cs.CLNov 3, 2026

COMPREHEND: Ultra-Fine-Grained Benchmark Understanding by Entailment Hierarchy

Authors: Sivaraaman Balakrishnan, Prakriti Shetty, Jeremiah Hong, Hamed Zamani, Haw-Shiuan Chang

Organizations: University of Massachusetts, Amherst, USA · University of Arizona, Tucson, USA

Abstract

Understanding what kind of prompts users typically ask and how well an LLM performs on these prompt categories is crucial for LLM practitioners. The existing methods satisfy the demand by hierarchically clustering the user prompts and synthesizing the cluster names using an LLM to build a taxonomy. However, the cluster names from these methods are usually too general for humans to understand the detailed prompt distributions and identify the exact strengths and weaknesses of LLMs. In this study, we propose COMPREHEND, which automatically constructs an ultra-fine-grained entailment hierarchy for the prompts. The entailment hierarchy replaces the cluster names in the taxonomy with sentences to provide more precise cluster descriptions for more fine-grained categorization. Compared with EvalTree, a state-of-the-art taxonomy construction method, COMPREHEND improves an entailment/faithfulness metric from 22.6 to 41.7 and an informative metric from 16.3 to 39.1 in WildBench. Our experiments also show that the weakness report generated based on our entailment hierarchy is much more informative than EvalTree in terms of predicting the response scores in the benchmark. All the code is released in https://github.com/JackNapier20/COMPREHEND_public.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Less Back-and-Forth: A Comparative Study of Structured Prompting

    May 19, 2026Saurav Ghosh, Gabriella Polach, Abdou SowLLM EvaluationStructured Prompting

  2. PROMPT2BOX:Improving LLM Weakness Discovery and Specificity Estimation by Uncovering Entailment Structure among Prompts

    Mar 22, 2026Neeladri Bhuiya, Shib Sankar Dasgupta, Andrew McCallum +1LLM EvaluationRepresentation Learning

  3. Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement

    Jun 25, 2026Sangwoo Cho, Kushal Chawla, Pengshan Cai +4LLM EvaluationLLM-as-a-Judge