towards a Unified Framework for Reference Retrieval and Related Work GenerationZhengliang Shi, Shen Gao, Zhen Zhang, Xiuying Chen et al.EMNLP Findings 2023 · 7 citations
Dusk over the sea between two cliffs drawn in fine vertical lines