[논문리뷰] ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and JudgearXiv에 게시된 'ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge' 논문에 대한 자세한 리뷰입니다.#Review#LLM Evaluation#Rubric-based Benchmark#Professional Knowledge#Multi-domain Tasks#LLM-Judge Bias Mitigation#Cost Reduction#Reasoning Assessment#Open-weight Models2025년 10월 23일댓글 수 로딩 중