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

TL;DR

This paper introduces GROVE, an interactive visualization tool that displays multiple language model outputs as overlapping paths in a text graph, revealing distributional structures to improve user understanding.

Contribution

GROVE enables visualization of language model output distributions, highlighting shared structures and diversity, based on user studies and formative research.

Findings

Graph summaries improve diversity assessment.

Direct output inspection better for detail-oriented questions.

User studies validate GROVE's effectiveness in understanding distributions.

Abstract

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.