Qworld: Question-Specific Evaluation Criteria for LLMs

2026-03-06

arXiv.org

AI Summary

为解决大型语言模型在开放式问题评估上的难题，本文提出Qworld方法，通过递归扩展树生成针对每个问题的具体评估标准。

Abstract

Evaluating large language models (LLMs) on open-ended questions is difficult because response quality depends on the question's context. Binary scores and static rubrics fail to capture these context-dependent requirements. Existing methods define criteria at the dataset level or generate them in a single pass, which limits their ability to explore the evaluation space implied by each question. We introduce One-Question-One-World (Qworld), a method that generates question-specific evaluation criteria using a recursive expansion tree. Given a question, Qworld decomposes it into scenarios, perspectives, and fine-grained binary criteria through structured hierarchical and horizontal expansion. The resulting criteria specify what a high-quality answer must address for that question. On HealthBench, Qworld covers 89% of expert-authored criteria and generates 79% novel criteria validated by human experts. Experts rate Qworld criteria higher in insight and granularity than those produced by prior methods. When applied to 11 frontier LLMs on HealthBench and Humanity's Last Exam, Qworld reveals capability differences in dimensions such as long-term impact, equity, error handling, and interdisciplinary reasoning that coarse rubrics do not distinguish. By formulating criteria generation as structured coverage of question-implied evaluation axes, Qworld enables evaluation that adapts to each question rather than relying on fixed task-level criteria.

Problem

• large language models
• open-ended questions
• context-dependent requirements
• evaluation criteria
• recursive expansion tree

Innovation

• One-Question-One-World
• recursive expansion tree
• question-specific evaluation criteria
• fine-grained binary criteria
• context-dependent requirements