shchegrikovich
Re:Use Prolog to improve LLM's reasoning
on Friday October 18, 2024 @12:12PM (#41880757)
I have another example - just a few people believed that you can apply 'a simple next token prediction algorithm' and achieve what we know as LLM. From my perspective, in the past few years, we've tried a lot of different approaches to improve LLM reasoning; some of them were good, others not so good. We need to keep trying and researching. 'Prolog + LLM' is not the answer to all questions, but it looks like a good step to move us forward.
Re:Use Prolog to improve LLM's reasoning
on Friday October 18, 2024 @05:12AM (#41877620)
The draft version of this blog was called - 'Renaissance of Programming Languages'. With so much hidden gems we are re-discovering the full potential of formal languages.
Re:Use Prolog to improve LLM's reasoning
on Friday October 18, 2024 @03:10AM (#41877024)
Or something like Catala language - https://catala-lang.org/? Catala: A Programming Language for the Law - https://arxiv.org/abs/2103.03198
Re:Use Prolog to improve LLM's reasoning
on Friday October 18, 2024 @02:51AM (#41876957)
I agree; we can do much more with LLMs if we focus on declarative-style languages.
Re:Use Prolog to improve LLM's reasoning
on Friday October 18, 2024 @02:47AM (#41876931)
I discussed this a few weeks back. The idea is to take a Python dataset, as Python is the most popular language, and write a transpiler to Prolog with the help of llms. So, creating this synthetic dataset is not a huge problem.
Re:Use Prolog to improve LLM's reasoning
on Friday October 18, 2024 @02:44AM (#41876921)
I think another problem which we can try to solve with this approach is factual verification.
Re:Use Prolog to improve LLM's reasoning
on Friday October 18, 2024 @02:40AM (#41876898)
This is really cool!
Re:Use Prolog to improve LLM's reasoning
on Friday October 18, 2024 @02:36AM (#41876880)
Have you tried - https://www.minizinc.org/?