ReTAG: Retrieval-Enhanced, Topic-Augmented Graph-Based Global Sensemaking
On the map: LLM reasoning → Knowledge- and tool-augmented reasoning
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 20 of its 34 references that are in the map. First posted on arXiv 30 Sep 2025.
Builds on
20 of 34 references.
Closest ancestors · 2
Same direction, newest first
- 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph15 Jul
- 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions20 Dec
Other references · 18
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
- 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
- 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
- 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
- 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
- 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
- 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
- 2018From Louvain to Leiden: guaranteeing well-connected communitiescited by 385
- 2024MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queriescited by 257
- 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 152
6 more
- 2019Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answeringcited by 147
- 2020Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherencecited by 121
- 2020Leveraging Graph to Improve Abstractive Multi-Document Summarizationcited by 67
- 2017Graph-based Neural Multi-Document Summarizationcited by 54
- 2021BASS: Boosting Abstractive Summarization with Unified Semantic Graphcited by 21
- 2025ReSCORE: Label-free Iterative Retriever Training for Multi-hop Question Answering with Relevance-Consistency Supervisioncited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.
- 2026Core-based Hierarchies for Efficient GraphRAGcited by 2
- 2026Core-based Hierarchies for Efficient GraphRAG5 Mar 2026
Similar, not cited
Close in wording, no citation either way
- 2026KGiRAG: An Iterative GraphRAG Approach for Responding Sensemaking Queries
- 2025REAP: Enhancing RAG with Recursive Evaluation and Adaptive Planning for Multi-Hop Question Answering
- 2025Semantic Bridge: Universal Multi-Hop Question Generation via AMR-Driven Graph Synthesis
- 2025SUBQRAG: Sub-Question Driven Dynamic Graph RAG
- 2025Tagging-Augmented Generation: Assisting Language Models in Finding Intricate Knowledge In Long Contexts
- 2026SentGraph: Hierarchical Sentence Graph for Multi-hop Retrieval-Augmented Question Answering
- 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
- 2026Local-to-Global Sentence-Level Graph Reranking for Scientific Synthesis