Scientific Paper Retrieval with LLM-Guided Semantic-Based Ranking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yunyi, Yang, Ruozhen, Jiao, Siqi, Kang, SeongKu, Han, Jiawei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912628509507584
author Zhang, Yunyi
Yang, Ruozhen
Jiao, Siqi
Kang, SeongKu
Han, Jiawei
author_facet Zhang, Yunyi
Yang, Ruozhen
Jiao, Siqi
Kang, SeongKu
Han, Jiawei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_21815
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Scientific Paper Retrieval with LLM-Guided Semantic-Based Ranking
Zhang, Yunyi
Yang, Ruozhen
Jiao, Siqi
Kang, SeongKu
Han, Jiawei
Information Retrieval
Artificial Intelligence
Computation and Language
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.
title Scientific Paper Retrieval with LLM-Guided Semantic-Based Ranking
topic Information Retrieval
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2505.21815