Hacker News new | ask | show | jobs
by jimmySixDOF 568 days ago
> It seems like a willful denial of the complexity and ambiguity of natural language

There is a paper and set of work recently that uses a measurement of entropy on the set of returned logits to detect a "certainty" estimate for outputs and flag hallucinations. It is a lot more rigorous than the OP but like everything in this space needs further testing.
1 comments
fzzzy 568 days ago
I've been thinking a lot about whether this would work lately. Do you have a link?
link
jimmySixDOF 567 days ago
This group of conversations is what I was thinking of: https://x.com/seb_far/status/1803446067343556872 https://oatml.cs.ox.ac.uk/blog/2024/06/19/detecting_hallucin...

Some people in the Open Source community I think implemented it a few months ago as Shrek Entropy Sampeling and it got a pop in circulation (https://github.com/xjdr-alt/entropix)

best of luck!

link
fzzzy 566 days ago
Thank you very much. I found this last night when looking into some of the keywords you mentioned. Looks like some of the same authors you referenced. Exciting!

https://arxiv.org/abs/2406.15927

link