Research map / Large language models / Retrieval and knowledge
BrowseNet: Knowledge Graph-Based Associative Memory for Contextual Information Retrieval
PAVAN KUMAR S, Kiran Kumar Nakka, C Vamshi Krishna Reddy, Divyateja Pasupuleti, Prakhar Agarwal, Harpinder Jot Singh, Anshu Avinash, Nirav Pravinbhai Bhatt
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| query-specific graph-of-chunks traversal instead of dense retrieval alone (BrowseNet vs NV-Embed-v2) | retrieval · 2WikiMQA | Recall@5: 76.72 -> 93.30 | Improved |
| BrowseNet instead of HippoRAG-2 | retrieval · MuSiQue | Recall@5: 74.20 -> 73.91 | No clear effect |
| BrowseNet instead of NV-Embed-v2 | retrieval · HotpotQA | Recall@2: 83.95 -> 83.85 | No clear effect |
| BrowseNet instead of HippoRAG-2 | answer generation · MuSiQue | Exact Match: 35.00 -> 41.60 | Improved |
| BrowseNet instead of HippoRAG-2 | answer generation · 2WikiMQA | Exact Match: 60.50 -> 63.90 | Improved |
| use graph-of-chunks to restrict corpus (ablation) | BrowseNet · MuSiQue (100 questions) | Recall@5 and time: 70.75 -> 75.08; 177 s -> 115 s | Improved |
| lower ColBERT synonymity threshold to 0.7 (ablation) | BrowseNet · Average retrieval | Recall@5: 87.87 -> 87.72 | No clear effect |
| increase n_subgraphs to 10 or 15 (ablation) | BrowseNet · Average retrieval | Recall@5: 87.87 -> 87.71 | No clear effect |
| use Claude-3.7-Sonnet as query decomposer instead of GPT-4o (ablation) | BrowseNet · Average retrieval | Recall@5: 87.87 -> 86.37 | Hurt |
| replace NV-Embed-v2 encoder with GTE-Qwen2 (7B) (ablation) | BrowseNet · Average retrieval | Recall@5: 87.87 -> 81.90 | Hurt |
| use BrowseNet instead of NaiveRAG with Granite-125M encoder | retrieval · Average Recall@5 | Recall@5: 71.76 -> 81.39 | Improved |
| answer with gpt-3.5-turbo instead of gpt-4o-mini (ablation) | BrowseNet · Average QA | Exact Match: 55.90 -> 47.97 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- HippoRAG-2 — HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models (NeurIPS 2024) · better on 6 of 7 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation (ICLR 2025 · similarity 0.87)
- Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation (ICLR 2025 · similarity 0.87)
- Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need? (NeurIPS 2025 · similarity 0.87)
- ReMindRAG: Low-Cost LLM-Guided Knowledge Graph Traversal for Efficient RAG (NeurIPS 2025 · similarity 0.87)
- HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation (NeurIPS 2025 · similarity 0.86)
- A Systematic Exploration of Knowledge Graph Alignment with Large Language Models in Retrieval Augmented Generation (AAAI 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
