mlsanityData to 14 Oct 2026

Meaning without reference in large language models

arXiv 2208.02957 ↗First posted 5 Aug 2022cs.CL cs.AIcited by 76

Not on the map. Why?

Abstract (arXiv)

The widespread success of large language models (LLMs) has been met with skepticism that they possess anything like human concepts or meanings. Contrary to claims that LLMs possess no meaning whatsoever, we argue that they likely capture important aspects of meaning, and moreover work in a way that approximates a compelling account of human cognition in which meaning arises from conceptual role. Because conceptual role is defined by the relationships between internal representational states, meaning cannot be determined from a model's architecture, training data, or objective function, but only by examination of how its internal states relate to each other. This approach may clarify why and how LLMs are so successful and suggest how they can be made more human-like.

Key facts. Cited by 76 papers in the map (data through 14 Oct 2026). Builds on 19 of its 66 references that are in the map. First posted on arXiv 5 Aug 2022.

Builds on

19 of 66 references.

References · 19

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2018Deep contextualized word representationscited by 2,290
  4. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  5. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,392
  6. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 445
  7. 2017Unsupervised Machine Translation Using Monolingual Corpora Onlycited by 273
  8. 2020Experience Grounds Languagecited by 242
  9. 2021Implicit Representations of Meaning in Neural Language Modelscited by 180
  10. 2022Language models show human-like content effects on reasoning taskscited by 173
  11. 2021Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Colorcited by 119
  12. 2016Learning Distributed Representations of Sentences from Unlabelled Datacited by 91
7 more
  1. 2021Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefscited by 79
  2. 2020MEGATRON-CNTRL: Controllable Story Generation with External Knowledge Using Large-Scale Language Modelscited by 74
  3. 2021Shaking the foundations: delusions in sequence models for interaction and controlcited by 62
  4. 2020Word meaning in minds and machinescited by 51
  5. 2020A Review of Winograd Schema Challenge Datasets and Approachescited by 27
  6. 2016HyperLex: A Large-Scale Evaluation of Graded Lexical Entailmentcited by 26
  7. 2021Symbolic Behaviour in Artificial Intelligencecited by 25

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 9; 2023: 22; 2024: 16; 2025: 19; 2026: 10.

76 papers.

Sort:

By area:

  1. 2022Towards Reasoning in Large Language Models: A Surveycited by 596
  2. 2023Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Taskscited by 246
  3. 2023Evaluating the Moral Beliefs Encoded in LLMscited by 215
  4. 2023Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solvecited by 178
  5. 2022Talking About Large Language Modelscited by 175
  6. 2022The Debate Over Understanding in AI's Large Language Modelscited by 142
  7. 2023Harms from Increasingly Agentic Algorithmic Systemscited by 135
  8. 2022Language Models as Agent Modelscited by 132
  9. 2022Does CLIP Bind Concepts? Probing Compositionality in Large Image Modelscited by 102
  10. 2023Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblockscited by 78
  11. 2023Learning to Model the World with Languagecited by 68
  12. 2024LLMs achieve adult human performance on higher-order theory of mind taskscited by 61
38 more
  1. 2024Evaluating Gender Bias in Large Language Models via Chain-of-Thought Promptingcited by 50
  2. 2024Large Language Models and Cognitive Science: A Comprehensive Review of Similarities, Differences, and Challengescited by 49
  3. 2023From task structures to world models: What do LLMs know?cited by 46
  4. 2023Testing AI on language comprehension tasks reveals insensitivity to underlying meaningcited by 45
  5. 2023The Vector Grounding Problemcited by 39
  6. 2024Benchmarks as Microscopes: A Call for Model Metrologycited by 35
  7. 2022DALL-E 2 Fails to Reliably Capture Common Syntactic Processescited by 31
  8. 2024Standards for Belief Representations in LLMscited by 30
  9. 2023Dissociating language and thought in large language modelscited by 29
  10. 2023Do Vision and Language Models Share Concepts? A Vector Space Alignment Studycited by 27
  11. 2024At the Dawn of Generative AI Era: A Tutorial-cum-Survey on New Frontiers in 6G Wireless Intelligencecited by 25
  12. 2024Language Models as Models of Languagecited by 24
  13. 2024A Philosophical Introduction to Language Models -- Part I: Continuity With Classic Debatescited by 23
  14. 2022Unpacking Large Language Models with Conceptual Consistencycited by 18
  15. 2023MEWL: Few-shot multimodal word learning with referential uncertaintycited by 17
  16. 2023Challenges of Large Language Models for Mental Health Counselingcited by 17
  17. 2024Large Language Model Benchmarks in Medical Taskscited by 17
  18. 2022COMPS: Conceptual Minimal Pair Sentences for testing Robust Property Knowledge and its Inheritance in Pre-trained Language Modelscited by 15
  19. 2024Language in Vivo vs. in Silico: Size Matters but Larger Language Models Still Do Not Comprehend Language on a Par with Humans Due to Impenetrable Semantic Referencecited by 15
  20. 2023Operationalising Representation in Natural Language Processingcited by 14
  21. 2025Calibrating Verbalized Confidence with Self-Generated Distractorscited by 14
  22. 2023Being Right for Whose Right Reasons?cited by 12
  23. 2024Are Language Models More Like Libraries or Like Librarians? Bibliotechnism, the Novel Reference Problem, and the Attitudes of LLMscited by 11
  24. 2025How Causal Abstraction Underpins Computational Explanationcited by 11
  25. 2025Mechanistic Indicators of Understanding in Large Language Modelscited by 8
  26. 2023Causal interventions expose implicit situation models for commonsense language understandingcited by 7
  27. 2024Does Thought Require Sensory Grounding? From Pure Thinkers to Large Language Modelscited by 7
  28. 2024Understanding Epistemic Language with a Language-augmented Bayesian Theory of Mindcited by 6
  29. 2025What Do Large Language Models Know? Tacit Knowledge as a Potential Causal-Explanatory Structurecited by 6
  30. 2022Do ever larger octopi still amplify reporting biases? Evidence from judgments of typical colourcited by 5
  31. 2023Does Conceptual Representation Require Embodiment? Insights From Large Language Modelscited by 5
  32. 2023Meaning and understanding in large language modelscited by 5
  33. 2025A quantum semantic framework for natural language processingcited by 5
  34. 2025In-Context Algebracited by 5
  35. 2023Understanding Natural Language Understanding Systems. A Critical Analysiscited by 4
  36. 2025Language models align with brain regions that represent concepts across modalitiescited by 4
  37. 2023Artificial intelligence is algorithmic mimicry: why artificial "agents" are not (and won't be) proper agentscited by 3
  38. 2025A Categorical Analysis of Large Language Models and Why LLMs Circumvent the Symbol Grounding Problemcited by 3

50 most cited of 76 All 76 (JSON)