Research map / Large language models / Retrieval and knowledge
CFT-RAG: An Entity Tree Based Retrieval Augmented Generation Algorithm With Cuckoo Filter
Zihang Li, Yangdong Ruan, Wenjun Liu, Zhengyang Wang, Tong Yang
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 |
|---|---|---|---|
| replace naive BFS entity lookup with Cuckoo Filter lookup | Tree-RAG · Retrieval time, 600 trees | time (s): 3.301436 -> 0.023776 | Improved |
| replace naive BFS entity lookup with Cuckoo Filter lookup | Tree-RAG · Answer accuracy, 600 trees | accuracy (%): 66.45 -> 66.50 | No clear effect |
| use Cuckoo Filter instead of Bloom Filter pruning | Tree-RAG · Retrieval time, 600 trees | time (s): 2.638721 -> 0.023776 | Improved |
| skip Bloom Filter checks near leaf nodes (BF2) | Bloom Filter T-RAG · Retrieval time, 600 trees | time (s): 2.638721 -> 2.171958 | Improved |
| increase number of query entities from 5 to 20 | Naive T-RAG · Retrieval time, 600 trees | time (s): 12.615021 -> 38.479844 | Hurt |
| increase number of query entities from 5 to 20 | CFT-RAG · Retrieval time, 600 trees | time (s): 0.074715 -> 0.087526 | No clear effect |
| add temperature-based sorting of fingerprints in buckets (ablation) | CFT-RAG · Retrieval time over query rounds | time | Improved |
Closest papers by meaning
- Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting (ICLR 2025 · similarity 0.86)
- StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization (ICLR 2025 · similarity 0.86)
- RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards (ICLR 2025 · similarity 0.85)
- SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG (NeurIPS 2025 · similarity 0.85)
- Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need? (NeurIPS 2025 · similarity 0.85)
- GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation (NeurIPS 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.
