GitHub - manyoso/haltt4llm: This project is an attempt to create a common metric to test LLM's for progress in eliminating hallucinations which is the most serious current problem in widespread adoption of LLM's for many real purposes. - discu.eu

Hacker News

GPT4All outscores GPT-3.5 on new hallucination metric https://github.com/manyoso/haltt4llm 13 comments 30/3/2023

New metric for LLM hallucinations with results for GPT-3, GPT3-5 and Alpaca Lora https://github.com/manyoso/haltt4llm 3 comments 29/3/2023

Linking pages

Related searches:

Search whole site: site:github.com

Search title: GitHub - manyoso/haltt4llm: This project is an attempt to create a common metric to test LLM's for progress in eliminating hallucinations which is the most serious current problem in widespread adoption of LLM's for many real purposes.

See how to search.

Submit link to: