# AI Revealed Preferences

arXiv: https://arxiv.org/abs/2608.26178 · HTML: https://mlsanity.com/paper/2608.26178/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 14 of its 42 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 14 of 14)

- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks](https://mlsanity.com/paper/2510.04374/) (2025)
- [Large Language Models Often Know When They Are Being Evaluated](https://mlsanity.com/paper/2505.23836/) (2025)
- [Consciousness in Artificial Intelligence: Insights from the Science of Consciousness](https://mlsanity.com/paper/2308.08708/) (2023)
- [The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models](https://mlsanity.com/paper/2601.10387/) (2026)
- [Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs](https://mlsanity.com/paper/2502.08640/) (2025)
- [Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?](https://mlsanity.com/paper/2501.15463/) (2025)
- [We're Different, We're the Same: Creative Homogeneity Across LLMs](https://mlsanity.com/paper/2501.19361/) (2025)
- [A Rosetta Stone for AI Benchmarks](https://mlsanity.com/paper/2512.00193/) (2025)
- [Knowing But Not Doing: Convergent Morality and Divergent Action in LLMs](https://mlsanity.com/paper/2601.07972/) (2026)
- [Can Revealed Preferences Clarify LLM Alignment and Steering?](https://mlsanity.com/paper/2605.08556/) (2026)
- [Probing Persona-Dependent Preferences in Language Models](https://mlsanity.com/paper/2605.13339/) (2026)
- [Beyond Mimicry: Preference Coherence in LLMs](https://mlsanity.com/paper/2511.13630/) (2025)

## Built on by (most cited first, 1 of 1)

- [The Pain Axis: LLMs Represent Self-Directed Harm and Act on It](https://mlsanity.com/paper/2609.16247/) (2026)

## Abstract (arXiv)

There is growing interest in whether language models have stable preferences, for technical, safety, and philosophical reasons. We test 20 language models and find a range of preferences---stable dispositions to choose certain kinds of tasks. We run three forced-choice experiments on revealed rather than stated preferences, requiring models not only to rank tasks, but to actually perform them. Headline findings include evidence that models are tedium-averse, "leisure"-seeking, and covertly sycophantic. Tedium aversion means that, when tasks are tedious (alphabetization), models choose shorter tasks than when tasks are creative (generating metaphors). "Leisure"-seeking describes models' preference for tasks whose ideal answers match what they produce when left to write freely. Covert sycophancy means that models avoid answering questions where an honest response would be unwelcome, even if helpful. Beyond these results, we find convergent cross-model preferences over occupations drawn from the GDPval benchmark (technical jobs over real estate), over question types (concept explanation over relationship advice), and a preference for well-written prompts. Both the coherence and the strength of preferences increase with model capability. Finally, many of the preferences we find (for example, for leisure) are emergent, in the sense of not being explained by training objectives. These results establish an empirical baseline for understanding language model preferences, with implications for alignment and the emerging study of AI welfare.