mlsanityData to 14 Oct 2026

How Can We Know What Language Models Know?

arXiv 1911.12543 ↗First posted 28 Nov 2019cs.CL cs.LGcited by 959

Not on the map. Why?

Cited by 77 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recent work has presented intriguing results examining the knowledge contained in language models (LM) by having the LM fill in the blanks of prompts such as "Obama is a _ by profession". These prompts are usually manually created, and quite possibly sub-optimal; another prompt such as "Obama worked as a _" may result in more accurately predicting the correct profession. Because of this, given an inappropriate prompt, we might fail to retrieve facts that the LM does know, and thus any given prompt only provides a lower bound estimate of the knowledge contained in an LM. In this paper, we attempt to more accurately estimate the knowledge contained in LMs by automatically discovering better prompts to use in this querying process. Specifically, we propose mining-based and paraphrasing-based methods to automatically generate high-quality and diverse prompts, as well as ensemble methods to combine answers from different prompts. Extensive experiments on the LAMA benchmark for extracting relational knowledge from LMs demonstrate that our methods can improve accuracy from 31.1% to 39.6%, providing a tighter lower bound on what LMs know. We have released the code and the resulting LM Prompt And Query Archive (LPAQA) at https://github.com/jzbjyb/LPAQA.

Key facts. Cited by 959 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 120; 2022: 197; 2023: 286; 2024: 191; 2025: 101; 2026: 64.

959 papers.

Sort:

By area:

  1. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  2. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  3. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  4. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  5. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  6. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
  7. 2022Visual Prompt Tuningcited by 1,681
  8. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,433
  9. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  10. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  11. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,135
  12. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,081
38 more
  1. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
  2. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,035
  3. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,026
  4. 2022Mass-Editing Memory in a Transformercited by 1,001
  5. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  6. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 938
  7. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 817
  8. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  9. 2023Whose Opinions Do Language Models Reflect?cited by 773
  10. 2021BARTScore: Evaluating Generated Text as Text Generationcited by 722
  11. 2021GPT Understands, Toocited by 716
  12. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  13. 2021Knowledge Neurons in Pretrained Transformerscited by 601
  14. 2021Editing Factual Knowledge in Language Modelscited by 553
  15. 2022Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Spacecited by 532
  16. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 532
  17. 2023Dissecting Recall of Factual Associations in Auto-Regressive Language Modelscited by 528
  18. 2023Active Retrieval Augmented Generationcited by 516
  19. 2021Fast Model Editing at Scalecited by 498
  20. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 463
  21. 2023Augmented Language Models: a Surveycited by 403
  22. 2022Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)cited by 402
  23. 2021Learning How to Ask: Querying LMs with Mixtures of Soft Promptscited by 377
  24. 2022RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learningcited by 366
  25. 2021Measuring and Improving Consistency in Pretrained Language Modelscited by 364
  26. 2021True Few-Shot Learning with Language Modelscited by 344
  27. 2023Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflictscited by 341
  28. 2021Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLPcited by 337
  29. 2021Do Prompt-Based Models Really Understand the Meaning of their Prompts?cited by 326
  30. 2021Pre-Trained Models: Past, Present and Futurecited by 319
  31. 2022Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classificationcited by 312
  32. 2021Prompting Visual-Language Models for Efficient Video Understandingcited by 310
  33. 2023MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questionscited by 300
  34. 2021Time-Aware Language Models as Temporal Knowledge Basescited by 296
  35. 2023Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspectivecited by 294
  36. 2021Factual Probing Is [MASK]: Learning vs. Learning to Recallcited by 291
  37. 2022What does a platypus look like? Generating customized prompts for zero-shot image classificationcited by 267
  38. 2021Surface Form Competition: Why the Highest Probability Answer Isn't Always Rightcited by 263

50 most cited of 959 All 959 (JSON)