mlsanityData to 14 Oct 2026

Do Large Language Models Know How Much They Know?

arXiv 2502.19573 ↗First posted 26 Feb 2025cs.CL cs.AI cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) have emerged as highly capable systems and are increasingly being integrated into various uses. However, the rapid pace of their deployment has outpaced a comprehensive understanding of their internal mechanisms and a delineation of their capabilities and limitations. A desired attribute of an intelligent system is its ability to recognize the scope of its own knowledge. To investigate whether LLMs embody this characteristic, we develop a benchmark designed to challenge these models to enumerate all information they possess on specific topics. This benchmark evaluates whether the models recall excessive, insufficient, or the precise amount of information, thereby indicating their awareness of their own knowledge. Our findings reveal that all tested LLMs, given sufficient scale, demonstrate an understanding of how much they know about specific topics. While different architectures exhibit varying rates of this capability's emergence, the results suggest that awareness of knowledge may be a generalizable attribute of LLMs. Further research is needed to confirm this potential and fully elucidate the underlying mechanisms.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 39 of its 56 references that are in the map. First posted on arXiv 26 Feb 2025.

Builds on

39 of 56 references.

References · 39

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  6. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  7. 2016Layer Normalizationcited by 5,669
  8. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  9. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  10. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  11. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  12. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,411
27 more
  1. 2019Language Models as Knowledge Bases?cited by 1,936
  2. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  3. 2023Pythia: A Suite for Analyzing Large Language Models Across Training and Scalingcited by 1,786
  4. 2016Understanding intermediate layers using linear classifier probescited by 1,353
  5. 2019How Can We Know What Language Models Know?cited by 959
  6. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 719
  7. 2023Dissecting Recall of Factual Associations in Auto-Regressive Language Modelscited by 528
  8. 2022Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskcited by 431
  9. 2023The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"cited by 407
  10. 2020Calibration of Pre-trained Transformerscited by 315
  11. 2023Physics of Language Models: Part 3.1, Knowledge Storage and Extractioncited by 270
  12. 2015A Neural Conversational Modelcited by 196
  13. 2022A Review on Language Models as Knowledge Basescited by 157
  14. 2023Taken out of context: On measuring situational awareness in LLMscited by 143
  15. 2023Physics of Language Models: Part 3.2, Knowledge Manipulationcited by 143
  16. 2020Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queriescited by 107
  17. 2019Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Surveycited by 93
  18. 2023Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanationscited by 85
  19. 2023How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questionscited by 83
  20. 2023Knowledge of Knowledge: Exploring Known-Unknowns Uncertainty with Large Language Modelscited by 61
  21. 2023Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Methodcited by 51
  22. 2021BERTnesia: Investigating the capture and forgetting of knowledge in BERTcited by 40
  23. 2020Unwrapping The Black Box of Deep ReLU Networks: Interpretability, Diagnostics, and Simplificationcited by 32
  24. 2023An Evaluation on Large Language Model Outputs: Discourse and Memorizationcited by 20
  25. 2024Can Language Models Act as Knowledge Bases at Scale?cited by 17
  26. 2021Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense Knowledgecited by 8
  27. 2023EpiK-Eval: Evaluation for Language Models as Epistemic Modelscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 6.

11 papers.

  1. 2025Mamba Modulation: On the Length Generalization of Mambacited by 16
  2. 2026Instinct vs. Reflection: Unifying Token and Verbalized Confidence in Multimodal Large Modelscited by 4
  3. 2025Agents Require Metacognitive and Strategic Reasoning to Succeed in the Coming Labor Marketscited by 2
  4. 2025Evaluating the Unseen Capabilities: How Many Theorems Do LLMs Know?cited by 2
  5. 2025Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinationscited by 2
  6. 2026Fine-Tuning Language Models to Know What They Knowcited by 2
  7. 2025Trusted Uncertainty in Large Language Models: A Unified Framework for Confidence Calibration and Risk-Controlled Refusalcited by 1
  8. 2026Pretraining Exposure Explains Popularity Judgments in Large Language Modelscited by 1
  9. 2026Metacognition in LLMs: Foundations, Progress, and Opportunitiescited by 1
  10. 2026UniComp: A Unified Evaluation of Large Language Model Compression via Pruning, Quantization, and Distillationcited by 0
  11. 2026Distilling What Matters: Confidence-Aware Selective Distillation for Large Language Modelscited by 0