Tzu-Heng Huang

Time To Impeach LLM-as-a-Judge: Programs are the Future of Evaluation

2025 · arXiv (Cornell University)

Large language models (LLMs) are widely used to evaluate the quality of LLM generations and responses, but this leads to significant challenges: high API costs, uncertain reliability, inflexible pipelines, and inherent biases. To address these, …