A proposed evaluation method for video captioning replaces BLEU and METEOR with Multiple-Choice Question Answering (MCQA), scoring captions by the percentage of video-grounded questions an LLM can ans…
LLM-as-a-Judge is a technique that uses a large language model to evaluate the output of another model, offering a scalable and explainable proxy for human preference. The approach was formalized in a…
A study on GPT-5.2's Spanish-Chinese journalistic translations found that translation theory-driven prompts improved quality under expert evaluation, with the brief-oriented prompt scoring highest (MQ…
Shrijith Venkatramana, building git-lrc, explains the evolution of LLM evaluation metrics from BLEU to BLEURT and COMET. BLEU, introduced in 2002, measures n-gram overlap and correlates with human jud…
A user training a T5 model asked for alternative metrics to Exact Match for evaluating text generation. Community members suggested ROUGE-1, ROUGE-2, and BLEU, and recommended Braintrust for running e…