# Towards properly implementing Theory of Mind in AI systems: An account of four misconceptions

arXiv: https://arxiv.org/abs/2503.16468 · HTML: https://mlsanity.com/paper/2503.16468/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 115 references that are in the map.
- First posted on arXiv 28 Feb 2025.

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [OLMo: Accelerating the Science of Language Models](https://mlsanity.com/paper/2402.00838/) (2024)
- [Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks](https://mlsanity.com/paper/2302.08399/) (2023)
- [Emergent Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2212.09196/) (2022)
- [Machine Theory of Mind](https://mlsanity.com/paper/1802.07740/) (2018)
- [Evaluating Large Language Models in Theory of Mind Tasks](https://mlsanity.com/paper/2302.02083/) (2023)
- [FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions](https://mlsanity.com/paper/2310.15421/) (2023)
- [Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models](https://mlsanity.com/paper/2305.14763/) (2023)
- [MMToM-QA: Multimodal Theory of Mind Question Answering](https://mlsanity.com/paper/2401.08743/) (2024)
- [Aligning Superhuman AI with Human Behavior: Chess as a Model System](https://mlsanity.com/paper/2006.01855/) (2020)
- [ToMBench: Benchmarking Theory of Mind in Large Language Models](https://mlsanity.com/paper/2402.15052/) (2024)
- [Boosting Theory-of-Mind Performance in Large Language Models via Prompting](https://mlsanity.com/paper/2304.11490/) (2023)
- [LLMs achieve adult human performance on higher-order theory of mind tasks](https://mlsanity.com/paper/2405.18870/) (2024)
- [Hybrid Intelligence](https://mlsanity.com/paper/2105.00691/) (2021)
- [Theory of Mind in Large Language Models: Examining Performance of 11 State-of-the-Art models vs. Children Aged 7-10 on Advanced Tests](https://mlsanity.com/paper/2310.20320/) (2023)
- [ToMChallenges: A Principle-Guided Dataset and Diverse Evaluation Tasks for Exploring Theory of Mind](https://mlsanity.com/paper/2305.15068/) (2023)
- [TMGBench: A Systematic Game Benchmark for Evaluating Strategic Reasoning Abilities of LLMs](https://mlsanity.com/paper/2410.10479/) (2024)
- [Large Language Models: The Need for Nuance in Current Debates and a Pragmatic Perspective on Understanding](https://mlsanity.com/paper/2310.19671/) (2023)
- [A Notion of Complexity for Theory of Mind via Discrete World Models](https://mlsanity.com/paper/2406.11911/) (2024)
- [Does ChatGPT Have a Mind?](https://mlsanity.com/paper/2407.11015/) (2024)
- [Do large language models solve verbal analogies like children do?](https://mlsanity.com/paper/2310.20384/) (2023)
- [GPT-4o reads the mind in the eyes](https://mlsanity.com/paper/2410.22309/) (2024)

## Built on by (most cited first, 3 of 3)

- [Agentic Large Language Models, a survey](https://mlsanity.com/paper/2503.23037/) (2025)
- [Understanding Large Language Models](https://mlsanity.com/paper/2607.01006/) (2026)
- [Evaluating Theory of Mind in Reasoning Models: Robustness over Reasoning](https://mlsanity.com/paper/2608.04646/) (2026)

## Abstract (arXiv)

The search for effective collaboration between humans and computer systems is one of the biggest challenges in Artificial Intelligence. One of the more effective mechanisms that humans use to coordinate with one another is theory of mind (ToM). ToM can be described as the ability to `take someone else's perspective and make estimations of their beliefs, desires and intentions, in order to make sense of their behaviour and attitudes towards the world'. If leveraged properly, this skill can be very useful in Human-AI collaboration. This introduces the question how we implement ToM when building an AI system. Humans and AI Systems work quite differently, and ToM is a multifaceted concept, each facet rooted in different research traditions across the cognitive and developmental sciences. We observe that researchers from artificial intelligence and the computing sciences, ourselves included, often have difficulties finding their way in the ToM literature. In this paper, we identify four common misconceptions around ToM that we believe should be taken into account when developing an AI system. We have hyperbolised these misconceptions for the sake of the argument, but add nuance in their discussion. The misconceptions we discuss are: (1) "Humans Use a ToM Module, So AI Systems Should As Well". (2) "Every Social Interaction Requires (Advanced) ToM". (3) "All ToM is the Same". (4) "Current Systems Already Have ToM". After discussing the misconception, we end each section by providing tentative guidelines on how the misconception can be overcome.