Optimization before Evaluation: Evaluation with Unoptimised Prompts Can be Misleading

Documenti analoghi

• Can Out-of-Distribution Evaluations Uncover Reliance on Shortcuts? A Case Study in Question Answering
  di: Štefánik, Michal, et al.
  Pubblicazione: (2025)
• RASP-Tuner: Retrieval-Augmented Soft Prompts for Context-Aware Black-Box Optimization in Non-Stationary Environments
  di: Pan, Enze
  Pubblicazione: (2026)
• Talk, Evaluate, Diagnose: User-aware Agent Evaluation with Automated Error Analysis
  di: Chong, Penny, et al.
  Pubblicazione: (2026)
• Tape: A Cellular Automata Benchmark for Evaluating Rule-Shift Generalization in Reinforcement Learning
  di: Pan, Enze
  Pubblicazione: (2026)
• OCR or Not? Rethinking Document Information Extraction in the MLLMs Era with Real-World Large-Scale Datasets
  di: Shen, Jiyuan, et al.
  Pubblicazione: (2026)