Social preferences with unstable interactive reasoning: Large language models in economic trust games
On the map: LLM reasoning → Reasoning for agents, planning and code
Abstract (arXiv)
While large language models (LLMs) have demonstrated remarkable capabilities in understanding human languages, this study explores how they translate this understanding into social exchange contexts that capture certain essences of real world human interactions. Three LLMs - ChatGPT-4, Claude, and Bard - were placed in economic trust games where players balance self-interest with trust and reciprocity, making decisions that reveal their social preferences and interactive reasoning abilities. Our study shows that LLMs deviate from pure self-interest and exhibit trust and reciprocity even without being prompted to adopt a specific persona. In the simplest one-shot interaction, LLMs emulated how human players place trust at the beginning of such a game. Larger human-machine divergences emerged in scenarios involving trust repayment or multi-round interactions, where decisions were influenced by both social preferences and interactive reasoning. LLMs responses varied significantly when prompted to adopt personas like selfish or unselfish players, with the impact outweighing differences between models or game types. Response of ChatGPT-4, in an unselfish or neutral persona, resembled the highest trust and reciprocity, surpassing humans, Claude, and Bard. Claude and Bard displayed trust and reciprocity levels that sometimes exceeded and sometimes fell below human choices. When given selfish personas, all LLMs showed lower trust and reciprocity than humans. Interactive reasoning to the actions of counterparts or changing game mechanics appeared to be random rather than stable, reproducible characteristics in the response of LLMs, though some improvements were observed when ChatGPT-4 responded in selfish or unselfish personas.
Key facts. Cited by 2 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 12 of its 28 references that are in the map. First posted on arXiv 16 May 2025.
Builds on
12 of 28 references.
References · 12
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
- 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
- 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
- 2023The Internal State of an LLM Knows When It's Lyingcited by 659
- 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 515
- 2022Using cognitive psychology to understand GPT-3cited by 398
- 2023Playing repeated games with Large Language Modelscited by 217
- 2022Thinking Fast and Slow in Large Language Modelscited by 137
- 2024Escalation Risks from Language Models in Military and Diplomatic Decision-Makingcited by 63
- 2023Strategic Behavior of Large Language Models: Game Structure vs. Contextual Framingcited by 51
- 2024InterIntent: Investigating Social Intelligence of LLMs via Intention Understanding in an Interactive Game Contextcited by 26
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2024Can Large Language Model Agents Simulate Human Trust Behavior?
- 2025A closer look at how large language models trust humans: patterns and biases
- 2025Humans expect rationality and cooperation from LLM opponents in strategic games
- 2025Value-Based Large Language Model Agent Simulation for Mutual Evaluation of Trust and Interpersonal Closeness
- 2026Evaluating LLM Alignment With Human Trust Models
- 2025Computational Basis of LLM's Decision Making in Social Simulation
- 2025Spontaneous Giving and Calculated Greed in Language Models
- 2024Are LLMs Socially Adaptive? Contrasting Belief Evolution in Large Language Models and Humans