Year: 2025
Type: preprint
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-based approach to global sensemaking lacks retrieval mechanisms, topic specificity, and incurs high inference costs. To address these limitations, we propose ReTAG, a Retrieval-Enhanced, 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.
Source: arXiv (Cornell University)
Authors: Kim, Boyoung, Lee, Dosung, An, Sumin, Jeong, Jinseong, Seo, Paul Hongsuck
Institutions: Korea University, Korea University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: G7492658114, G7542792045
OpenAlex ID: W7084447221
Cites:
Cited by:
Related to: