Statistically Reliable LLM-Based Ranking Evaluation via Prediction-Powered Inference

• URL: http://arxiv.org/abs/2606.05308v1
• Date: Wed, 03 Jun 2026 18:01:08 GMT
• Title: Statistically Reliable LLM-Based Ranking Evaluation via Prediction-Powered Inference
• Abstract summary: We extend Prediction-Powered Inference to produce bias-corrected estimates of ranking evaluation metrics.<n>We make it applicable to hierarchical metrics like Precision@K, where annotations are per-document but the metric is per-query.<n>On the ESCI benchmark, augmenting 30 human annotations with Claude 3 Sonnet judgments reduces the standard error of Precision@4 estimates from 4.45 to 3.50.
• Score: 0.4230349220081444
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: With PRECISE, we extended Prediction-Powered Inference to produce bias-corrected estimates of ranking evaluation metrics by combining a small human-labeled set with a large LLM-judged set. PPI is provably unbiased regardless of the LLM judge's error profile. We make it applicable to hierarchical metrics like Precision@K, where annotations are per-document but the metric is per-query, by reducing the output-space computation from O(2^|C|) to O(2^K). On the ESCI benchmark, augmenting 30 human annotations with Claude 3 Sonnet judgments reduces the standard error of Precision@4 estimates from 4.45 to 3.50 (a 21% relative reduction). In a production system, our framework correctly identified the best of three system variants from 100 human labels and 2 hours of domain-expert annotation; A/B testing confirmed this ranking with +407 bps in daily sales.

