mlsanityData to 7 Oct 2026

MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers

arXiv 2102.01454 ↗First posted 2 Feb 2021cs.CLcited by 466

Not on the map. Why?

Cited by 76 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

As major progress is made in open-ended text generation, measuring how close machine-generated text is to human language remains a critical open problem. We introduce MAUVE, a comparison measure for open-ended text generation, which directly compares the learnt distribution from a text generation model to the distribution of human-written text using divergence frontiers. MAUVE scales up to modern text generation models by computing information divergences in a quantized embedding space. Through an extensive empirical study on three open-ended generation tasks, we find that MAUVE identifies known properties of generated text, scales naturally with model size, and correlates with human judgments, with fewer restrictions than existing distributional evaluation metrics.

Key facts. Cited by 466 papers in the map (data through 7 Oct 2026). Builds on 37 of its 72 references that are in the map. First posted on arXiv 2 Feb 2021.

Builds on

37 of 72 references.

References · 37

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  6. 2016Improved Techniques for Training GANscited by 2,938
  7. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  8. 2018Demystifying MMD GANscited by 1,268
  9. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
  10. 2018Hierarchical Neural Story Generationcited by 1,182
  11. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  12. 2019Defending Against Neural Fake Newscited by 553
25 more
  1. 2019Neural Text Generation with Unlikelihood Trainingcited by 489
  2. 2018Texygen: A Benchmarking Platform for Text Generation Modelscited by 484
  3. 2019MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distancecited by 415
  4. 2018Assessing Generative Models via Precision and Recallcited by 401
  5. 2016From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classificationcited by 337
  6. 2020Evaluation of Text Generation: A Surveycited by 275
  7. 2019Automatic Detection of Generated Text is Easiest when Humans are Fooledcited by 260
  8. 2016Revisiting Classifier Two-Sample Testscited by 258
  9. 2017Why We Need New Evaluation Metrics for NLGcited by 232
  10. 2019The Second Conversational Intelligence Challenge (ConvAI2)cited by 178
  11. 2020A Survey of Evaluation Metrics Used for NLG Systemscited by 164
  12. 2020Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translationcited by 137
  13. 2019Unifying Human and Statistical Evaluation for Natural Language Generationcited by 127
  14. 2018Spreading vectors for similarity searchcited by 114
  15. 2020PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Trackingcited by 104
  16. 2018Language GANs Falling Shortcited by 97
  17. 2020Trading Off Diversity and Quality in Natural Language Generationcited by 94
  18. 2017RUBER: An Unsupervised Method for Automatic Evaluation of Open-Domain Dialog Systemscited by 88
  19. 2020UNION: An Unreferenced Metric for Evaluating Open-ended Story Generationcited by 60
  20. 2020Consistency of a Recurrent Language Model With Respect to Incomplete Decodingcited by 54
  21. 2019How Decoding Strategies Affect the Verifiability of Generated Textcited by 27
  22. 2020Towards a Decomposable Metric for Explainable Evaluation of Text Generation from AMRcited by 25
  23. 2020Sparse Text Generationcited by 24
  24. 2018On Accurate Evaluation of GANs for Language Generationcited by 20
  25. 2020Deep Residual Mixture Modelscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 52; 2023: 92; 2024: 106; 2025: 95; 2026: 120.

466 papers.

Sort:

By area:

  1. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  3. 2024Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Headscited by 821
  4. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distributioncited by 712
  5. 2022Contrastive Decoding: Open-ended Text Generation as Optimizationcited by 598
  6. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
  7. 2023PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimizationcited by 311
  8. 2022Quark: Controllable Text Generation with Reinforced Unlearningcited by 236
  9. 2022A Contrastive Framework for Neural Text Generationcited by 224
  10. 2022ZeroGen: Efficient Zero-shot Learning via Dataset Generationcited by 209
  11. 2022Continuous diffusion for categorical datacited by 202
  12. 2022Factuality Enhanced Language Models for Open-Ended Text Generationcited by 200
38 more
  1. 2022SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Controlcited by 191
  2. 2023Does Writing with Language Models Reduce Content Diversity?cited by 190
  3. 2025Remasking Discrete Diffusion Models with Inference-Time Scalingcited by 181
  4. 2023On the Reliability of Watermarks for Large Language Modelscited by 170
  5. 2022Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Textcited by 154
  6. 2023A Reparameterized Discrete Diffusion Model for Text Generationcited by 152
  7. 2023The Science of Detecting LLM-Generated Textscited by 126
  8. 2022Truncation Sampling as Language Model Desmoothingcited by 121
  9. 2024A Thorough Examination of Decoding Methods in the Era of LLMscited by 112
  10. 2023A Critical Evaluation of Evaluations for Long-form Question Answeringcited by 111
  11. 2022Latent Diffusion for Language Generationcited by 110
  12. 2023On the Exploitability of Instruction Tuningcited by 110
  13. 2022Locally Typical Samplingcited by 108
  14. 2022Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipecited by 108
  15. 2022Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generationcited by 90
  16. 2022Language Models Can See: Plugging Visual Controls in Text Generationcited by 89
  17. 2023KoLA: Carefully Benchmarking World Knowledge of Large Language Modelscited by 85
  18. 2022Training Trajectories of Language Models Across Scalescited by 80
  19. 2022The AI Teacher Test: Measuring the Pedagogical Ability of Blender and GPT-3 in Educational Dialoguescited by 78
  20. 2024Differentially Private Synthetic Data via Foundation Model APIs 2: Textcited by 74
  21. 2023Evaluating Large Language Models on Controlled Generation Taskscited by 73
  22. 2024Beyond Autoregression: Fast LLMs via Self-Distillation Through Timecited by 73
  23. 2022RankGen: Improving Text Generation with Large Ranking Modelscited by 72
  24. 2023On the Learnability of Watermarks for Language Modelscited by 72
  25. 2024Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluationcited by 72
  26. 2022Differentially Private Language Models for Secure Data Sharingcited by 68
  27. 2022ProGen: Progressive Zero-shot Dataset Generation via In-context Feedbackcited by 67
  28. 2024SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMscited by 67
  29. 2023Harnessing large-language models to generate private synthetic textcited by 65
  30. 2023TESS: Text-to-Text Self-Conditioned Simplex Diffusioncited by 63
  31. 2023Contrasting Linguistic Patterns in Human and LLM-Generated News Textcited by 62
  32. 2023Mark My Words: Analyzing and Evaluating Language Model Watermarkscited by 62
  33. 2023Uncertainty in Natural Language Generation: From Theory to Applicationscited by 61
  34. 2022Data Feedback Loops: Model-driven Amplification of Dataset Biasescited by 59
  35. 2022Contrastive Search Is What You Need For Neural Text Generationcited by 58
  36. 2024Discrete Copula Diffusioncited by 53
  37. 2023What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variabilitycited by 51
  38. 2024Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMscited by 50

50 most cited of 466 All 466 (JSON)