Perspective: LLM Evaluation at Scale�Metrics Beyond BLEU and ROUGE
Abstract
We propose evaluation metrics for large language models based on truthfulness, consistency, and latency-cost tradeoffs.
Cite this article
Desai, R. & Thomas, A. (2022). Perspective: LLM Evaluation at Scale�Metrics Beyond BLEU and ROUGE. Research Explorations in Global Knowledge & Technology (REGKT), 1 (11). Retrieved from https://regkt.com/article.php?id=663&slug=perspective-llm-evaluation-at-scale-beyond-bleu-rouge