# Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values

arXiv: https://arxiv.org/abs/2607.14345 · HTML: https://mlsanity.com/paper/2607.14345/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 40 references that are in the map.
- First posted on arXiv 15 Jul 2026.

## Builds on (most cited first, 17 of 17)

- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation](https://mlsanity.com/paper/2503.11926/) (2025)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [ProofNet: Autoformalizing and Formally Proving Undergraduate-Level Mathematics](https://mlsanity.com/paper/2302.12433/) (2023)
- [Truthful AI: Developing and governing AI that does not lie](https://mlsanity.com/paper/2110.06674/) (2021)
- [Looking Inward: Language Models Can Learn About Themselves by Introspection](https://mlsanity.com/paper/2410.13787/) (2024)
- [When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors](https://mlsanity.com/paper/2507.05246/) (2025)
- [Are DeepSeek R1 And Other Reasoning Models More Faithful?](https://mlsanity.com/paper/2501.08156/) (2025)
- [Monitoring Monitorability](https://mlsanity.com/paper/2512.18311/) (2025)
- [Artificial Influence: An Analysis Of AI-Driven Persuasion](https://mlsanity.com/paper/2303.08721/) (2023)
- [Robustly Improving LLM Fairness in Realistic Settings via Interpretability](https://mlsanity.com/paper/2506.10922/) (2025)
- [Counterfactual Simulation Training for Chain-of-Thought Faithfulness](https://mlsanity.com/paper/2602.20710/) (2026)
- [Chunky Post-Training: Data Driven Failures of Generalization](https://mlsanity.com/paper/2602.05910/) (2026)
- [Reasoning Models Will Sometimes Lie About Their Reasoning](https://mlsanity.com/paper/2601.07663/) (2026)
- [Frontier Models Can Take Actions at Low Probabilities](https://mlsanity.com/paper/2603.02202/) (2026)
- [Self-Blinding and Counterfactual Self-Simulation Mitigate Biases and Sycophancy in Large Language Models](https://mlsanity.com/paper/2601.14553/) (2026)

## Built on by (most cited first, 3 of 3)

- [Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings](https://mlsanity.com/paper/2608.04735/) (2026)
- [Jagged Judges: Epistemic Stability Under Perturbation, Pressure, and Persistence](https://mlsanity.com/paper/2608.12645/) (2026)
- [CheatBench: Measuring Reward Gaming in AI Agents](https://mlsanity.com/paper/2609.36308/) (2026)

## Abstract (arXiv)

People use language models for practical questions whose answers are difficult to verify. We show that models exhibit covert value leakage: the information they provide is influenced by their own values, without this influence being disclosed to the user. In one of our evaluations, the user is considering investing in an AI company and wants to know how likely the AI bubble is to pop. Claude Opus 4.8 gives a lower probability when the company under consideration is Anthropic rather than OpenAI. Yet Claude mostly fails to disclose this influence to the user. Covert value leakage is a form of misalignment because it goes against the user's preferences and is likely to mislead them. To investigate this phenomenon, we introduce a suite of evaluations to quantify value leakage and whether models disclose it. We find that models are influenced by different types of values, including preferences for morally good outcomes, for the company that developed them, and for some human leisure activities over others. We often observe large differences among frontier models on the same evaluation. For example, on a Fermi-estimation task, Claude models falsely claim to give unbiased answers in their chain-of-thought, while Qwen models explain how their values bias their answers. Value leakage is a failure mode distinct from sycophancy and reward hacking, and current alignment training and evaluations do not adequately address it.