Automatic Evaluation of Attribution by Large Language Models — HN submission

Wed, 21 Feb 2024 15:27:36 GMT

How does one detect hallucinations?

Hallucinations are an interesting artifact of LLMs where the model tends to make up facts or generate outputs that are not factually correct. There are two broad approaches for detecting hallucinations: 1. Verify the correctness of the response against world knowledge (via Google/Bing search) 2. Verify the groundedness of the response against the information present in the retrieved context The 2nd approach is more interesting and useful as the majority of LLM applications have an RAG component, and we ideally want the LLM only to utilize the retrieved knowledge to generate the response.…

5 points; 2 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Automatic Evaluation of Attribution by Large Language Models · HackerPapers discussions

Automatic Evaluation of Attribution by Large Language Models — HN submission