# Evaluating the Evaluation of Diversity in Natural Language Generation

arXiv: https://arxiv.org/abs/2004.02990 · HTML: https://mlsanity.com/paper/2004.02990/

## Key facts

- Cited by 129 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Apr 2020.

## Built on by (most cited first, 30 of 129)

- [Understanding the Effects of RLHF on LLM Generalisation and Diversity](https://mlsanity.com/paper/2310.06452/) (2023)
- [Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias](https://mlsanity.com/paper/2306.15895/) (2023)
- [Does Writing with Language Models Reduce Content Diversity?](https://mlsanity.com/paper/2309.05196/) (2023)
- [COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability](https://mlsanity.com/paper/2402.08679/) (2024)
- [The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text](https://mlsanity.com/paper/2311.09807/) (2023)
- [Curiosity-driven Red-teaming for Large Language Models](https://mlsanity.com/paper/2402.19464/) (2024)
- [LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts](https://mlsanity.com/paper/2410.10700/) (2024)
- [Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models](https://mlsanity.com/paper/2310.05338/) (2023)
- [Evaluating Large Language Model Biases in Persona-Steered Generation](https://mlsanity.com/paper/2405.20253/) (2024)
- [NoveltyBench: Evaluating Language Models for Humanlike Diversity](https://mlsanity.com/paper/2504.05228/) (2025)
- [One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity](https://mlsanity.com/paper/2411.04427/) (2024)
- [Flipping the Dialogue: Training and Evaluating User Language Models](https://mlsanity.com/paper/2510.06552/) (2025)
- [Diverse Preference Optimization](https://mlsanity.com/paper/2501.18101/) (2025)
- [What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variability](https://mlsanity.com/paper/2305.11707/) (2023)
- [Evaluating the Diversity and Quality of LLM Generated Content](https://mlsanity.com/paper/2504.12522/) (2025)
- [Standardizing the Measurement of Text Diversity: A Tool and a Comparative Analysis of Scores](https://mlsanity.com/paper/2403.00553/) (2024)
- [Forcing Diffuse Distributions out of Language Models](https://mlsanity.com/paper/2404.10859/) (2024)
- [Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding](https://mlsanity.com/paper/2502.01563/) (2025)
- [The Price of Format: Diversity Collapse in LLMs](https://mlsanity.com/paper/2505.18949/) (2025)
- [Benchmarking Language Model Creativity: A Case Study on Code Generation](https://mlsanity.com/paper/2407.09007/) (2024)
- [Modifying Large Language Model Post-Training for Diverse Creative Writing](https://mlsanity.com/paper/2503.17126/) (2025)
- [Benchmarking Linguistic Diversity of Large Language Models](https://mlsanity.com/paper/2412.10271/) (2024)
- [The Homogenizing Effect of Large Language Models on Human Expression and Thought](https://mlsanity.com/paper/2508.01491/) (2025)
- [From Distributional to Overton Pluralism: Investigating Large Language Model Alignment](https://mlsanity.com/paper/2406.17692/) (2024)
- [On the Challenges and Opportunities in Generative AI](https://mlsanity.com/paper/2403.00025/) (2024)
- [CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation](https://mlsanity.com/paper/2204.00862/) (2022)
- [Semantic Diversity in Dialogue with Natural Language Inference](https://mlsanity.com/paper/2205.01497/) (2022)
- [Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models](https://mlsanity.com/paper/2408.02085/) (2024)
- [Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs](https://mlsanity.com/paper/2402.11442/) (2024)
- [LLM Probability Concentration: How Alignment Shrinks the Generative Horizon](https://mlsanity.com/paper/2506.17871/) (2025)

## Abstract (arXiv)

Despite growing interest in natural language generation (NLG) models that produce diverse outputs, there is currently no principled method for evaluating the diversity of an NLG system. In this work, we propose a framework for evaluating diversity metrics. The framework measures the correlation between a proposed diversity metric and a diversity parameter, a single parameter that controls some aspect of diversity in generated text. For example, a diversity parameter might be a binary variable used to instruct crowdsourcing workers to generate text with either low or high content diversity. We demonstrate the utility of our framework by: (a) establishing best practices for eliciting diversity judgments from humans, (b) showing that humans substantially outperform automatic metrics in estimating content diversity, and (c) demonstrating that existing methods for controlling diversity by tuning a "decoding parameter" mostly affect form but not meaning. Our framework can advance the understanding of different diversity metrics, an essential step on the road towards better NLG systems.