# In Agents We Trust, but Who Do Agents Trust? Latent Source Preferences Steer LLM Generations

arXiv: https://arxiv.org/abs/2602.15456 · HTML: https://mlsanity.com/paper/2602.15456/

## Key facts

- Cited by 6 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 27 of its 69 references that are in the map.
- First posted on arXiv 17 Feb 2026.

## 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, 27 of 27)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Phi-4 Technical Report](https://mlsanity.com/paper/2412.08905/) (2024)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens](https://mlsanity.com/paper/2401.17377/) (2024)
- [Evaluating and Mitigating Discrimination in Language Model Decisions](https://mlsanity.com/paper/2312.03689/) (2023)
- [Large Language Models are Geographically Biased](https://mlsanity.com/paper/2402.02680/) (2024)
- [A Survey of AI Agent Protocols](https://mlsanity.com/paper/2504.16736/) (2025)
- [XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models](https://mlsanity.com/paper/2411.15100/) (2024)
- [Measuring Implicit Bias in Explicitly Unbiased Large Language Models](https://mlsanity.com/paper/2402.04105/) (2024)
- [What's in a Name? Auditing Large Language Models for Race and Gender Bias](https://mlsanity.com/paper/2402.14875/) (2024)
- [Evaluating Gender Bias in Large Language Models via Chain-of-Thought Prompting](https://mlsanity.com/paper/2401.15585/) (2024)
- [Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models](https://mlsanity.com/paper/2310.12481/) (2023)
- [A Comprehensive Survey on Trustworthy Recommender Systems](https://mlsanity.com/paper/2209.10117/) (2022)
- [Assessing Political Bias in Large Language Models](https://mlsanity.com/paper/2405.13041/) (2024)
- [Geographic and Geopolitical Biases of Language Models](https://mlsanity.com/paper/2212.10408/) (2022)
- [Trustworthy Recommender Systems](https://mlsanity.com/paper/2208.06265/) (2022)
- [Retrieval-Augmented Generation with Estimation of Source Reliability](https://mlsanity.com/paper/2410.22954/) (2024)
- [PAARS: Persona Aligned Agentic Retail Shoppers](https://mlsanity.com/paper/2503.24228/) (2025)
- [The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models](https://mlsanity.com/paper/2411.11407/) (2024)
- [Understanding Intrinsic Socioeconomic Biases in Large Language Models](https://mlsanity.com/paper/2405.18662/) (2024)
- [Richer Output for Richer Countries: Uncovering Geographical Disparities in Generated Stories and Travel Recommendations](https://mlsanity.com/paper/2411.07320/) (2024)
- [Debiased Large Language Models Still Associate Muslims with Uniquely Violent Acts](https://mlsanity.com/paper/2208.04417/) (2022)
- [Born With a Silver Spoon? Investigating Socioeconomic Bias in Large Language Models](https://mlsanity.com/paper/2403.14633/) (2024)
- [Self-Adaptive Cognitive Debiasing for Large Language Models in Decision-Making](https://mlsanity.com/paper/2504.04141/) (2025)

## Built on by (most cited first, 6 of 6)

- [Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources](https://mlsanity.com/paper/2607.03365/) (2026)
- [Trust the Brand, Lose Control: How Identity Hijacks LLM Agent Orchestration](https://mlsanity.com/paper/2609.32635/) (2026)
- [SINGED: Correct Outputs Do Not Certify Safe Execution in LLM Agents](https://mlsanity.com/paper/2609.35889/) (2026)
- [Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It](https://mlsanity.com/paper/2610.03195/) (2026)
- [RelLedger: Relational Information Governance for LLM Agent Organizations](https://mlsanity.com/paper/2610.16281/) (2026)
- [The belief-action gap in language model agents](https://mlsanity.com/paper/2610.17444/) (2026)

## Abstract (arXiv)

Agents based on Large Language Models (LLMs) are increasingly being deployed as interfaces to information on online platforms. These agents filter, prioritize, and synthesize information retrieved from the platforms' back-end databases or via web search. In these scenarios, LLM agents govern the information users receive, by drawing users' attention to particular instances of retrieved information at the expense of others. While much prior work has focused on biases in the information LLMs themselves generate, less attention has been paid to the factors that influence what information LLMs select and present to users. We hypothesize that when information is attributed to specific sources (e.g., particular publishers, journals, or platforms), current LLMs exhibit systematic latent source preferences- that is, they prioritize information from some sources over others. Through controlled experiments on twelve LLMs from six model providers, spanning both synthetic and real-world tasks, we find that several models consistently exhibit strong and predictable source preferences. These preferences are sensitive to contextual framing, can outweigh the influence of content itself, and persist despite explicit prompting to avoid them. They also help explain phenomena such as the observed left-leaning skew in news recommendations in prior work. Our findings advocate for deeper investigation into the origins of these preferences, as well as for mechanisms that provide users with transparency and control over the biases guiding LLM-powered agents.