# Judge the Judges: A Large-Scale Evaluation Study of Neural Language Models for Online Review Generation

arXiv: https://arxiv.org/abs/1901.00398 · HTML: https://mlsanity.com/paper/1901.00398/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jan 2019.

## Built on by (most cited first, 17 of 17)

- [All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text](https://mlsanity.com/paper/2107.00061/) (2021)
- [The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation](https://mlsanity.com/paper/2109.06835/) (2021)
- [OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metrics](https://mlsanity.com/paper/2105.08920/) (2021)
- [Attacking Open-domain Question Answering by Injecting Misinformation](https://mlsanity.com/paper/2110.07803/) (2021)
- [Language Models Hallucinate, but May Excel at Fact Verification](https://mlsanity.com/paper/2310.14564/) (2023)
- [CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation](https://mlsanity.com/paper/2204.00862/) (2022)
- [The Authenticity Gap in Human Evaluation](https://mlsanity.com/paper/2205.11930/) (2022)
- [Recent Advances in Neural Text Generation: A Task-Agnostic Survey](https://mlsanity.com/paper/2203.03047/) (2022)
- [Automated Evaluation of Personalized Text Generation using Large Language Models](https://mlsanity.com/paper/2310.11593/) (2023)
- [Diffusing Gaussian Mixtures for Generating Categorical Data](https://mlsanity.com/paper/2303.04635/) (2023)
- [Is Human-Like Text Liked by Humans? Multilingual Human Detection and Preference Against AI](https://mlsanity.com/paper/2502.11614/) (2025)
- [Collaborative Evaluation of Deepfake Text with Deliberation-Enhancing Dialogue Systems](https://mlsanity.com/paper/2503.04945/) (2025)
- [Adversarial Machine Learning in Text Analysis and Generation](https://mlsanity.com/paper/2101.08675/) (2021)
- [A Comprehensive Survey of Natural Language Generation Advances from the Perspective of Digital Deception](https://mlsanity.com/paper/2208.05757/) (2022)
- [Collocation2Text: Controllable Text Generation from Guide Phrases in Russian](https://mlsanity.com/paper/2206.09248/) (2022)
- [Evaluation of Categorical Generative Models -- Bridging the Gap Between Real and Synthetic Data](https://mlsanity.com/paper/2210.16405/) (2022)
- [Andha-Dhun: A First Look at Audio Descriptions in Hindi](https://mlsanity.com/paper/2607.06457/) (2026)

## Abstract (arXiv)

We conduct a large-scale, systematic study to evaluate the existing evaluation methods for natural language generation in the context of generating online product reviews. We compare human-based evaluators with a variety of automated evaluation procedures, including discriminative evaluators that measure how well machine-generated text can be distinguished from human-written text, as well as word overlap metrics that assess how similar the generated text compares to human-written references. We determine to what extent these different evaluators agree on the ranking of a dozen of state-of-the-art generators for online product reviews. We find that human evaluators do not correlate well with discriminative evaluators, leaving a bigger question of whether adversarial accuracy is the correct objective for natural language generation. In general, distinguishing machine-generated text is challenging even for human evaluators, and human decisions correlate better with lexical overlaps. We find lexical diversity an intriguing metric that is indicative of the assessments of different evaluators. A post-experiment survey of participants provides insights into how to evaluate and improve the quality of natural language generation systems.