박준 석박통합과정, 권준 석박통합과정, 김종효 석박통합과정 EMNLP 2026 국제 학술대회 논문 채택 

26 Aug 2026

DIAL 연구실 소속 소프트웨어학과 박준(석박통합과정, 공동 제1저자) 학생, 권준(석박통합과정, 공동 제1저자) 학생, 김종효(석박통합과정, 제3저자) 학생, 이종욱(교신저자) 교수가 참여한 논문 "Group-Level Expansion in Graph-based Adaptive Retrieval"이 자연어처리 분야 최우수 국제 학술대회인 The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026)에 게재 승인되었으며 오는 10월에 발표될 예정입니다.

Abstract

Reasoning-intensive retrieval addresses queries whose relevance cannot be identified by surface-level matching, thereby requiring multi-step reasoning. Because relevant documents rarely appear in the initial candidate set, retrieval systems suffer from the bounded recall problem. Existing methods iteratively expand a candidate pool at the document level over a corpus graph, examining each neighbor in isolation and drifting toward a narrow region of the corpus. To address this problem, we propose Group-Aware Adaptive Retrieval for Evidence Navigation (GAREN), which explores the corpus graph through group-level expansion. GAREN organizes documents into semantically coherent and distinguishable groups based on their connections in the corpus graph. The information in each group indicates what can be accessed by expanding through it, providing guidance beyond individual document-level signals. At each iteration, GAREN uses a group-level navigator to identify promising expansion directions, retrieves documents from the selected groups, and applies a document-level reranker to evaluate the updated candidate set. Extensive experiments show that GAREN achieves up to 8.0% improvement over the strongest baseline on BRIGHT.