# Language Models Might Not Understand You: Evaluating Theory of Mind via Story Prompting

arXiv: https://arxiv.org/abs/2506.19089 · HTML: https://mlsanity.com/paper/2506.19089/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 23 Jun 2025.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)

## Builds on (most cited first, 25 of 25)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks](https://mlsanity.com/paper/2302.08399/) (2023)
- [Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning](https://mlsanity.com/paper/2502.14768/) (2025)
- [InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews](https://mlsanity.com/paper/2310.17976/) (2023)
- [Understanding Social Reasoning in Language Models with Language Models](https://mlsanity.com/paper/2306.15448/) (2023)
- [FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions](https://mlsanity.com/paper/2310.15421/) (2023)
- [Does Synthetic Data Generation of LLMs Help Clinical Text Mining?](https://mlsanity.com/paper/2303.04360/) (2023)
- [MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining](https://mlsanity.com/paper/2505.07608/) (2025)
- [Evaluating the World Model Implicit in a Generative Model](https://mlsanity.com/paper/2406.03689/) (2024)
- [Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples](https://mlsanity.com/paper/2305.15269/) (2023)
- [ToMBench: Benchmarking Theory of Mind in Large Language Models](https://mlsanity.com/paper/2402.15052/) (2024)
- [HI-TOM: A Benchmark for Evaluating Higher-Order Theory of Mind Reasoning in Large Language Models](https://mlsanity.com/paper/2310.16755/) (2023)
- [PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models](https://mlsanity.com/paper/2504.16074/) (2025)
- [On the Diversity of Synthetic Data and its Impact on Training Large Language Models](https://mlsanity.com/paper/2410.15226/) (2024)
- [OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Models](https://mlsanity.com/paper/2402.06044/) (2024)
- [DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows](https://mlsanity.com/paper/2402.10379/) (2024)
- [CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds](https://mlsanity.com/paper/2412.05631/) (2024)
- [Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models](https://mlsanity.com/paper/2412.02980/) (2024)
- [Explore Theory of Mind: Program-guided adversarial data generation for theory of mind reasoning](https://mlsanity.com/paper/2412.12175/) (2024)
- [A Notion of Complexity for Theory of Mind via Discrete World Models](https://mlsanity.com/paper/2406.11911/) (2024)
- [Emo Pillars: Knowledge Distillation to Support Fine-Grained Context-Aware and Context-Less Emotion Classification](https://mlsanity.com/paper/2504.16856/) (2025)

## Abstract (arXiv)

We introduce StorySim, a programmable framework for synthetically generating stories to evaluate the theory of mind (ToM) and world modeling (WM) capabilities of large language models (LLMs). Unlike prior benchmarks that may suffer from contamination in pretraining data, or rely on an LLM for generation, StorySim produces novel, compositional story prompts anchored by a highly controllable Storyboard, enabling precise manipulation of character perspectives and events. Using StorySim, we evaluate LLMs across three kinds of ToM tasks: false belief, goal-directed, and preference attribution tasks. We then use our framework to design first- and second-order ToM tasks alongside WM tasks that control for the ability to track and model mental states. Our experiments across a suite of LLMs show that most models achieve higher accuracy on WM tasks than on ToM tasks, and that some models tend to reason more accurately when the subject of reasoning is a person rather than an inanimate object. Additionally, models struggle with goal-directed reasoning the most, and performance does not always scale with model size. All code for generating data and evaluations is freely available.