AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

HalluClean: A Unified Framework to Combat Hallucinations in LLMs

Yaxin Zhao, Yu Zhang

AAAI 2026 · Large language models › Retrieval and knowledge · approach: Knowledge editing in LLMs

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
add structured plan-then-reason detection to task routing (ablation)GPT-3.5-turbo · QA detectionF1: 39.3% -> 67.8%Improved
add task-oriented routing prompt to direct ask (ablation)GPT-3.5-turbo · Summarization detectionF1: 24.7% -> 60.0%Improved
add task-oriented routing to direct ask (ablation)GPT-3.5-turbo · MWPs detectionaccuracy: 59.5% -> 59.5%No clear effect
add structured reasoning after routing (ablation)GPT-3.5-turbo · Dialogue detectionaccuracy: 67.8% -> 69.3%Improved
HalluClean vs direct askGPT-3.5-turbo · Self-contradiction detectionaccuracy: 64.0% -> 87.0%Improved
HalluClean vs ChatProtect on dialogueGPT-3.5-turbo · Dialogue detectionF1 and accuracy: F1 72.0% -> 74.3%; accuracy 69.3% -> 69.3%Mixed
switch backbone to DeepSeek-V3HalluClean · Math word problems detectionaccuracy: 81.5% -> 89.5%Improved
add retrieval augmentationHalluClean · HaluEval QA detectionF1: 67.8% -> 80.4%Improved
apply HalluClean to Chinese benchmarkGPT-3.5-turbo · HalluQAaccuracy: 46.5% -> 55.0% (HalluQA); 50.0% -> 51.5% (CMHE-HD)Mixed
apply HalluClean revision moduleGPT-3.5-turbo · QA revisionhallucination reduction rate: 20.5% -> 72.5%Improved
HalluClean revision on DeepSeek-V3 vs direct askDeepSeek-V3 · QA revisionhallucination reduction rate: 49.0% -> 74.0%Improved

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