# Scientific Paper Retrieval with LLM-Guided Semantic-Based Ranking

arXiv: https://arxiv.org/abs/2505.21815 · HTML: https://mlsanity.com/paper/2505.21815/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 40 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 30 of 31)

- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models](https://mlsanity.com/paper/2405.17428/) (2024)
- [RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2010.08191/) (2020)
- [Generate rather than Retrieve: Large Language Models are Strong Context Generators](https://mlsanity.com/paper/2209.10063/) (2022)
- [Generative Representational Instruction Tuning](https://mlsanity.com/paper/2402.09906/) (2024)
- [Distilling Knowledge from Reader to Retriever for Question Answering](https://mlsanity.com/paper/2012.04584/) (2020)
- [Sparse, Dense, and Attentional Representations for Text Retrieval](https://mlsanity.com/paper/2005.00181/) (2020)
- [Generation-Augmented Retrieval for Open-domain Question Answering](https://mlsanity.com/paper/2009.08553/) (2020)
- [Optimizing Dense Retrieval Model Training with Hard Negatives](https://mlsanity.com/paper/2104.08051/) (2021)
- [SciRepEval: A Multi-Format Benchmark for Scientific Document Representations](https://mlsanity.com/paper/2211.13308/) (2022)
- [PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval](https://mlsanity.com/paper/2108.06027/) (2021)
- [Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback](https://mlsanity.com/paper/2108.13454/) (2021)
- [BERT-QE: Contextualized Query Expansion for Document Re-ranking](https://mlsanity.com/paper/2009.07258/) (2020)
- [Pseudo-Relevance Feedback for Multiple Representation Dense Retrieval](https://mlsanity.com/paper/2106.11251/) (2021)
- [TELEClass: Taxonomy Enrichment and LLM-Enhanced Hierarchical Text Classification with Minimal Supervision](https://mlsanity.com/paper/2403.00165/) (2024)
- [Keyphrase Generation for Scientific Document Retrieval](https://mlsanity.com/paper/2106.14726/) (2021)
- [Adaptive Re-Ranking with a Corpus Graph](https://mlsanity.com/paper/2208.08942/) (2022)
- [CSFCube -- A Test Collection of Computer Science Research Articles for Faceted Query by Example](https://mlsanity.com/paper/2103.12906/) (2021)
- [The Effect of Metadata on Scientific Literature Tagging: A Cross-Field Cross-Model Study](https://mlsanity.com/paper/2302.03341/) (2023)
- [Sparse Meets Dense: A Hybrid Approach to Enhance Scientific Document Retrieval](https://mlsanity.com/paper/2401.04055/) (2024)
- [Taxonomy-guided Semantic Indexing for Academic Paper Search](https://mlsanity.com/paper/2410.19218/) (2024)
- [Improving Retrieval in Theme-specific Applications using a Corpus Topical Taxonomy](https://mlsanity.com/paper/2403.04160/) (2024)
- [Entity Retrieval for Answering Entity-Centric Questions](https://mlsanity.com/paper/2408.02795/) (2024)
- [textttMixGR: Enhancing Retriever Generalization for Scientific Domain through Complementary Granularity](https://mlsanity.com/paper/2407.10691/) (2024)
- [Improving Scientific Document Retrieval with Concept Coverage-based Query Set Generation](https://mlsanity.com/paper/2502.11181/) (2025)
- [Noisy Pair Corrector for Dense Retrieval](https://mlsanity.com/paper/2311.03798/) (2023)

## Built on by (most cited first, 10 of 10)

- [SurveyG: A Multi-Agent LLM Framework with Hierarchical Citation Graph for Automated Survey Generation](https://mlsanity.com/paper/2510.07733/) (2025)
- [PaperScout: An Autonomous Agent for Academic Paper Search with Process-Aware Sequence-Level Policy Optimization](https://mlsanity.com/paper/2601.10029/) (2026)
- [PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing](https://mlsanity.com/paper/2508.11116/) (2025)
- [Rethinking Literature Search Evaluation: Deep Research Helps, and Human Citation Lists Are Not a Ground Truth](https://mlsanity.com/paper/2605.29234/) (2026)
- [Using Artificial Intuition in Distinct, Minimalist Classification of Scientific Abstracts for Management of Technology Portfolios](https://mlsanity.com/paper/2508.13182/) (2025)
- [Improving Scientific Document Retrieval with Academic Concept Index](https://mlsanity.com/paper/2601.00567/) (2026)
- [AI Co-Scientist for Knowledge Synthesis in Medical Contexts: A Proof of Concept](https://mlsanity.com/paper/2601.11825/) (2026)
- [AiraXiv: An AI-Driven Open-Access Platform for Human and AI Scientists](https://mlsanity.com/paper/2605.21481/) (2026)
- [Scientific Knowledge Discovery in the Age of Large Language Models](https://mlsanity.com/paper/2607.26670/) (2026)
- [GRAFT: Graph-Distilled Generative Retrieval for Facet-Aware Scientific Literature Exploration](https://mlsanity.com/paper/2608.22381/) (2026)

## Abstract (arXiv)

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 using multi-granular 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 existing LLM-based baselines, and remains highly efficient.