# Large Model Strategic Thinking, Small Model Efficiency: Transferring Theory of Mind in Large Language Models

arXiv: https://arxiv.org/abs/2408.05241 · HTML: https://mlsanity.com/paper/2408.05241/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 26 of its 56 references that are in the map.
- First posted on arXiv 5 Aug 2024.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 26 of 26)

- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Large Language Models: A Survey](https://mlsanity.com/paper/2402.06196/) (2024)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs](https://mlsanity.com/paper/2210.13312/) (2022)
- [Playing repeated games with Large Language Models](https://mlsanity.com/paper/2305.16867/) (2023)
- [Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4](https://mlsanity.com/paper/2304.03439/) (2023)
- [Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve](https://mlsanity.com/paper/2309.13638/) (2023)
- [GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations](https://mlsanity.com/paper/2402.12348/) (2024)
- [LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models](https://mlsanity.com/paper/2404.01230/) (2024)
- [Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation](https://mlsanity.com/paper/2309.17234/) (2023)
- [The rising costs of training frontier AI models](https://mlsanity.com/paper/2405.21015/) (2024)
- [How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments](https://mlsanity.com/paper/2403.11807/) (2024)
- [Strategic Behavior of Large Language Models: Game Structure vs. Contextual Framing](https://mlsanity.com/paper/2309.05898/) (2023)
- [Fine-tuning Large Language Models for Domain-specific Machine Translation](https://mlsanity.com/paper/2402.15061/) (2024)
- [Fine-tuning and Utilization Methods of Domain-specific LLMs](https://mlsanity.com/paper/2401.02981/) (2024)
- [Unveiling the Generalization Power of Fine-Tuned Large Language Models](https://mlsanity.com/paper/2403.09162/) (2024)
- [ALYMPICS: LLM Agents Meet Game Theory -- Exploring Strategic Decision-Making with AI Agents](https://mlsanity.com/paper/2311.03220/) (2023)
- [Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains](https://mlsanity.com/paper/2402.05140/) (2024)
- [Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks](https://mlsanity.com/paper/2404.00376/) (2024)
- [Fine Tuning LLM for Enterprise: Practical Guidelines and Recommendations](https://mlsanity.com/paper/2404.10779/) (2024)
- [The Machine Psychology of Cooperation: Can GPT models operationalise prompts for altruism, cooperation, competitiveness and selfishness in economic games?](https://mlsanity.com/paper/2305.07970/) (2023)
- [Balancing Specialized and General Skills in LLMs: The Impact of Modern Tuning and Data Strategy](https://mlsanity.com/paper/2310.04945/) (2023)
- [Can Language Models Teach Weaker Agents? Teacher Explanations Improve Students via Personalization](https://mlsanity.com/paper/2306.09299/) (2023)
- [Assessing Large Language Models' ability to predict how humans balance self-interest and the interest of others](https://mlsanity.com/paper/2307.12776/) (2023)
- [Human-Like Intuitive Behavior and Reasoning Biases Emerged in Language Models -- and Disappeared in GPT-4](https://mlsanity.com/paper/2306.07622/) (2023)
- [The Reasoning Under Uncertainty Trap: A Structural AI Risk](https://mlsanity.com/paper/2402.01743/) (2024)

## Built on by (most cited first, 7 of 7)

- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [From Black Boxes to Transparent Minds: Evaluating and Enhancing the Theory of Mind in Multimodal Large Language Models](https://mlsanity.com/paper/2506.14224/) (2025)
- [Heterogeneous Debate Engine: Identity-Grounded Cognitive Architecture for Resilient LLM-Based Ethical Tutoring](https://mlsanity.com/paper/2603.27404/) (2026)
- [Interpretable Risk Mitigation in LLM Agent Systems](https://mlsanity.com/paper/2505.10670/) (2025)
- [UniToMBench: Integrating Perspective-Taking to Improve Theory of Mind in LLMs](https://mlsanity.com/paper/2506.09450/) (2025)
- [Communication Enhances LLMs' Stability in Strategic Thinking](https://mlsanity.com/paper/2602.06081/) (2026)
- [Strategy, Not Payoffs: A Behavioural Embedding of Normal-Form Games](https://mlsanity.com/paper/2607.27536/) (2026)

## Abstract (arXiv)

As the performance of larger, newer Large Language Models continues to improve for strategic Theory of Mind (ToM) tasks, the demand for these state-of-the-art models increases commensurately. However, their deployment is costly both in terms of processing power and time. In this paper, we investigate the feasibility of creating smaller, highly-performing specialized algorithms by way of fine-tuning. To do this, we first present a large pre-trained model with 20 unique scenarios that combine different social contexts with games of varying social dilemmas, record its answers, and use them for Q&A fine-tuning on a smaller model of the same family. Our focus is on in-context game-theoretic decision-making, the same domain within which human interaction occurs and that requires both a theory of mind (or a semblance thereof) and an understanding of social dynamics. The smaller model is therefore trained not just on the answers provided, but also on the motivations provided by the larger model, which should contain advice and guidelines to navigate both strategic dilemmas and social cues. We find that the fine-tuned smaller language model consistently bridged the gap in performance between the smaller pre-trained version of the model and its larger relative and that its improvements extended in areas and contexts beyond the ones provided in the training examples, including on out-of-sample scenarios that include completely different game structures. On average for all games, through fine-tuning, the smaller model showed a 46% improvement measured as alignment towards the behavior of the larger model, with 100% representing indistinguishable behavior. When presented with out-of-sample social contexts and games, the fine-tuned model still displays remarkable levels of alignment, reaching an improvement of 18% and 28% respectively.