# Constrained Reasoning Chains for Enhancing Theory-of-Mind in Large Language Models

arXiv: https://arxiv.org/abs/2409.13490 · HTML: https://mlsanity.com/paper/2409.13490/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 10 of its 51 references that are in the map.
- First posted on arXiv 20 Sep 2024.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 10 of 10)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilities](https://mlsanity.com/paper/2311.10227/) (2023)
- [Privacy in Large Language Models: Attacks, Defenses and Future Directions](https://mlsanity.com/paper/2310.10383/) (2023)
- [NegotiationToM: A Benchmark for Stress-testing Machine Theory of Mind on Negotiation Surrounding](https://mlsanity.com/paper/2404.13627/) (2024)
- [Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extraction](https://mlsanity.com/paper/2404.14215/) (2024)
- [Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Information](https://mlsanity.com/paper/2408.02559/) (2024)
- [Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models](https://mlsanity.com/paper/2405.07667/) (2024)
- [Self-Consistent Narrative Prompts on Abductive Natural Language Inference](https://mlsanity.com/paper/2309.08303/) (2023)

## Built on by (most cited first, 5 of 5)

- [MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems](https://mlsanity.com/paper/2505.18943/) (2025)
- [Rethinking Chain-of-Thought from the Perspective of Self-Training](https://mlsanity.com/paper/2412.10827/) (2024)
- [Pragmatic Inference Chain (PIC) Improving LLMs' Reasoning of Authentic Implicit Toxic Language](https://mlsanity.com/paper/2503.01539/) (2025)
- [Specification and Evaluation of Multi-Agent LLM Systems -- Prototype and Cybersecurity Applications](https://mlsanity.com/paper/2506.10467/) (2025)
- [Assessing mentalization in humans and large language models](https://mlsanity.com/paper/2608.26291/) (2026)

## Abstract (arXiv)

Theory-of-Mind (ToM) ability possessed by Large Language Models (LLMs) has been shown to be limited. Most existing methods for improving ToM in LLMs adopt zero-shot prompting, and they face challenges including poor performance in complex ToM reasoning tasks and an inability to handle non-narrative contexts. We propose a zero-shot prompting method named Constrained Chain-of-ToM (CCoToM) that leverages domain knowledge and the causal relations between ToM dimensions to address these limitations. Specifically, CCoToM guides LLMs to construct explicit reasoning chains by first prompting LLMs to infer related ToM dimensions (e.g., belief). Afterward, CCoToM prompts LLMs to infer the queried ToM dimension based on the generated related ToM dimensions and corresponding causal relations. Additionally, CCoToM adaptively imposes constraints on prompts to introduce inductive biases and improve consistency between ToM dimensions. Besides narratives, CCoToM can also handle non-narrative contexts like conversations. Extensive experiments show that CCoToM consistently outperforms previous state-of-the-art methods by large margins across all LLMs and datasets used. We also conduct in-depth analyses to gain deeper insights into CCoToM. We have made our code publicly available.