Hamel Husain

@hamelhusain

Q: Are similarity metrics useful for evaluating LLM outputs? A: Similar wording does not tell you whether an answer works for your application. Check specific failures. Similarity metrics can help with retrieval and output diversity. https://hamel.dev/blog/posts/evals-faq/are-similarity-metrics-bertscore-rouge-etc-useful-for-evaluating-llm-outputs.html
打开原帖#511482
  1. Industry

    Alexandr Wang: clearing my schedule today to give muse media training 😑
  2. Industry

    Clément Delangue: Super excited about this and I know weights are coming (https://huggi…
  3. Industry

    Aravind Srinivas: Perplexity wins on Hugging Face Decision Index (benchmark for decisio…