←back to thread

Use Prolog to improve LLM's reasoning

(shchegrikovich.substack.com)
232 points shchegrikovich | 7 comments | 13 Oct 24 21:22 UTC | HN request time: 1.402s | source | bottom
1. YeGoblynQueenne ◴[17 Oct 24 21:53 UTC] No.41874200[source]▶
That's not going to work. Garbage in - Garbage out is success-set equivalent to Garbage in - Prolog out.

Garbage is garbage and failure to reason is failure to reason no matter the language. If your LLM can't translate your problem to a Prolog program that solves your problem- Prolog can't solve your problem.

replies(3): >>41874322 #>>41875551 #>>41876345 #
2. Philpax ◴[17 Oct 24 22:10 UTC] No.41874322[source]▶
This is a shallow critique that does not engage with the core idea. Specifying the problem is not the same as solving the problem.
replies(1): >>41874902 #
3. YeGoblynQueenne ◴[17 Oct 24 23:34 UTC] No.41874902[source]▶
I've programmed in Prolog for ~13 years and my PhD thesis is in machine learning of Prolog programs. How deep would you like me to go?
replies(2): >>41875047 #>>41875563 #
4. Philpax ◴[17 Oct 24 23:58 UTC] No.41875047{3}[source]▶
As deep as is required to actually make your argument!
5. mountainriver ◴[18 Oct 24 01:27 UTC] No.41875551[source]▶
Agree, reasoning has to come from within the model. These are hacks that only work in specific use cases
6. MrLeap ◴[18 Oct 24 01:30 UTC] No.41875563{3}[source]▶
I'm excited for the possibility of an escalation after reading this.
7. OutOfHere ◴[18 Oct 24 04:29 UTC] No.41876345[source]▶
Why do you think that the LLM cannot translate the problem into a program? Granted, it has been said that the Curry or Mercury languages may be better than Prolog at times with their functional logic programming features. Ultimately it's best if the LLM has the freedom to decide what's best to use from what it knows.