AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Efficient Hallucination Detection: Adaptive Bayesian Estimation of Semantic Entropy with Guided Semantic Exploration

Qiyao Sun, Xingming Li, Xixiang He, Ao Cheng, Xuanyu Ji, Hailun Lu, Runke Huang, Qingyong Hu

AAAI 2026 · Large language models › Language, safety and interpretability · approach: Uncertainty quantification for LLMs · 1 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
use adaptive Bayesian semantic entropy with guided exploration instead of SESDLGLlama-3.1-8B · TriviaQA (N=2)AUROC: .741 -> .855Improved
use adaptive Bayesian semantic entropy instead of SESDLG at larger budgetMistral-Small-24B · SimpleQA (N=5)AUROC: .873 -> .871No clear effect
use adaptive Bayesian semantic entropy instead of SESDLG at low budgetLlama-2-7B · SimpleQA (N=2)AUROC: .891 -> .895No clear effect
add weighted-perplexity adaptive prior (vs fixed K = Kobs + 1) (ablation)Adaptive Bayesian SE · TriviaQA, Llama-3.1-8B (N=2)AUROC: .812 -> .855Improved
add variance-based adaptive sampling with Bayesian framework (vs fixed sampling w/o Bayesian) (ablation)Adaptive Bayesian SE · TriviaQA, Llama-3.1-8B (N=2)AUROC: .759 -> .855Improved
add Bayesian framework to fixed sampling (ablation)Fixed-budget sampling · TriviaQA, Llama-3.1-8B (N=2)AUROC: .759 -> .798Improved
add guided semantic exploration with importance sampling (ablation)Adaptive Bayesian SE · TriviaQA, Llama-3.1-8B (N=2)AUROC: .823 -> .855Improved
add guided semantic exploration with importance sampling (ablation)Adaptive Bayesian SE · TriviaQA, Llama-3.1-8B (N=5)AUROC: .892 -> .913Improved
increase budget from N=2 to N=5 for relative gain over baselinesAdaptive Bayesian SE · Average over 12 settingsAUROC: 12.6% -> 6.3% avg improvementMixed

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