←back to thread

Use Prolog to improve LLM's reasoning

(shchegrikovich.substack.com)
379 points shchegrikovich | 2 comments | 13 Oct 24 21:22 UTC | HN request time: 0.415s | source
Show context
gorkempacaci ◴[17 Oct 24 22:40 UTC] No.41874542[source]▶
The generated programs are only technically Prolog programs. They use CLPFD, which makes these constraint programs. Prolog programs are quite a bit more tricky with termination issues. I wouldn’t have nitpicked if it wasn’t in the title.

Also, the experiment method has some flaws. Problems are hand-picked out of a random subset of the full set. Why not run the full set?

replies(2): >>41875614 #>>41879313 #
1. YeGoblynQueenne ◴[18 Oct 24 13:33 UTC] No.41879313[source]▶
>> Why not run the full set?

Most likely cherry-picking. The approach is only going to work well in domains where Prolog is commonly used to write solutions to problems, like logical puzzles or constraint problems etc.

replies(1): >>41883717 #
2. gorkempacaci ◴[18 Oct 24 21:35 UTC] No.41883717[source]▶
Yeah probably.