Related papers

• A Four-Axis Trustworthiness Benchmark for LLM-as-Judge in Principle-Based Regulation [0.0]
  We release Principle-Bench, 168 cryptoasset financial-promotion scenarios mapped to two UK FCA principles.<n>A calibrated, auditable assessor emits exact per-exemplar counterfactual attributions.<n>Across keyword counting, three sentence-transformer embedders, an open-weight LLM-judge, and a calibrated cascade, no method dominates all four axes.
  arXiv  Detail & Related papers  (2026-08-14T14:20:38Z)
• From Uncertain Judgments to Calibrated Rankings: Conformal Elo Estimation for LLM Evaluation [3.5637034560362935]
  We quantify the resulting judge-human disagreement at two complementary levels.<n>At the local level, we estimate per-battle uncertainty from the judge's own score differences.<n>This alone provides a drastic improvement to Elo estimation accuracy.
  arXiv  Detail & Related papers  (2026-06-11T11:38:05Z)
• Knowledge Index of Noah's Ark [63.143852586221534]
  We introduce KINA, an 899-item benchmark across 261 fine-grained disciplines.<n>We prove a bonus-on-bar tournament weakly FOSD-dominates flat payment in released-review quality.<n>The top model, Gemini-3.1-Pro-Preview, reaches 53.17%, followed by Claude-Opus-4.6 at 49.92% and GPT-5.4 at 48.55%.
  arXiv  Detail & Related papers  (2026-06-03T17:06:49Z)
• VERDI: Single-Call Confidence Estimation for Verification-Based LLM Judges via Decomposed Inference [0.0]
  VERDI (VERification-Decomposed Inference Inference) is a method that extracts confidence from a structured judge.<n> VERDI decomposes each evaluation into sub-checks and derives three structural signals.<n>On three public benchmarks, VERDI achieves AUROC 0.72-0.91 on GPT-4.1-mini and 0.66-0.80 on GPT-5.4-mini.
  arXiv  Detail & Related papers  (2026-05-11T23:39:19Z)
• Judging the Judges: A Systematic Evaluation of Bias Mitigation Strategies in LLM-as-a-Judge Pipelines [0.0]
  We compare nine debiasing strategies across five judge models from four provider families.<n>Style bias is the dominant bias (0.76-0.92 across all models), far exceeding position bias (= 0.04)<n>The combined budget strategy significantly improves Claude Sonnet 4 by +11.2 pp (p 0.0001), with directionally positive trends for other models.
  arXiv  Detail & Related papers  (2026-04-25T07:18:30Z)
• The Verification Tax: Fundamental Limits of AI Auditing in the Rare-Error Regime [0.0]
  Most cited calibration result in deep learning -- post-temperature-scaling ECE of 0.012 on CIFAR-100 -- is below the statistical noise floor.<n>We prove this is not a failure of the experiment but a law: the minimax rate for estimating calibration error with model error rate epsilon is Theta((Lepsilon/m)2/3), and no estimator can beat it.
  arXiv  Detail & Related papers  (2026-04-14T16:48:24Z)
• PRECISE: Reducing the Bias of LLM Evaluations Using Prediction-Powered Ranking Estimation [3.867363075280545]
  Prediction-Powered Inference (PPI) combines minimal human annotations with Large Language Models (LLMs) to produce reliable estimates of metrics.<n>Our method requires as few as 100 human-annotated queries and 10,000 unlabeled examples, reducing annotation requirements significantly.
  arXiv  Detail & Related papers  (2026-01-26T18:46:49Z)
• Rethinking LLM Evaluation: Can We Evaluate LLMs with 200x Less Data? [82.09573568241724]
  EssenceBench is a coarse-to-fine framework utilizing an iterative Genetic Algorithm (GA)<n>Our approach yields superior compression results with lower reconstruction error and markedly higher efficiency.<n>On the HellaSwag benchmark (10K samples), our method preserves the ranking of all models shifting within 5% using 25x fewer samples, and achieves 95% ranking preservation shifting within 5% using only 200x fewer samples.
  arXiv  Detail & Related papers  (2025-10-12T05:38:10Z)
• TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them [58.04324690859212]
  Large Language Models (LLMs) as automated evaluators (LLM-as-a-judge) has revealed critical inconsistencies in current evaluation frameworks.<n>We identify two fundamental types of inconsistencies: Score-Comparison Inconsistency and Pairwise Transitivity Inconsistency.<n>We propose TrustJudge, a probabilistic framework that addresses these limitations through two key innovations.
  arXiv  Detail & Related papers  (2025-09-25T13:04:29Z)
• VADER: A Human-Evaluated Benchmark for Vulnerability Assessment, Detection, Explanation, and Remediation [0.8087612190556891]
  VADER comprises 174 real-world software vulnerabilities, each carefully curated from GitHub and annotated by security experts.<n>For each vulnerability case, models are tasked with identifying the flaw, classifying it using Common Weaknession (CWE), explaining its underlying cause, proposing a patch, and formulating a test plan.<n>Using a one-shot prompting strategy, we benchmark six state-of-the-art LLMs (Claude 3.7 Sonnet, Gemini 2.5 Pro, GPT-4.1, GPT-4.5, Grok 3 Beta, and o3) on VADER.<n>Our results show that current state-of-the-
  arXiv  Detail & Related papers  (2025-05-26T01:20:44Z)
• Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation [136.16507050034755]
  Existing human evaluation studies for summarization either exhibit a low inter-annotator agreement or have insufficient scale. We propose a modified summarization salience protocol, Atomic Content Units (ACUs), which is based on fine-grained semantic units. We curate the Robust Summarization Evaluation (RoSE) benchmark, a large human evaluation dataset consisting of 22,000 summary-level annotations over 28 top-performing systems.
  arXiv  Detail & Related papers  (2022-12-15T17:26:05Z)
• Optimizing Partial Area Under the Top-k Curve: Theory and Practice [151.5072746015253]
  We develop a novel metric named partial Area Under the top-k Curve (AUTKC) AUTKC has a better discrimination ability, and its Bayes optimal score function could give a correct top-K ranking with respect to the conditional probability. We present an empirical surrogate risk minimization framework to optimize the proposed metric.
  arXiv  Detail & Related papers  (2022-09-03T11:09:13Z)
• Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Ranking [57.42241521034744]
  We propose the concept of certified error control of candidate set pruning for relevance ranking. Our method successfully prunes the first-stage retrieved candidate sets to improve the second-stage reranking speed.
  arXiv  Detail & Related papers  (2022-05-19T16:00:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.