# Rating the Raters: Rasch Measurement Theory for LLM Evaluation

arXiv: https://arxiv.org/abs/2608.27463 · HTML: https://mlsanity.com/paper/2608.27463/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 55 references that are in the map.
- First posted on arXiv 14 Jul 2026.

## Builds on (most cited first, 21 of 21)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection](https://mlsanity.com/paper/2111.07997/) (2021)
- [Do LLMs exhibit human-like response biases? A case study in survey design](https://mlsanity.com/paper/2311.04076/) (2023)
- [MultiVerS: Improving scientific claim verification with weak supervision and full-document context](https://mlsanity.com/paper/2112.01640/) (2021)
- [Toward a Perspectivist Turn in Ground Truthing for Predictive Computing](https://mlsanity.com/paper/2109.04270/) (2021)
- [The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs](https://mlsanity.com/paper/2501.10970/) (2025)
- [Position: Evaluating Generative AI Systems Is a Social Science Measurement Challenge](https://mlsanity.com/paper/2502.00561/) (2025)
- [Comparing Test Sets with Item Response Theory](https://mlsanity.com/paper/2106.00840/) (2021)
- [Measurement to Meaning: A Validity-Centered Framework for AI Evaluation](https://mlsanity.com/paper/2505.10573/) (2025)
- [Toward an Evaluation Science for Generative AI Systems](https://mlsanity.com/paper/2503.05336/) (2025)
- [Large Language Model Psychometrics: A Systematic Review of Evaluation, Validation, and Enhancement](https://mlsanity.com/paper/2505.08245/) (2025)
- [Evaluating Scoring Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2506.22316/) (2025)
- [Human and LLM Biases in Hate Speech Annotations: A Socio-Demographic Analysis of Annotators and Targets](https://mlsanity.com/paper/2410.07991/) (2024)
- [Noisy but Valid: Robust Statistical Evaluation of LLMs with Imperfect Judges](https://mlsanity.com/paper/2601.20913/) (2026)
- [Diagnosing the Reliability of LLM-as-a-Judge via Item Response Theory](https://mlsanity.com/paper/2602.00521/) (2026)
- [Efficient Inference for Noisy LLM-as-a-Judge Evaluation](https://mlsanity.com/paper/2601.05420/) (2026)
- [Am I More Pointwise or Pairwise? Revealing Position Bias in Rubric-Based LLM-as-a-Judge](https://mlsanity.com/paper/2602.02219/) (2026)
- [Improving LLM Leaderboards with Psychometrical Methodology](https://mlsanity.com/paper/2501.17200/) (2025)

## Built on by (most cited first, 1 of 1)

- [Is the Platform Part of the Measurement? A Protocol and Simulation Study for Cross-Platform Equivalence of Machine-Labelled Policy Sentiment](https://mlsanity.com/paper/2610.16757/) (2026)

## Abstract (arXiv)

LLMs now sit on every side of evaluation: as examinees scored on benchmarks, judges of other models' outputs, and raters of human-generated content. Each paradigm can be viewed as a measurement problem, where a latent property of an object is probed with items from an instrument (e.g., benchmark) by judges or raters. Standard evaluation practices often neglect the contributions of each core component to the end result, limiting our understanding of what is being measured. Rasch measurement theory (RMT) is well-suited to this problem. RMT decomposes ordinal ratings into separable facets on a common scale. It further provides a battery of diagnostics that can identify miscalibrated measurements and rater biases. We present a case study of RMT applied to the LLM-as-rater paradigm using the Measuring Hate Speech corpus, whose construct was itself built under RMT. We fit a series of many-facet Rasch models to annotations from nine LLMs spanning families and capability levels. Our analyses show that LLMs systematically differ from human raters in severity, item-level calibration, question-order robustness, target-identity sensitivity, and rating scale use, all of which standard evaluation practice would largely obscure. Overall, we argue that RMT belongs in the toolkit for evaluating LLM-as-examinee, -judge, and -rater paradigms.