Research
Style over Story: Measuring LLM Narrative Preferences via Structured Selection
arXiv:2510.02025v4 Announce Type: replace Abstract: We introduce a constraint-selection-based experiment design for measuring narrative preferences of Large Language Models (LLMs). This design offers
arXiv:2510.02025v4 Announce Type: replace Abstract: We introduce a constraint-selection-based experiment design for measuring narrative preferences of Large Language Models (LLMs). This design offers an interpretable lens on LLMs' narrative selection behavior. We developed a library of 200 narratology-grounded constraints and prompted selections from six LLMs under three different instruction types: basic, quality-focused, and creativity-focused. Findings demonstrate that models consistently prioritize Style over narrative content elements like Event, Character, and Setting. Style preferences remain stable across models and instruction types, whereas content elements show cross-model divergence and instructional sensitivity. These results suggest that LLMs have latent narrative preferences, which should inform how the NLP community evaluates and deploys models in creative domains.
Related
- Emergent Structured Representations Support Flexible In-Context Inference in Large Language Models
- A closer look at how large language models trust humans: patterns and biases
- LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization
- Do LLMs Encode Functional Importance of Reasoning Tokens?
Source: arXiv cs.CL | 2026-04-21