Beyond Mimicry: Preference Coherence in LLMs
This research addresses concerns about AI deployment in contexts requiring complex value trade-offs, revealing that current systems lack unified preference structures, which is an incremental finding building on prior work in AI behavior analysis.
The study investigated whether large language models exhibit genuine preference structures by testing their responses to AI-specific trade-offs, finding that only 10.4% of model-category combinations showed meaningful preference coherence, while 54.2% showed no detectable trade-off behavior.
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.