AI Paper Atlas

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

Multi-LLM Adaptive Conformal Inference for Reliable LLM Response

Kangjun Noh, Seongchan Lee, Ilmun Kim, Kyungwoo Song

ICLR 2026 · Large language models › Language, safety and interpretability · approach: Uncertainty quantification for 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
use MACI multiplicative group-conditional conformal filtering instead of BCIMACI · MedLFQA, 90% targetretention ratio: 0.02 -> 0.50Improved
use MACI instead of CCIMACI · WikiBio, 90% targetretention ratio: 0.11 -> 0.25Improved
use MACI instead of CCI on ExpertQA at high coverage targetsMACI · ExpertQA, 95% targetretention ratio: 0.17 -> 0.10Hurt
group-conditional calibration (Mondrian) in place of a single global threshold (ablation)MACI · MedLFQA/WikiBio/ExpertQA groupsgroup coverageImproved
replace worst-claim conformity score with cumulative product of factuality-scores (ablation)MACI · all datasetsretention ratioImproved
ensemble three LLM scorers with FPR-optimized weights instead of single LLM or arithmetic mean (ablation)MACI factuality-score · MedLFQAFPR, MSE and retentionImproved
add density-ratio resampling of calibration set (MACI-DRE) under covariate shift (ablation)MACI · MedLFQA covariate shift, Medium risk, 90% targetcoverage: 0.82 -> 0.94Mixed
use MACI single-pass scoring and streamlined calibration instead of CCIMACI · WikiBio, 500 test sampleswall-clock time (s): 1643.91 -> 598.98Improved
let CCI use adaptive alpha to match MACI retentionCCI · WikiBiocoverageHurt

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.

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

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