Chain of Retrieval: Multi-Aspect Iterative Search Expansion and Post-Order Search Aggregation for Full Paper Retrieval

TL;DR

This paper introduces Chain of Retrieval (COR), an iterative, multi-aspect full-paper retrieval framework that builds a hierarchical search tree and outperforms existing methods on a new large-scale benchmark.

Contribution

COR is a novel iterative retrieval framework that decomposes papers into multiple aspects, expands search iteratively, and aggregates results hierarchically, improving full-paper retrieval accuracy.

Findings

COR significantly outperforms existing retrieval baselines.

The SCIFULLBENCH dataset enables comprehensive evaluation of full-paper retrieval methods.

Hierarchical aggregation captures complex relations across retrieval iterations.

Abstract

Scientific paper retrieval, particularly framed as document-to-document retrieval, aims to identify relevant papers in response to a long-form query paper, rather than a short query string. Previous approaches to this task have focused exclusively on abstracts, embedding them into dense vectors as surrogates for full documents and calculating similarity between them. Yet, abstracts offer only sparse and high-level summaries, and such methods primarily optimize one-to-one similarity, overlooking the dynamic relations that emerge across relevant papers during the retrieval process. To address this, we propose Chain of Retrieval(COR), a novel iterative framework for full-paper retrieval. Specifically, COR decomposes each query paper into multiple aspect-specific views, matches them against segmented candidate papers, and iteratively expands the search by promoting top-ranked results as new queries, thereby forming a tree-structured retrieval process. The resulting retrieval tree is then aggregated in a post-order manner: descendants are first combined at the query level, then recursively merged with their parent nodes, to capture hierarchical relations across iterations. To validate this, we present SCIFULLBENCH, a large-scale benchmark providing both complete and segmented contexts of full papers for queries and candidates, and results show that COR significantly outperforms existing retrieval baselines. Our code and dataset is available at https://github.com/psw0021/Chain-of-Retrieval-Official.