# Rushes: A Human Preference Dataset for Pluralistic Alignment

arXiv: https://arxiv.org/abs/2607.20767 · HTML: https://mlsanity.com/paper/2607.20767/

## Key facts

- No citing papers in the map yet (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 10 of its 19 references that are in the map.
- First posted on arXiv 22 Jul 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, 10 of 10)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [PERSONA: A Reproducible Testbed for Pluralistic Alignment](https://mlsanity.com/paper/2407.17387/) (2024)
- [TextQuests: How Good are LLMs at Text-Based Video Games?](https://mlsanity.com/paper/2507.23701/) (2025)
- [Fabula Entropy Indexing: Objective Measures of Story Coherence](https://mlsanity.com/paper/2104.07472/) (2021)
- [Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures](https://mlsanity.com/paper/2510.14616/) (2025)
- [Narrative Studio: Visual narrative exploration using LLMs and Monte Carlo Tree Search](https://mlsanity.com/paper/2504.02426/) (2025)
- [LikeBench: Evaluating Subjective Likability in LLMs for Personalization](https://mlsanity.com/paper/2512.13077/) (2025)

## Abstract (arXiv)

We introduce Rushes, a dataset and benchmark for studying revealed human engagement preferences in interactive narrative environments. Rushes is collected through a game interface where users interact with AI-generated branching narratives and select one choice from a small, explicit candidate set at each decision point. Each interaction logs the full candidate set, the user's choice, and the evolving narrative context, yielding time-ordered trajectories with persistent user-level identifiers. Rushes contains 44,226 decision events from 8,167 unique users across six games, capturing sequential, personalized engagement behavior rather than static judgments. We show that user choices exhibit structured, non-random patterns, quantified by a low choice entropy relative to a uniform baseline. We position Rushes as a diagnostic benchmark for pluralistic alignment and demonstrate a robust Engagement Gap: state-of-the-art LLMs, including GPT-5, fail to outperform simple baselines. While classical Matrix Factorization (SVD) captures measurable personalized signal (37.7%), frontier LLMs (34.23%) struggle to even match the Popularity Baseline (36.4%) on event-level choice prediction. This gap suggests that single, population-level objectives, like those used in modern RLHF, appear insufficient to capture heterogeneous, context-dependent engagement signals. As a result, even highly capable models default to majority preferences rather than adapting to individual trajectories. We release Rushes to support research into pluralistic alignment and sequential decision-making in generative systems. The full code for the platform and dataset will be available here: https://github.com/microsoft/rushes