ReTAG: Retrieval-Enhanced, Topic-Augmented Graph-Based Global Sensemaking
This addresses a significant problem in question answering for researchers and practitioners, though it appears incremental by building on prior graph-based methods.
The paper tackles the challenge of global sensemaking by synthesizing information from an entire corpus, proposing ReTAG, which improves response quality and significantly reduces inference time compared to a baseline.
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.