conftrace_

llm-based judge

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

readability-controlled perturbation (1) stylistic perturbation (1) benchmark (1) replication (1) icml papers (1) rubrics (1) style perturbation (1) linguistic adaptability (1) health question answering (1) ai agent (1)

Papers

Evaluating Health Question Answering Under Readability-Controlled Style Perturbations EMNLP 2025 PaperBench: Evaluating AI’s Ability to Replicate AI Research ICML 2025