HELM: Revision history

From Rice Wiki

Diff selection: Mark the radio buttons of the revisions to compare and hit enter or the button at the bottom.
Legend: (cur) = difference with latest revision, (prev) = difference with preceding revision, m = minor edit.

19 June 2024

  • curprev 01:4401:44, 19 June 2024Rice talk contribs 280 bytes +280 Created page with "'''HELM''' (Holistic Evaluation of Language Models) is a benchmark for evaluating LLMs for dangers to the user. It checks LLM in many scenarios with many metrics for ethical concerns. Its goal is to be a standardized and holistic language model benchmark. Category:LLM" Tag: Visual edit