# Benchmarking LLMs' Judgments with No Gold Standard

arXiv: https://arxiv.org/abs/2411.07127 · HTML: https://mlsanity.com/paper/2411.07127/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 62 references that are in the map.
- First posted on arXiv 11 Nov 2024.

## Builds on (most cited first, 26 of 26)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [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)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [GPTScore: Evaluate as You Desire](https://mlsanity.com/paper/2302.04166/) (2023)
- [NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark](https://mlsanity.com/paper/2310.18018/) (2023)
- [Proving Test Set Contamination in Black Box Language Models](https://mlsanity.com/paper/2310.17623/) (2023)
- [Time Travel in LLMs: Tracing Data Contamination in Large Language Models](https://mlsanity.com/paper/2308.08493/) (2023)
- [Benchmarking Foundation Models with Language-Model-as-an-Examiner](https://mlsanity.com/paper/2306.04181/) (2023)
- [ReviewerGPT? An Exploratory Study on Using Large Language Models for Paper Reviewing](https://mlsanity.com/paper/2306.00622/) (2023)
- [GPT4 is Slightly Helpful for Peer-Review Assistance: A Pilot Study](https://mlsanity.com/paper/2307.05492/) (2023)
- [Crowdsourced Judgement Elicitation with Endogenous Proficiency](https://mlsanity.com/paper/1303.0799/) (2013)
- [Peer Reviews of Peer Reviews: A Randomized Controlled Trial and Other Experiments](https://mlsanity.com/paper/2311.09497/) (2023)
- [Max-MIG: an Information Theoretic Approach for Joint Learning from Crowds](https://mlsanity.com/paper/1905.13436/) (2019)
- [What Can Natural Language Processing Do for Peer Review?](https://mlsanity.com/paper/2405.06563/) (2024)
- [Eliciting Informative Text Evaluations with Large Language Models](https://mlsanity.com/paper/2405.15077/) (2024)
- [Eliciting Expertise without Verification](https://mlsanity.com/paper/1802.08312/) (2018)
- [Water from Two Rocks: Maximizing the Mutual Information](https://mlsanity.com/paper/1802.08887/) (2018)
- [Measurement Integrity in Peer Prediction: A Peer Assessment Case Study](https://mlsanity.com/paper/2108.05521/) (2021)
- [Spot Check Equivalence: an Interpretable Metric for Information Elicitation Mechanisms](https://mlsanity.com/paper/2402.13567/) (2024)

## Built on by (most cited first, 19 of 19)

- [Don't Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation](https://mlsanity.com/paper/2505.16222/) (2025)
- [Automatic Reviewers Fail to Detect Faulty Reasoning in Research Papers: A New Counterfactual Evaluation Framework](https://mlsanity.com/paper/2508.21422/) (2025)
- [What do Large Language Models Say About Animals? Investigating Risks of Animal Harm in Generated Text](https://mlsanity.com/paper/2503.04804/) (2025)
- [Ad Insertion in LLM-Generated Responses](https://mlsanity.com/paper/2601.19435/) (2026)
- [InfiCoEvalChain: A Blockchain-Based Decentralized Framework for Collaborative LLM Evaluation](https://mlsanity.com/paper/2602.08229/) (2026)
- [Beyond Rating: A Comprehensive Evaluation and Benchmark for AI Reviews](https://mlsanity.com/paper/2604.19502/) (2026)
- [Choosing to Be Green: Advancing Green AI via Dynamic Model Selection](https://mlsanity.com/paper/2509.19996/) (2025)
- [Identity-Link IRT for Label-Free LLM Evaluation: Preserving Additivity in TVD-MI Scores](https://mlsanity.com/paper/2510.14966/) (2025)
- [Incentive-Aligned Multi-Source LLM Summaries](https://mlsanity.com/paper/2509.25184/) (2025)
- [Peer-Predictive Self-Training for Language Model Reasoning](https://mlsanity.com/paper/2604.13356/) (2026)
- [Let's Measure Information Step-by-Step: AI-Based Evaluation Beyond Vibes](https://mlsanity.com/paper/2508.05469/) (2025)
- [From scratch to silver: Creating trustworthy training data for patent-SDG classification using Large Language Models](https://mlsanity.com/paper/2509.09303/) (2025)
- [PMIScore: An Unsupervised Approach to Quantify Dialogue Engagement](https://mlsanity.com/paper/2603.13796/) (2026)
- [Robust LLM Performance Certification via Constrained Maximum Likelihood Estimation](https://mlsanity.com/paper/2604.03257/) (2026)
- [Likelihood scoring for continuations of mathematical text: a self-supervised benchmark with tests for shortcut vulnerabilities](https://mlsanity.com/paper/2605.10810/) (2026)
- [PromptNCE: Conditional Probabilities and PMI Using Only LLMs and Contrastive Estimation Prompts](https://mlsanity.com/paper/2605.21776/) (2026)
- [Scoring Rules! Statistical and Strategic Alignment for Text Evaluation Metrics](https://mlsanity.com/paper/2608.01423/) (2026)
- [Who Drives the Probability Game of VLMs? A Temporal Causal Drive Evaluation Framework](https://mlsanity.com/paper/2609.02000/) (2026)
- [How Is Automated Research Evaluated? A Survey of Benchmarks and Evaluation Practices](https://mlsanity.com/paper/2610.11877/) (2026)

## Abstract (arXiv)

We introduce the GEM (Generative Estimator for Mutual Information), an evaluation metric for assessing language generation by Large Language Models (LLMs), particularly in generating informative judgments, without the need for a gold standard reference. GEM broadens the scenarios where we can benchmark LLM generation performance-from traditional ones, like machine translation and summarization, where gold standard references are readily available, to subjective tasks without clear gold standards, such as academic peer review. GEM uses a generative model to estimate mutual information between candidate and reference responses, without requiring the reference to be a gold standard. In experiments on a human-annotated dataset, GEM demonstrates competitive correlations with human scores compared to the state-of-the-art GPT-4o Examiner, and outperforms all other baselines. Additionally, GEM is more robust against strategic manipulations, such as rephrasing or elongation, which can artificially inflate scores under a GPT-4o Examiner. We also present GRE-bench (Generating Review Evaluation Benchmark) which evaluates LLMs based on how well they can generate high-quality peer reviews for academic research papers. Because GRE-bench is based upon GEM, it inherits its robustness properties. Additionally, GRE-bench circumvents data contamination problems (or data leakage) by using the continuous influx of new open-access research papers and peer reviews each year. We show GRE-bench results of various popular LLMs on their peer review capabilities using the ICLR2023 dataset.