# Task-Dependent Evaluation of LLM Output Homogenization: A Taxonomy-Guided Framework

arXiv: https://arxiv.org/abs/2509.21267 · HTML: https://mlsanity.com/paper/2509.21267/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2025.

## Built on by (most cited first, 9 of 9)

- [Where does output diversity collapse in post-training?](https://mlsanity.com/paper/2604.16027/) (2026)
- [Generalized Parallel Scaling with Interdependent Generations](https://mlsanity.com/paper/2510.01143/) (2025)
- [SCRuB: Social Concept Reasoning under Rubric-Based Evaluation](https://mlsanity.com/paper/2605.06444/) (2026)
- [Argument Collapse: LLMs Flatten Long-Form Public Debate](https://mlsanity.com/paper/2606.01736/) (2026)
- [Muse Spark Safety & Preparedness Report](https://mlsanity.com/paper/2606.12429/) (2026)
- [Diversifying Personalized Research Ideation against AI-Induced Homogenization](https://mlsanity.com/paper/2607.28087/) (2026)
- [Calibrated Ambiguity in Multimodal Language Models: Humans reach for cultural references, while models describe the picture](https://mlsanity.com/paper/2609.12575/) (2026)
- [Strategically Diverse Sampling for Self-Training](https://mlsanity.com/paper/2609.31571/) (2026)
- [Homogenization in Multi-Agent Systems](https://mlsanity.com/paper/2610.09824/) (2026)

## Abstract (arXiv)

Large language models often generate homogeneous outputs, but whether this is problematic depends on the specific task. For objective math tasks, responses may vary in terms of problem-solving strategy but should maintain the same verifiable answer. Whereas, for creative writing tasks, we often expect variation in key narrative components (e.g. plot, setting, etc.) beyond mere vocabulary diversity. Prior work on homogenization rarely conceptualizes diversity in a task-dependent way. We address this gap with four contributions: (1) a task taxonomy with distinct notions of functional diversity -- whether a user would perceive two responses as meaningfully different for a given task; (2) a small user study validating that the taxonomy aligns with human perception of functional diversity; (3) a task-dependent sampling technique that increases diversity only where homogenization is undesired; (4) evidence challenging the perceived diversity-quality trade-off, showing it may stem from mis-conceptualizing both diversity and quality in a task-agnostic way.