Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Qworld: Question-Specific Evaluation Criteria for LLMs

Shanghua Gao, Yuchang Su, Pengwei Sui, Curtis Ginder +1 more

Published

Mar 6, 2026

Citations

0

Trust level

Moderate

Usefulness score

50/100 (Medium)

Extraction confidence

55% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Domain Experts

Signals refreshed

Aug 19, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

General Rubric Rating

Should you rely on this paper?

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Use this for comparison and orientation, not as your only source.

Best use

Secondary protocol comparison source

Use if you need

Background context only.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

The abstract does not clearly describe the evaluation setup.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Weak or implicit
Validate from full paper
Usefulness for eval research
50/100
Moderate-confidence candidate

Useful as a secondary reference; validate protocol details against neighboring papers.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

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 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 capture. By generating evaluation criteria for each question, Qworld enables assessment of LLM responses that is tailored to the question rather than based on fixed task-level criteria.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

strong

Rubric Rating

Directly usable for protocol triage.

"Evaluating large language models (LLMs) on open-ended questions is difficult because response quality depends on the question's context."

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"Evaluating large language models (LLMs) on open-ended questions is difficult because response quality depends on the question's context."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Evaluating large language models (LLMs) on open-ended questions is difficult because response quality depends on the question's context."

Benchmarks / Datasets

strong

HLE, Healthbench

Useful for quick benchmark comparison.

"On HealthBench, Qworld covers 89% of expert-authored criteria and generates 79% novel criteria validated by human experts."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"Evaluating large language models (LLMs) on open-ended questions is difficult because response quality depends on the question's context."

Rater Population

strong

Domain Experts

Helpful for staffing comparability.

"On HealthBench, Qworld covers 89% of expert-authored criteria and generates 79% novel criteria validated by human experts."

Benchmarks and datasets

HLEHealthbench

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
Yes
Feedback types
Rubric Rating
Rater population
Domain Experts
Unit of annotation
Multi Dim Rubric
Expertise required
General
Evaluation details
Evaluation modes
None
Agentic eval
None
Quality controls
Not reported
Evidence quality
Moderate
Use this page as
Secondary protocol comparison source

Research brief

Metadata summary

Evaluating large language models (LLMs) on open-ended questions is difficult because response quality depends on the question's context.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • 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.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Expert verification evaluation

Contribution summary

  • 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.
  • On HealthBench, Qworld covers 89% of expert-authored criteria and generates 79% novel criteria validated by human experts.

Why it matters for eval

  • We introduce One-Question-One-World (Qworld), a method that generates question-specific evaluation criteria using a recursive expansion tree.
  • On HealthBench, Qworld covers 89% of expert-authored criteria and generates 79% novel criteria validated by human experts.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Rubric Rating

  • Evaluation mode is explicit

    No clear evaluation mode extracted.

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    Detected: HLE, Healthbench

  • Metric reporting is present

    No metric terms extracted.