An Empirical Study of LLM-as-a-Judge: How Design Choices Impact Evaluation Reliability

Documenti analoghi

• Mining Hidden Thoughts from Texts: Evaluating Continual Pretraining with Synthetic Data for LLM Reasoning
  di: Ishibashi, Yoichi, et al.
  Pubblicazione: (2025)
• LaMDAgent: An Autonomous Framework for Post-Training Pipeline Optimization via LLM Agents
  di: Yano, Taro, et al.
  Pubblicazione: (2025)
• Can Large Language Models Invent Algorithms to Improve Themselves?: Algorithm Discovery for Recursive Self-Improvement through Reinforcement Learning
  di: Ishibashi, Yoichi, et al.
  Pubblicazione: (2024)
• Can a Crow Hatch a Falcon? Lineage Matters in Predicting Large Language Model Performance
  di: Tamura, Takuya, et al.
  Pubblicazione: (2025)
• Effective Harness Engineering for Algorithm Discovery with Coding Agents
  di: Ishibashi, Yoichi, et al.
  Pubblicazione: (2026)