# Narrative Landscape: Mapping Narrative Dispositions Across LLMs

arXiv: https://arxiv.org/abs/2605.08742 · HTML: https://mlsanity.com/paper/2605.08742/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 16 references that are in the map.
- First posted on arXiv 9 May 2026.

## Builds on (most cited first, 7 of 7)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2406.07791/) (2024)
- [The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs](https://mlsanity.com/paper/2509.03730/) (2025)
- [LMLPA: Language Model Linguistic Personality Assessment](https://mlsanity.com/paper/2410.17632/) (2024)
- [Large Language Models Often Say One Thing and Do Another](https://mlsanity.com/paper/2503.07003/) (2025)
- [A Comparative Study of Large Language Models and Human Personality Traits](https://mlsanity.com/paper/2505.14845/) (2025)
- [Style over Story: Measuring LLM Narrative Preferences via Structured Selection](https://mlsanity.com/paper/2510.02025/) (2025)

## Abstract (arXiv)

This study proposes a quantitative framework for profiling LLM dispositions as stable, model-specific regularities in output under repeated, controlled elicitation. Using a structured narrative constraint-selection task administered across six frontier models and three instruction types, we operationalize disposition through two dimensions: "consistency", measured as cross-replication selection overlap via Jaccard similarity, and "diversity", measured as dispersion across options via the inverse Simpson index. We further introduce Narrative Landscape, a PCA-based visualization that maps each model's selection profile into a shared space for direct comparison. Results reveal a clear rigidity-exploration spectrum across model families and show that instruction types shift the geometry of selection spaces even when scalar metrics appear similar, indicating that comparable scores can mask qualitatively distinct selection topologies.