mlsanityData to 7 Oct 2026

Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal View

arXiv 2203.12258 ↗First posted 23 Mar 2022cs.CLcited by 31

Not on the map. Why?

Abstract (arXiv)

Prompt-based probing has been widely used in evaluating the abilities of pretrained language models (PLMs). Unfortunately, recent studies have discovered such an evaluation may be inaccurate, inconsistent and unreliable. Furthermore, the lack of understanding its inner workings, combined with its wide applicability, has the potential to lead to unforeseen risks for evaluating and applying PLMs in real-world applications. To discover, understand and quantify the risks, this paper investigates the prompt-based probing from a causal view, highlights three critical biases which could induce biased results and conclusions, and proposes to conduct debiasing via causal intervention. This paper provides valuable insights for the design of unbiased datasets, better probing frameworks and more reliable evaluations of pretrained language models. Furthermore, our conclusions also echo that we need to rethink the criteria for identifying better pretrained language models. We openly released the source code and data at https://github.com/c-box/causalEval.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Builds on 41 of its 56 references that are in the map. First posted on arXiv 23 Mar 2022.

Builds on

41 of 56 references.

References · 41

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  6. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  7. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  8. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  9. 2019Language Models as Knowledge Bases?cited by 1,922
  10. 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,718
  11. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  12. 2019How Can We Know What Language Models Know?cited by 953
29 more
  1. 2019Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inferencecited by 864
  2. 2020A Primer in BERTology: What we know about how BERT workscited by 807
  3. 2017Counterfactual Fairnesscited by 802
  4. 2021GPT Understands, Toocited by 715
  5. 2018Gender Bias in Coreference Resolutioncited by 438
  6. 2021Learning How to Ask: Querying LMs with Mixtures of Soft Promptscited by 376
  7. 2021Measuring and Improving Consistency in Pretrained Language Modelscited by 361
  8. 2019What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language modelscited by 317
  9. 2021Factual Probing Is [MASK]: Learning vs. Learning to Recallcited by 291
  10. 2021ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generationcited by 258
  11. 2020AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Promptscited by 246
  12. 2017Avoiding Discrimination through Causal Reasoningcited by 191
  13. 2019Commonsense Knowledge Mining from Pretrained Modelscited by 189
  14. 2021Visually Grounded Reasoning across Languages and Culturescited by 188
  15. 2021Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyondcited by 177
  16. 2020A Survey of Evaluation Metrics Used for NLG Systemscited by 164
  17. 2019oLMpics -- On what Language Model Pre-training Capturescited by 161
  18. 2020X-FACTR: Multilingual Factual Knowledge Retrieval from Pretrained Language Modelscited by 117
  19. 2021Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Basescited by 107
  20. 2017Adversarial Learning for Neural Dialogue Generationcited by 103
  21. 2019E-BERT: Efficient-Yet-Effective Entity Embeddings for BERTcited by 96
  22. 2019Evaluating Commonsense in Pre-trained Language Modelscited by 95
  23. 2021Can Language Models be Biomedical Knowledge Bases?cited by 83
  24. 2018Event2Mind: Commonsense Inference on Events, Intents, and Reactionscited by 82
  25. 2021BERTese: Learning to Speak to BERTcited by 82
  26. 2017Neural Natural Language Inference Models Enhanced with External Knowledgecited by 40
  27. 2017The Effect of Different Writing Tasks on Linguistic Style: A Case Study of the ROC Story Cloze Taskcited by 39
  28. 2019Re-evaluating ADEM: A Deeper Look at Scoring Dialogue Responsescited by 22
  29. 2018Visual Referring Expression Recognition: What Do Systems Actually Learn?cited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 13; 2024: 9; 2025: 4; 2026: 1.

31 papers.

Sort:

By area:

  1. 2023Evaluating Large Language Models in Theory of Mind Taskscited by 217
  2. 2023Language Model Behavior: A Comprehensive Surveycited by 92
  3. 2023Give Us the Facts: Enhancing Large Language Models with Knowledge Graphs for Fact-aware Language Modelingcited by 56
  4. 2023The language of prompting: What linguistic properties make a prompt successful?cited by 43
  5. 2023Give Me the Facts! A Survey on Factual Knowledge Probing in Pre-trained Language Modelscited by 32
  6. 2022Neuro-Symbolic Procedural Planning with Commonsense Promptingcited by 28
  7. 2024Large Language Models and Causal Inference in Collaboration: A Surveycited by 26
  8. 2023The Life Cycle of Knowledge in Big Language Models: A Surveycited by 23
  9. 2023Retentive or Forgetful? Diving into the Knowledge Memorizing Mechanism of Language Modelscited by 18
  10. 2024A Causal Explainable Guardrails for Large Language Modelscited by 18
  11. 2022Context Variance Evaluation of Pretrained Language Models for Prompt-based Biomedical Knowledge Probingcited by 15
  12. 2023A Review of the Role of Causality in Developing Trustworthy AI Systemscited by 14
19 more
  1. 2024StructEval: Deepen and Broaden Large Language Model Assessment via Structured Evaluationcited by 9
  2. 2023Causality-aware Concept Extraction based on Knowledge-guided Promptingcited by 8
  3. 2022Towards Robust NLG Bias Evaluation with Syntactically-diverse Promptscited by 7
  4. 2025Preference Learning for AI Alignment: a Causal Perspectivecited by 6
  5. 2024Comparing Template-based and Template-free Language Model Probingcited by 5
  6. 2023MixPro: Simple yet Effective Data Augmentation for Prompt-based Learningcited by 4
  7. 2024Why Don't Prompt-Based Fairness Metrics Correlate?cited by 4
  8. 2025On Entity Identification in Language Modelscited by 3
  9. 2023Test-time Augmentation for Factual Probingcited by 2
  10. 2024UniArk: Improving Generalisation and Consistency for Factual Knowledge Extraction through Debiasingcited by 2
  11. 2024CRAT: A Multi-Agent Framework for Causality-Enhanced Reflective and Retrieval-Augmented Translation with Large Language Modelscited by 2
  12. 2025Causal MAS: A Survey of Large Language Model Architectures for Discovery and Effect Estimationcited by 2
  13. 2024A Unified Causal View of Instruction Tuningcited by 1
  14. 2024A Comprehensive Evaluation of Semantic Relation Knowledge of Pretrained Language Models and Humanscited by 1
  15. 2025Three tiers of computation in transformers and in brain architecturescited by 1
  16. 2022Causal Intervention-based Prompt Debiasing for Event Argument Extractioncited by 0
  17. 2023Psychologically-Inspired Causal Promptscited by 0
  18. 2023Inducing Causal Structure for Abstractive Text Summarizationcited by 0
  19. 2026When Words Speak Louder than Images: Towards Understanding Language Bias in Vision-Language Modelscited by 0