# Word meaning in minds and machines

arXiv: https://arxiv.org/abs/2008.01766 · HTML: https://mlsanity.com/paper/2008.01766/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Aug 2020.

## Built on by (most cited first, 30 of 51)

- [Talking About Large Language Models](https://mlsanity.com/paper/2212.03551/) (2022)
- [The Debate Over Understanding in AI's Large Language Models](https://mlsanity.com/paper/2210.13966/) (2022)
- [Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning](https://mlsanity.com/paper/2107.02794/) (2021)
- [Meaning without reference in large language models](https://mlsanity.com/paper/2208.02957/) (2022)
- [Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning](https://mlsanity.com/paper/2112.03763/) (2021)
- [Probing the Creativity of Large Language Models: Can models produce divergent semantic association?](https://mlsanity.com/paper/2310.11158/) (2023)
- [Strong and weak alignment of large language models with human values](https://mlsanity.com/paper/2408.04655/) (2024)
- [The Defeat of the Winograd Schema Challenge](https://mlsanity.com/paper/2201.02387/) (2022)
- [Relational Memory Augmented Language Models](https://mlsanity.com/paper/2201.09680/) (2022)
- [Inductive reasoning in humans and large language models](https://mlsanity.com/paper/2306.06548/) (2023)
- [Frequency-based Distortions in Contextualized Word Embeddings](https://mlsanity.com/paper/2104.08465/) (2021)
- [MEWL: Few-shot multimodal word learning with referential uncertainty](https://mlsanity.com/paper/2306.00503/) (2023)
- [COMPS: Conceptual Minimal Pair Sentences for testing Robust Property Knowledge and its Inheritance in Pre-trained Language Models](https://mlsanity.com/paper/2210.01963/) (2022)
- [Are Language Models More Like Libraries or Like Librarians? Bibliotechnism, the Novel Reference Problem, and the Attitudes of LLMs](https://mlsanity.com/paper/2401.04854/) (2024)
- [Characterizing the Role of Similarity in the Property Inferences of Language Models](https://mlsanity.com/paper/2410.22590/) (2024)
- [Long-range and hierarchical language predictions in brains and algorithms](https://mlsanity.com/paper/2111.14232/) (2021)
- [Predicting Human Similarity Judgments Using Large Language Models](https://mlsanity.com/paper/2202.04728/) (2022)
- [Human Behavioral Benchmarking: Numeric Magnitude Comparison Effects in Large Language Models](https://mlsanity.com/paper/2305.10782/) (2023)
- [AI for Mathematics: A Cognitive Science Perspective](https://mlsanity.com/paper/2310.13021/) (2023)
- [Exploring the Representation of Word Meanings in Context: A Case Study on Homonymy and Synonymy](https://mlsanity.com/paper/2106.13553/) (2021)
- [Deanthropomorphising NLP: Can a Language Model Be Conscious?](https://mlsanity.com/paper/2211.11483/) (2022)
- [Does Thought Require Sensory Grounding? From Pure Thinkers to Large Language Models](https://mlsanity.com/paper/2408.09605/) (2024)
- [One-Shot Learning from a Demonstration with Hierarchical Latent Language](https://mlsanity.com/paper/2203.04806/) (2022)
- [Understanding Epistemic Language with a Language-augmented Bayesian Theory of Mind](https://mlsanity.com/paper/2408.12022/) (2024)
- [Revealing emergent human-like conceptual representations from language prediction](https://mlsanity.com/paper/2501.12547/) (2025)
- [Language with Vision: a Study on Grounded Word and Sentence Embeddings](https://mlsanity.com/paper/2206.08823/) (2022)
- [Does Conceptual Representation Require Embodiment? Insights From Large Language Models](https://mlsanity.com/paper/2305.19103/) (2023)
- [Learning to Summarize and Answer Questions about a Virtual Robot's Past Actions](https://mlsanity.com/paper/2306.09922/) (2023)
- [Meaning and understanding in large language models](https://mlsanity.com/paper/2310.17407/) (2023)
- [Understanding Natural Language Understanding Systems. A Critical Analysis](https://mlsanity.com/paper/2303.04229/) (2023)

## Abstract (arXiv)

Machines have achieved a broad and growing set of linguistic competencies, thanks to recent progress in Natural Language Processing (NLP). Psychologists have shown increasing interest in such models, comparing their output to psychological judgments such as similarity, association, priming, and comprehension, raising the question of whether the models could serve as psychological theories. In this article, we compare how humans and machines represent the meaning of words. We argue that contemporary NLP systems are fairly successful models of human word similarity, but they fall short in many other respects. Current models are too strongly linked to the text-based patterns in large corpora, and too weakly linked to the desires, goals, and beliefs that people express through words. Word meanings must also be grounded in perception and action and be capable of flexible combinations in ways that current systems are not. We discuss more promising approaches to grounding NLP systems and argue that they will be more successful with a more human-like, conceptual basis for word meaning.