AI Paper Atlas

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

ICLR 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation · 6 citations (OpenAlex)

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 changedWhereMeasuredEffect
replace naive BFS entity lookup with Cuckoo Filter lookupTree-RAG · Retrieval time, 600 treestime (s): 3.301436 -> 0.023776Improved
replace naive BFS entity lookup with Cuckoo Filter lookupTree-RAG · Answer accuracy, 600 treesaccuracy (%): 66.45 -> 66.50No clear effect
use Cuckoo Filter instead of Bloom Filter pruningTree-RAG · Retrieval time, 600 treestime (s): 2.638721 -> 0.023776Improved
skip Bloom Filter checks near leaf nodes (BF2)Bloom Filter T-RAG · Retrieval time, 600 treestime (s): 2.638721 -> 2.171958Improved
increase number of query entities from 5 to 20Naive T-RAG · Retrieval time, 600 treestime (s): 12.615021 -> 38.479844Hurt
increase number of query entities from 5 to 20CFT-RAG · Retrieval time, 600 treestime (s): 0.074715 -> 0.087526No clear effect
add temperature-based sorting of fingerprints in buckets (ablation)CFT-RAG · Retrieval time over query roundstimeImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy