Scientific Paper Retrieval with LLM-Guided Semantic-Based Ranking
This work addresses the challenge of capturing fine-grained scientific concepts for researchers, though it appears incremental as it builds on existing dense retrieval and LLM-based approaches.
The paper tackled the problem of scientific paper retrieval by proposing SemRank, a framework that combines LLM-guided query understanding with a concept-based semantic index, resulting in consistent performance improvements over existing methods.
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.