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

Source: [ReTAG: Retrieval-Enhanced, Topic-Augmented Graph-Based Global Sensemaking](<https://www.sota2.com/research/paper/68fa7bc81e209131cea8a742>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:48:24.291Z

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

Published: 2025-09-30T05:41:58.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2509.25814>)

[PDF](<https://arxiv.org/pdf/2509.25814.pdf>)
