mlsanityData to 7 Oct 2026

How Reliable are Model Diagnostics?

arXiv 2105.05641 ↗First posted 12 May 2021cs.CL cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

In the pursuit of a deeper understanding of a model's behaviour, there is recent impetus for developing suites of probes aimed at diagnosing models beyond simple metrics like accuracy or BLEU. This paper takes a step back and asks an important and timely question: how reliable are these diagnostics in providing insight into models and training setups? We critically examine three recent diagnostic tests for pre-trained language models, and find that likelihood-based and representation-based model diagnostics are not yet as reliable as previously assumed. Based on our empirical findings, we also formulate recommendations for practitioners and researchers.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 29 of its 39 references that are in the map. First posted on arXiv 12 May 2021.

Builds on

29 of 39 references.

References · 29

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  4. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  5. 2019Language Models as Knowledge Bases?cited by 1,922
  6. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 979
  7. 2019How Can We Know What Language Models Know?cited by 953
  8. 2019Attention is not Explanationcited by 916
  9. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
  10. 2016Semantics derived automatically from language corpora contain human-like biasescited by 894
  11. 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 703
  12. 2019How multilingual is Multilingual BERT?cited by 642
17 more
  1. 2019Designing and Interpreting Probes with Control Taskscited by 608
  2. 2020Underspecification Presents Challenges for Credibility in Modern Machine Learningcited by 488
  3. 2018What you can cram into a single vector: Probing sentence embeddings for linguistic propertiescited by 452
  4. 2018Gender Bias in Coreference Resolutioncited by 438
  5. 2019What do you learn from context? Probing for sentence structure in contextualized word representationscited by 436
  6. 2019On Measuring Social Biases in Sentence Encoderscited by 397
  7. 2020Calibration of Pre-trained Transformerscited by 307
  8. 2018Analysis Methods in Neural Language Processing: A Surveycited by 276
  9. 2018Targeted Syntactic Evaluation of Language Modelscited by 239
  10. 2020Information-Theoretic Probing with Minimum Description Lengthcited by 230
  11. 2020Measuring and Reducing Gendered Correlations in Pre-trained Modelscited by 222
  12. 2016Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Taskscited by 216
  13. 2017What do Neural Machine Translation Models Learn about Morphology?cited by 165
  14. 2019Learning to Deceive with Attention-Based Explanationscited by 111
  15. 2019BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performancecited by 89
  16. 2019Investigating Multilingual NMT Representations at Scalecited by 68
  17. 2020Gradient-based Analysis of NLP Models is Manipulablecited by 41

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 5; 2023: 2; 2024: 3; 2025: 0; 2026: 1.

13 papers.

Sort:

By area:

  1. 2021An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Modelscited by 96
  2. 2021The MultiBERTs: BERT Reproductions for Robustness Analysiscited by 89
  3. 2022MABEL: Attenuating Gender Bias using Textual Entailment Datacited by 31
  4. 2023An Empirical Analysis of Parameter-Efficient Methods for Debiasing Pre-Trained Language Modelscited by 16
  5. 2024From 'Showgirls' to 'Performers': Fine-tuning with Gender-inclusive Language for Bias Reduction in LLMscited by 15
  6. 2023Women Are Beautiful, Men Are Leaders: Gender Stereotypes in Machine Translation and Language Modelingcited by 12
  7. 2022Trustworthy Social Bias Measurementcited by 7
  8. 2022On the data requirements of probingcited by 4
  9. 2022Undesirable Biases in NLP: Addressing Challenges of Measurementcited by 4
  10. 2024MAGPIE: Multi-Task Media-Bias Analysis Generalization for Pre-Trained Identification of Expressionscited by 4
  11. 2024RuBia: A Russian Language Bias Detection Datasetcited by 4
  12. 2022Evaluation for Changecited by 0
1 more
  1. 2026Are Near-Tied LLM Rankings Robust to Family-DIF-Guided Benchmark Recomposition?cited by 0