# Right Order, Wrong Scale: Auditing LLM Judges for Occupational AI Measurement

arXiv: https://arxiv.org/abs/2610.02492 · HTML: https://mlsanity.com/paper/2610.02492/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 37 references that are in the map.
- First posted on arXiv 1 Oct 2026.

## Builds on (most cited first, 24 of 24)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [RewardBench: Evaluating Reward Models for Language Modeling](https://mlsanity.com/paper/2403.13787/) (2024)
- [Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models](https://mlsanity.com/paper/2405.01535/) (2024)
- [JudgeLM: Fine-tuned Large Language Models are Scalable Judges](https://mlsanity.com/paper/2310.17631/) (2023)
- [Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2406.07791/) (2024)
- [LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks](https://mlsanity.com/paper/2406.18403/) (2024)
- [Prediction-Powered Inference](https://mlsanity.com/paper/2301.09633/) (2023)
- [GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks](https://mlsanity.com/paper/2510.04374/) (2025)
- [Position: Evaluating Generative AI Systems Is a Social Science Measurement Challenge](https://mlsanity.com/paper/2502.00561/) (2025)
- [Limits to scalable evaluation at the frontier: LLM as Judge won't beat twice the data](https://mlsanity.com/paper/2410.13341/) (2024)
- [Future of Work with AI Agents: Auditing Automation and Augmentation Potential across the U.S. Workforce](https://mlsanity.com/paper/2506.06576/) (2025)
- [Beyond correlation: The Impact of Human Uncertainty in Measuring the Effectiveness of Automatic Evaluation and LLM-as-a-Judge](https://mlsanity.com/paper/2410.03775/) (2024)
- [JuStRank: Benchmarking LLM Judges for System Ranking](https://mlsanity.com/paper/2412.09569/) (2024)
- [Anthropic Economic Index report: Uneven geographic and enterprise AI adoption](https://mlsanity.com/paper/2511.15080/) (2025)
- [Validating LLM-as-a-Judge Systems under Rating Indeterminacy](https://mlsanity.com/paper/2503.05965/) (2025)
- [ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge](https://mlsanity.com/paper/2510.18941/) (2025)
- [When the Judge Changes, So Does the Measurement: Auditing LLM-as-Judge Reliability](https://mlsanity.com/paper/2607.08535/) (2026)
- [Agreement Metrics for LLM-as-Judge Evaluation: What to Report and Why](https://mlsanity.com/paper/2606.00093/) (2026)
- [LINKAGE: Listwise Ranking among Varied-Quality References for Non-Factoid QA Evaluation via LLMs](https://mlsanity.com/paper/2409.14744/) (2024)
- [Crashing Waves vs. Rising Tides: Findings on AI Automation from Thousands of Worker Evaluations of Labor Market Tasks](https://mlsanity.com/paper/2604.01363/) (2026)

## Abstract (arXiv)

LLM judges are increasingly used to assess whether AI outputs meet workplace requirements, but agreement on response rankings does not establish agreement on acceptance rates or occupational aggregates. We introduce O*NET-BENCH, an audit suite derived from an existing survey of 45,796 worker ratings, and evaluate 33 pre-existing judge configurations across six model families on 4,501 test ratings. Twenty-five configurations achieve tie-aware pair accuracy of at least 0.60, although a train-fitted response-only TF-IDF baseline nearly matches the strongest judge. Despite this ordering agreement, judges estimate that 3.0%-97.9% of responses are acceptable, compared with 61.1% for occupation-matched workers. In one fine-tuned lineage, changing from pointwise scoring to a bundled few-shot/listwise protocol improves response ordering while reducing agreement with worker means at the task and occupation levels; this reversal replicates on a task- and worker-disjoint validation split under prespecified criteria. Cross-validated calibration largely removes mean bias, but calibrated scores explain at most 8.5% of individual worker-rating variance. Prediction-assisted estimation yields at most small precision gains at the studied label budgets. These results show that ranking agreement alone is insufficient for occupational measurement. Judges should be validated against the acceptance rates and aggregates their scores will be used to estimate.