Confident Rankings with Fewer Items: Adaptive LLM Evaluation with Continuous Scores
Published 16 Sept 2026arXiv:2601.13885
Updated 12 h ago · first seen 15 Sept 2026
paper_01M2JK0TPQR9FQP96SMPJRKVG5
Abstract
Computerized Adaptive Testing (CAT) has proven effective for efficient LLM evaluation on multiple-choice benchmarks, but modern LLM evaluation increasingly relies on generation tasks where outputs are scored continuously rather than marked correct/incorrect. We present a principled extension of IRT-based adaptive testing to continuous bounded scores (ROUGE, BLEU, LLM-as-a-Judge) by replacing the Bernoulli response distribution with a heteroskedastic normal distribution. Building on this, we introduce an uncertainty aware ranker with adaptive stopping criteria that achieves reliable model ranking while testing as few items and as cheaply as possible. We validate our method on five benchmarks spanning n-gram-based, embedding-based, and LLM-as-judge metrics. Our method improves ranking correlation by 0.13 $\tau$ over random sampling and has 99% accuracy on confident predictions while using 2% of the items after a one-time calibration step.
Organizations
Organizations 0
No organization stated. arXiv metadata does not carry affiliations; an organization is linked only when a model card or lab page cites the paper.
Models
Models introduced or described 0
Inbound described_by relations from model cards and documentation.
No model links this paper yet
Datasets
Datasets used 0
No dataset relation recorded.
Benchmarks
Benchmarks used 0
No benchmark relation recorded.
Code
Repositories & frameworks 0
No repository linked.
Timeline
Timeline 2
- Property changedPaperConfident Rankings with Fewer Items: Adaptive LLM Evaluation with Continuous Scores
Confident Rankings with Fewer Items: Adaptive LLM Evaluation with Continuous Scores: published at changed from 2026-09-15T04:00:00+00:00 to 2026-09-16T04:00:00+00:00
Published15 Sept 2026→16 Sept 2026arxiv New paper: Confident Rankings with Fewer Items: Adaptive LLM Evaluation with Continuous Scores
arxiv
Sources
Sources 2
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.