Reference-Based Analysis of Coherence and Diversity in Open-Ended Text Generation

Excerpt

arXiv:2609.28080v1 Announce Type: new Abstract: Evaluating open-ended text generation involves understanding how different properties of a continuation relate to its perceived quality. We present a reference-based framework for examining coherence and diversity through three perspectives: aligning their evolution with human trajectories, comparing their summaries with a human continuation of the same prompt, and estimating their likelihood under a human reference distribution. Experiments with h