Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Use Prolog to improve LLM's reasoning

shchegrikovich.substack.com

Post reply on HN
Print view View original

41–50 of 158 posts

Re: Use Prolog to improve LLM's reasoning

#41

Post by burntcaramel »

larodi wrote: post #40
z5h wrote: post #14

i've come to appreciate, over the past 2 years of heavy Prolog use, that all coding should be (eventually) be done in Prolog. It's one of few languages that is simultaneously a standalone logical formalism, and a standalone representation of computation. (With caveats and exceptions, I know). So a Prolog program can stand in as a document of all facts, rules and relations that a person/organization understands/declar…

Been shouting here and many places for quite a while that CoT and all similar stuff eventually leads to logic programming. So happy I’m not crazy.

COT = Chain-of-Thought

https://arxiv.org/abs/2201.11903

Re: Use Prolog to improve LLM's reasoning

#42

Post by Philpax »

YeGoblynQueenne wrote: post #39
Philpax wrote: post #24

Earlier quoted context omitted.

This is a shallow critique that does not engage with the core idea. Specifying the problem is not the same as solving the problem.

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?

As deep as is required to actually make your argument!

Re: Use Prolog to improve LLM's reasoning

#43

Post by nsxwolf »

tomcam wrote: post #32
z5h wrote: post #14

i've come to appreciate, over the past 2 years of heavy Prolog use, that all coding should be (eventually) be done in Prolog. It's one of few languages that is simultaneously a standalone logical formalism, and a standalone representation of computation. (With caveats and exceptions, I know). So a Prolog program can stand in as a document of all facts, rules and relations that a person/organization understands/declar…

Is it your thought that for the average programmer Prolog is easier to read and maintain than say Go, C#, or Java?

I found it completely impenetrable in college for all but the simplest problems and I tried to re-read the textbook recently and I didn’t do much better.

Re: Use Prolog to improve LLM's reasoning

#44

Post by eru »

z5h wrote: post #14

i've come to appreciate, over the past 2 years of heavy Prolog use, that all coding should be (eventually) be done in Prolog. It's one of few languages that is simultaneously a standalone logical formalism, and a standalone representation of computation. (With caveats and exceptions, I know). So a Prolog program can stand in as a document of all facts, rules and relations that a person/organization understands/declar…

Prolog was a neat exercise, but for practical programming you might want to combine both logical and functional programming. I think 'Curry' does that.

Re: Use Prolog to improve LLM's reasoning

#45

Post by dmead »

johnnyjeans wrote: post #33
dmead wrote: post #20

Earlier quoted context omitted.

It's taken ages for anything from functional programming to penetrate general use. Do you think uptake of logic stuff will be any faster?

Prolog (and logic programming in general) is much older than you think. In fact, if we take modern functional programming to have been born with John Backus' Turing Award presentation[1], then it even predates it. Many advancements to functional programming were implemented on top of Prolog! Erlang's early versions were built on top of a Prolog-derived language who's name escapes me. It's the source of Erlang's unfam…

Did you just answer me with chatgpt?

Re: Use Prolog to improve LLM's reasoning

#46

Post by xelxebar »

z5h wrote: post #14

i've come to appreciate, over the past 2 years of heavy Prolog use, that all coding should be (eventually) be done in Prolog. It's one of few languages that is simultaneously a standalone logical formalism, and a standalone representation of computation. (With caveats and exceptions, I know). So a Prolog program can stand in as a document of all facts, rules and relations that a person/organization understands/declar…

> over the past 2 years of heavy Prolog use

Oh, cool. Mind if I pick your brain a bit?

Recently, there was an HN post[0] of a paper that makes a case against pure logic languages in favor of "functional logic" ones, which they exhibit with Curry[1]. The setup argument is that Prolog's specs backtracking, which strongly downlimits it from full SLD resolution, causing fatally sharp edges in real world usage.

Being fairly naive to the paradigm, my interpretation is that writing real Prolog programs involves carefully thinking about and controlling the resolution algorithm, which feels very different than straight knowledge declaration. I believe cut/0 is the go-to example. Is that your experience with Prolog in practice?

