# Unveiling Theory of Mind in Large Language Models: A Parallel to Single Neurons in the Human Brain

arXiv: https://arxiv.org/abs/2309.01660 · HTML: https://mlsanity.com/paper/2309.01660/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 30 references that are in the map.
- First posted on arXiv 4 Sep 2023.

## Builds on (most cited first, 9 of 9)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only](https://mlsanity.com/paper/2306.01116/) (2023)
- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (2023)
- [Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks](https://mlsanity.com/paper/2302.08399/) (2023)
- [How well do Large Language Models perform in Arithmetic tasks?](https://mlsanity.com/paper/2304.02015/) (2023)
- [Solving Math Word Problems by Combining Language Models With Symbolic Solvers](https://mlsanity.com/paper/2304.09102/) (2023)
- [Do Large Language Models know what humans know?](https://mlsanity.com/paper/2209.01515/) (2022)
- [Can I say, now machines can think?](https://mlsanity.com/paper/2307.07526/) (2023)

## Built on by (most cited first, 18 of 18)

- [Secret Collusion among AI Agents: Multi-Agent Deception via Steganography](https://mlsanity.com/paper/2402.07510/) (2024)
- [A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners](https://mlsanity.com/paper/2406.11050/) (2024)
- [Can Language Models Learn to Skip Steps?](https://mlsanity.com/paper/2411.01855/) (2024)
- [Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents](https://mlsanity.com/paper/2405.16533/) (2024)
- [Re-evaluating Theory of Mind evaluation in large language models](https://mlsanity.com/paper/2502.21098/) (2025)
- [Editing Conceptual Knowledge for Large Language Models](https://mlsanity.com/paper/2403.06259/) (2024)
- [Weakly Supervised Detection of Hallucinations in LLM Activations](https://mlsanity.com/paper/2312.02798/) (2023)
- [Large Language Models as Theory of Mind Aware Generative Agents with Counterfactual Reflection](https://mlsanity.com/paper/2501.15355/) (2025)
- [Your Co-Workers Matter: Evaluating Collaborative Capabilities of Language Models in Blocks World](https://mlsanity.com/paper/2404.00246/) (2024)
- [A Survey of Theory of Mind in Large Language Models: Evaluations, Representations, and Safety Risks](https://mlsanity.com/paper/2502.06470/) (2025)
- [Conceptual Framework for Autonomous Cognitive Entities](https://mlsanity.com/paper/2310.06775/) (2023)
- [Language Models as Critical Thinking Tools: A Case Study of Philosophers](https://mlsanity.com/paper/2404.04516/) (2024)
- [ToM-LM: Delegating Theory of Mind Reasoning to External Symbolic Executors in Large Language Models](https://mlsanity.com/paper/2404.15515/) (2024)
- [MindSemantix: Deciphering Brain Visual Experiences with a Brain-Language Model](https://mlsanity.com/paper/2405.18812/) (2024)
- [Assessing mentalization in humans and large language models](https://mlsanity.com/paper/2608.26291/) (2026)
- [Automated Meta Prompt Engineering for Alignment with the Theory of Mind](https://mlsanity.com/paper/2505.09024/) (2025)
- [Theory of Mind in Action: The Instruction Inference Task in Dynamic Human-Agent Collaboration](https://mlsanity.com/paper/2507.02935/) (2025)
- [Neural Synchrony Between Socially Interacting Language Models](https://mlsanity.com/paper/2602.17815/) (2026)

## Abstract (arXiv)

With their recent development, large language models (LLMs) have been found to exhibit a certain level of Theory of Mind (ToM), a complex cognitive capacity that is related to our conscious mind and that allows us to infer another's beliefs and perspective. While human ToM capabilities are believed to derive from the neural activity of a broadly interconnected brain network, including that of dorsal medial prefrontal cortex (dmPFC) neurons, the precise processes underlying LLM's capacity for ToM or their similarities with that of humans remains largely unknown. In this study, we drew inspiration from the dmPFC neurons subserving human ToM and employed a similar methodology to examine whether LLMs exhibit comparable characteristics. Surprisingly, our analysis revealed a striking resemblance between the two, as hidden embeddings (artificial neurons) within LLMs started to exhibit significant responsiveness to either true- or false-belief trials, suggesting their ability to represent another's perspective. These artificial embedding responses were closely correlated with the LLMs' performance during the ToM tasks, a property that was dependent on the size of the models. Further, the other's beliefs could be accurately decoded using the entire embeddings, indicating the presence of the embeddings' ToM capability at the population level. Together, our findings revealed an emergent property of LLMs' embeddings that modified their activities in response to ToM features, offering initial evidence of a parallel between the artificial model and neurons in the human brain.