# A closer look at how large language models trust humans: patterns and biases

arXiv: https://arxiv.org/abs/2504.15801 · HTML: https://mlsanity.com/paper/2504.15801/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 24 of its 58 references that are in the map.
- First posted on arXiv 22 Apr 2025.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 24 of 24)

- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Mitigating Gender Bias in Natural Language Processing: Literature Review](https://mlsanity.com/paper/1906.08976/) (2019)
- [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023)
- ["Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters](https://mlsanity.com/paper/2310.09219/) (2023)
- [LanguageMPC: Large Language Models as Decision Makers for Autonomous Driving](https://mlsanity.com/paper/2310.03026/) (2023)
- [Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs](https://mlsanity.com/paper/2502.17424/) (2025)
- [MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making](https://mlsanity.com/paper/2404.15155/) (2024)
- [What Large Language Models Know and What People Think They Know](https://mlsanity.com/paper/2401.13835/) (2024)
- [Evil Geniuses: Delving into the Safety of LLM-based Agents](https://mlsanity.com/paper/2311.11855/) (2023)
- [LLM Social Simulations Are a Promising Research Method](https://mlsanity.com/paper/2504.02234/) (2025)
- [Clio: Privacy-Preserving Insights into Real-World AI Use](https://mlsanity.com/paper/2412.13678/) (2024)
- [Determinants of LLM-assisted Decision-Making](https://mlsanity.com/paper/2402.17385/) (2024)
- [LLM Voting: Human Choices and AI Collective Decision Making](https://mlsanity.com/paper/2402.01766/) (2024)
- [Investigating Subtler Biases in LLMs: Ageism, Beauty, Institutional, and Nationality Bias in Generative Models](https://mlsanity.com/paper/2309.08902/) (2023)
- [Trust in AI and Its Role in the Acceptance of AI Technologies](https://mlsanity.com/paper/2203.12687/) (2022)
- [Navigating LLM Ethics: Advancements, Challenges, and Future Directions](https://mlsanity.com/paper/2406.18841/) (2024)
- [LLM-Augmented Agent-Based Modelling for Social Simulations: Challenges and Opportunities](https://mlsanity.com/paper/2405.06700/) (2024)
- [The simulation of judgment in LLMs](https://mlsanity.com/paper/2502.04426/) (2025)
- [The impact of generative artificial intelligence on socioeconomic inequalities and policy making](https://mlsanity.com/paper/2401.05377/) (2023)
- [Enhancing Emergency Decision-making with Knowledge Graphs and Large Language Models](https://mlsanity.com/paper/2311.08732/) (2023)
- [Divine LLaMAs: Bias, Stereotypes, Stigmatization, and Emotion Representation of Religion in Large Language Models](https://mlsanity.com/paper/2407.06908/) (2024)
- [Surprising gender biases in GPT](https://mlsanity.com/paper/2407.06003/) (2024)
- [Measuring and identifying factors of individuals' trust in Large Language Models](https://mlsanity.com/paper/2502.21028/) (2025)
- [Measuring an artificial intelligence agent's trust in humans using machine incentives](https://mlsanity.com/paper/2212.13371/) (2022)

## Built on by (most cited first, 2 of 2)

- [Building and Measuring Trust between Large Language Models](https://mlsanity.com/paper/2508.15858/) (2025)
- [TrustMI: Causally controlling how assistants trust their users](https://mlsanity.com/paper/2610.06064/) (2026)

## Abstract (arXiv)

As large language models (LLMs) and LLM-based agents increasingly interact with humans in decision-making contexts, understanding the trust dynamics between humans and AI agents becomes a central concern. While considerable literature studies how humans trust AI agents, it is much less understood how LLM-based agents develop effective trust in humans. LLM-based agents likely rely on some sort of implicit effective trust in trust-related contexts (e.g., evaluating individual loan applications) to assist and affect decision making. Using established behavioral theories, we develop an approach that studies whether LLMs trust depends on the three major trustworthiness dimensions: competence, benevolence and integrity of the human subject. We also study how demographic variables affect effective trust. Across 43,200 simulated experiments, for five popular language models, across five different scenarios we find that LLM trust development shows an overall similarity to human trust development. We find that in most, but not all cases, LLM trust is strongly predicted by trustworthiness, and in some cases also biased by age, religion and gender, especially in financial scenarios. This is particularly true for scenarios common in the literature and for newer models. While the overall patterns align with human-like mechanisms of effective trust formation, different models exhibit variation in how they estimate trust; in some cases, trustworthiness and demographic factors are weak predictors of effective trust. These findings call for a better understanding of AI-to-human trust dynamics and monitoring of biases and trust development patterns to prevent unintended and potentially harmful outcomes in trust-sensitive applications of AI.