mlsanityData to 7 Oct 2026

Beyond Accuracy: Behavioral Testing of NLP models with CheckList

arXiv 2005.04118 ↗First posted 8 May 2020cs.CL cs.LGcited by 979

Not on the map. Why?

Cited by 48 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Although measuring held-out accuracy has been the primary approach to evaluate generalization, it often overestimates the performance of NLP models, while alternative approaches for evaluating models either focus on individual tasks or on specific behaviors. Inspired by principles of behavioral testing in software engineering, we introduce CheckList, a task-agnostic methodology for testing NLP models. CheckList includes a matrix of general linguistic capabilities and test types that facilitate comprehensive test ideation, as well as a software tool to generate a large and diverse number of test cases quickly. We illustrate the utility of CheckList with tests for three tasks, identifying critical failures in both commercial and state-of-art models. In a user study, a team responsible for a commercial sentiment analysis model found new and actionable bugs in an extensively tested model. In another user study, NLP practitioners with CheckList created twice as many tests, and found almost three times as many bugs as users without it.

Key facts. Cited by 979 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 151; 2022: 179; 2023: 159; 2024: 113; 2025: 114; 2026: 263.

979 papers.

Sort:

By area:

  1. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,326
  2. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,270
  3. 2023A Survey on Evaluation of Large Language Modelscited by 1,227
  4. 2022Red Teaming Language Models with Language Modelscited by 983
  5. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
  6. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 702
  7. 2023Tree of Attacks: Jailbreaking Black-Box LLMs Automaticallycited by 619
  8. 2023XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Modelscited by 477
  9. 2023"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Modelscited by 457
  10. 2021Dynabench: Rethinking Benchmarking in NLPcited by 447
  11. 2021Measuring and Improving Consistency in Pretrained Language Modelscited by 361
  12. 2021AI and the Everything in the Whole Wide World Benchmarkcited by 340
38 more
  1. 2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 337
  2. 2022Prompting GPT-3 To Be Reliablecited by 258
  3. 2021The GEM Benchmark: Natural Language Generation, its Evaluation and Metricscited by 239
  4. 2021Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Modelscited by 227
  5. 2021Get Your Vitamin C! Robust Fact Verification with Contrastive Evidencecited by 222
  6. 2021Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Modelscited by 219
  7. 2023PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Promptscited by 218
  8. 2021Trustworthy AI: From Principles to Practicescited by 206
  9. 2021What Will it Take to Fix Benchmarking in Natural Language Understanding?cited by 200
  10. 2022WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creationcited by 200
  11. 2023"Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letterscited by 196
  12. 2022Patching open-vocabulary models by interpolating weightscited by 187
  13. 2023Automatically Auditing Large Language Models via Discrete Optimizationcited by 187
  14. 2021Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyondcited by 177
  15. 2021XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluationcited by 167
  16. 2022Dawn of the transformer era in speech emotion recognition: closing the valence gapcited by 155
  17. 2022Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Textcited by 154
  18. 2021SituatedQA: Incorporating Extra-Linguistic Contexts into QAcited by 145
  19. 2023Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Modelscited by 144
  20. 2021CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLPcited by 142
  21. 2022Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidencecited by 142
  22. 2023Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarkscited by 139
  23. 2021VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomenacited by 134
  24. 2022Truncation Sampling as Language Model Desmoothingcited by 121
  25. 2023Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventionscited by 121
  26. 2021Salient ImageNet: How to discover spurious features in Deep Learning?cited by 114
  27. 2022VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relationscited by 113
  28. 2021Robustness Gym: Unifying the NLP Evaluation Landscapecited by 107
  29. 2021Measure and Improve Robustness in NLP Models: A Surveycited by 107
  30. 2024Cognitive Bias in Decision-Making with LLMscited by 104
  31. 2022XAI for Transformers: Better Explanations through Conservative Propagationcited by 100
  32. 2023DyVal: Dynamic Evaluation of Large Language Models for Reasoning Taskscited by 100
  33. 2022Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLPcited by 99
  34. 2022State-of-the-art generalisation research in NLP: A taxonomy and reviewcited by 97
  35. 2021QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehensioncited by 91
  36. 2021Evaluating the Robustness of Neural Language Models to Input Perturbationscited by 87
  37. 2024CheckEval: A reliable LLM-as-a-Judge framework for evaluating text generation using checklistscited by 87
  38. 2021Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalizationcited by 83

50 most cited of 979 All 979 (JSON)