ReTAG: Retrieval-Enhanced, Topic-Augmented Graph-Based Global Sensemaking

Boyoung Kim, Dosung Lee, Sumin An, Jinseong Jeong, Paul Hongsuck Seo


Abstract
Recent advances in question answering have led to substantial progress in tasks such as multi-hop reasoning. However, global sensemaking—answering questions by synthesizing information from an entire corpus—remains a significant challenge. A prior graph-basedapproach to global sensemaking lacks retrieval mechanisms, topic specificity, and incurs high inference costs. To address these limitations, we propose ReTAG, a RetrievalEnhanced, Topic-Augmented Graph framework that constructs topic-specific subgraphs and retrieves the relevant summaries for response generation. Experiments show that ReTAG improves response quality while significantly reducing inference time compared to the baseline. Our code is available at https://github.com/bykimby/retag.
Anthology ID:
2025.findings-emnlp.1212
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
22249–22277
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.1212/
DOI:
Bibkey:
Cite (ACL):
Boyoung Kim, Dosung Lee, Sumin An, Jinseong Jeong, and Paul Hongsuck Seo. 2025. ReTAG: Retrieval-Enhanced, Topic-Augmented Graph-Based Global Sensemaking. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 22249–22277, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
ReTAG: Retrieval-Enhanced, Topic-Augmented Graph-Based Global Sensemaking (Kim et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.1212.pdf
Checklist:
 2025.findings-emnlp.1212.checklist.pdf