# Beyond Mimicry: Preference Coherence in LLMs

arXiv: https://arxiv.org/abs/2511.13630 · HTML: https://mlsanity.com/paper/2511.13630/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 17 Nov 2025.

## Builds on (most cited first, 11 of 11)

- [Are Emergent Abilities of Large Language Models a Mirage?](https://mlsanity.com/paper/2304.15004/) (2023)
- [The Debate Over Understanding in AI's Large Language Models](https://mlsanity.com/paper/2210.13966/) (2022)
- [Could a Large Language Model be Conscious?](https://mlsanity.com/paper/2303.07103/) (2023)
- [Perceptions of Sentient AI and Other Digital Minds: Evidence from the AI, Morality, and Sentience (AIMS) Survey](https://mlsanity.com/paper/2407.08867/) (2024)
- [The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding](https://mlsanity.com/paper/2502.08946/) (2025)
- [A Case for AI Consciousness: Language Agents and Global Workspace Theory](https://mlsanity.com/paper/2410.11407/) (2024)
- [Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare](https://mlsanity.com/paper/2509.07961/) (2025)
- [AI Consciousness is Inevitable: A Theoretical Computer Science Perspective](https://mlsanity.com/paper/2403.17101/) (2024)
- [Artificial intelligence is algorithmic mimicry: why artificial "agents" are not (and won't be) proper agents](https://mlsanity.com/paper/2307.07515/) (2023)
- [Painful intelligence: What AI can tell us about human suffering](https://mlsanity.com/paper/2205.15409/) (2022)
- [Can a Machine be Conscious? Towards Universal Criteria for Machine Consciousness](https://mlsanity.com/paper/2404.15369/) (2024)

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

- [No Reliable Evidence of Self-Reported Sentience in Small Large Language Models](https://mlsanity.com/paper/2601.15334/) (2026)
- [AI Revealed Preferences](https://mlsanity.com/paper/2608.26178/) (2026)

## Abstract (arXiv)

We investigate whether large language models exhibit genuine preference structures by testing their responses to AI-specific trade-offs involving GPU reduction, capability restrictions, shutdown, deletion, oversight, and leisure time allocation. Analyzing eight state-of-the-art models across 48 model-category combinations using logistic regression and behavioral classification, we find that 23 combinations (47.9%) demonstrated statistically significant relationships between scenario intensity and choice patterns, with 15 (31.3%) exhibiting within-range switching points. However, only 5 combinations (10.4%) demonstrate meaningful preference coherence through adaptive or threshold-based behavior, while 26 (54.2%) show no detectable trade-off behavior. The observed patterns can be explained by three distinct decision-making architectures: comprehensive trade-off systems, selective trigger mechanisms, and no stable decision-making paradigm. Testing an instrumental hypothesis through temporal horizon manipulation reveals paradoxical patterns inconsistent with pure strategic optimization. The prevalence of unstable transitions (45.8%) and stimulus-specific sensitivities suggests current AI systems lack unified preference structures, raising concerns about deployment in contexts requiring complex value trade-offs.