# Beyond One Output: Visualizing and Comparing Distributions of Language Model Generations

arXiv: https://arxiv.org/abs/2604.18724 · HTML: https://mlsanity.com/paper/2604.18724/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 57 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 14 of 14)

- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts](https://mlsanity.com/paper/2110.01691/) (2021)
- [ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing](https://mlsanity.com/paper/2309.09128/) (2023)
- [Understanding the Benefits and Challenges of Using Large Language Model-based Conversational Agents for Mental Well-being Support](https://mlsanity.com/paper/2307.15810/) (2023)
- [Do LLMs write like humans? Variation in grammatical and rhetorical styles](https://mlsanity.com/paper/2410.16107/) (2024)
- [AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuances](https://mlsanity.com/paper/2409.11360/) (2024)
- [LLM Comparator: Visual Analytics for Side-by-Side Evaluation of Large Language Models](https://mlsanity.com/paper/2402.10524/) (2024)
- [Supporting Sensemaking of Large Language Model Outputs at Scale](https://mlsanity.com/paper/2401.13726/) (2024)
- [Detecting Mode Collapse in Language Models via Narration](https://mlsanity.com/paper/2402.04477/) (2024)
- [RELIC: Investigating Large Language Model Responses using Self-Consistency](https://mlsanity.com/paper/2311.16842/) (2023)
- [LMdiff: A Visual Diff Tool to Compare Language Models](https://mlsanity.com/paper/2111.01582/) (2021)
- [Prompting in the Dark: Assessing Human Performance in Prompt Engineering for Data Labeling When Gold Labels Are Absent](https://mlsanity.com/paper/2502.11267/) (2025)
- [generAItor: Tree-in-the-Loop Text Generation for Language Model Explainability and Adaptation](https://mlsanity.com/paper/2403.07627/) (2024)
- [The Impact of Revealing Large Language Model Stochasticity on Trust, Reliability, and Anthropomorphization](https://mlsanity.com/paper/2503.16114/) (2025)

## Abstract (arXiv)

Users typically interact with and evaluate language models via single outputs, but each output is just one sample from a broad distribution of possible completions. This interaction hides distributional structure such as modes, uncommon edge cases, and sensitivity to small prompt changes, leading users to over-generalize from anecdotes when iterating on prompts for open-ended tasks. Informed by a formative study with researchers who use LMs (n=13) examining when stochasticity matters in practice, how they reason about distributions over language, and where current workflows break down, we introduce GROVE. GROVE is an interactive visualization that represents multiple LM generations as overlapping paths through a text graph, revealing shared structure, branching points, and clusters while preserving access to raw outputs. We evaluate across three crowdsourced user studies (N=47, 44, and 40 participants) targeting complementary distributional tasks. Our results support a hybrid workflow: graph summaries improve structural judgments such as assessing diversity, while direct output inspection remains stronger for detail-oriented questions.