The real meat of the paper, however, is in its case that functional logic languages fully embed Prolog with almost 1-to-1 expressivity, while also providing more refined tools for externalizing knowledge about the intended search space of solutions.

Thoughts? How are you using Prolog, logic, or constraint programming? What languages and tooling in this arena do you reach for? What is some of your most hard-earned knowledge? Any lesser-known, but golden, websites, books, or materials you'd like to share?

Cheers!

[0]:https://news.ycombinator.com/item?id=41816545

[1]:https://www.curry-language.org/

Re: Use Prolog to improve LLM's reasoning

#47

Post by Avshalom »

cmrdporcupine wrote: post #23
z5h wrote: post #14

i've come to appreciate, over the past 2 years of heavy Prolog use, that all coding should be (eventually) be done in Prolog. It's one of few languages that is simultaneously a standalone logical formalism, and a standalone representation of computation. (With caveats and exceptions, I know). So a Prolog program can stand in as a document of all facts, rules and relations that a person/organization understands/declar…

So why Prolog in particular and not another logic language like Mercury or Oz/Mozart etc?

Probably because neither of them have much in the way or library or community support.

Re: Use Prolog to improve LLM's reasoning

#48

Post by bbor »

larodi wrote: post #40
z5h wrote: post #14

i've come to appreciate, over the past 2 years of heavy Prolog use, that all coding should be (eventually) be done in Prolog. It's one of few languages that is simultaneously a standalone logical formalism, and a standalone representation of computation. (With caveats and exceptions, I know). So a Prolog program can stand in as a document of all facts, rules and relations that a person/organization understands/declar…

Been shouting here and many places for quite a while that CoT and all similar stuff eventually leads to logic programming. So happy I’m not crazy.

You’re in good company — the most influential AI academic of all time, the cooky grandfather of AI who picked up right where (when!) Turing left off, the man hated by both camps yet somehow in charge of them, agrees with you. I’m talking about Marvin Minsky, of course. See: Logical vs. Analogical (Minsky, 1991) https://ojs.aaai.org/aimagazine/index.php/aimagazine/article...

  …the limitations of current machine intelligence largely stem from seeking unified theories or trying to repair the deficiencies of theoretically neat but conceptually impoverished ideological positions. 
  Our purely numeric connectionist networks are inherently deficient in abilities to reason well; our purely symbolic logical systems are inherently deficient in abilities to represent the all-important heuristic connections between things—the uncertain, approximate, and analogical links that we need for making new hypotheses. The versatility that we need can be found only in larger-scale architectures that can exploit and manage the advantages of several types of representations at the same time.
  Then, each can be used to overcome the deficiencies of the others. To accomplish this task, each formally neat type of knowledge representation or inference must be complemented with some scruffier kind of machinery that can embody the heuristic connections between the knowledge itself and what we hope to do with it.
He phrases it backwards here in comparison to what you’re talking about (probably because no one in their right mind would have predicted the feasibility of LLMs), but I think the parallel argument should be clear. Talking about “human reasoning” like Simon & Newell or LeCun & Hinton do in terms of one single paradigm is like talking about “human neurons”. There’s tons of different neuronal architectures at play in our brains, and only through the ad-hoc minimally-centralized combination of all of them do we find success.

Personally, I’m a big booster of the term Unified Artificial Intelligence (UAI) for this paradigm; isn’t it fetch? ;)

Re: Use Prolog to improve LLM's reasoning

#49

Post by hydrolox »

dmead wrote: post #45
johnnyjeans wrote: post #33

Earlier quoted context omitted.

Prolog (and logic programming in general) is much older than you think. In fact, if we take modern functional programming to have been born with John Backus' Turing Award presentation[1], then it even predates it. Many advancements to functional programming were implemented on top of Prolog! Erlang's early versions were built on top of a Prolog-derived language who's name escapes me. It's the source of Erlang's unfam…

Did you just answer me with chatgpt?

definitely not how chat gpt writes

Re: Use Prolog to improve LLM's reasoning

#50

Post by mountainriver »

YeGoblynQueenne wrote: post #22

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.

Agree, reasoning has to come from within the model. These are hacks that only work in specific use cases
Post reply on HN