←back to thread

Use Prolog to improve LLM's reasoning

(shchegrikovich.substack.com)
379 points shchegrikovich | 4 comments | 13 Oct 24 21:22 UTC | HN request time: 1.331s | source
Show context
z5h ◴[17 Oct 24 21:07 UTC] No.41873798[source]▶
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/declares to be true. Even if AI writes code for us, we should expect to have it presented and manipulated as a logical formalism.

Now if someone cares to argue that some other language/compiler is better at generating more performant code on certain architectures, then that person can declare their arguments in a logical formalism (Prolog) and we can use Prolog to translate between language representations, compile, optimize, etc.

replies(11): >>41874164 #>>41874229 #>>41874594 #>>41874985 #>>41875196 #>>41875236 #>>41876524 #>>41876589 #>>41876880 #>>41878634 #>>41882848 #
larodi ◴[17 Oct 24 23:47 UTC] No.41874985[source]▶
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.
replies(3): >>41875037 #>>41875543 #>>41876509 #
bbor ◴[18 Oct 24 01:26 UTC] No.41875543[source]▶
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? ;)

replies(3): >>41875691 #>>41879003 #>>41893668 #
1. YeGoblynQueenne ◴[18 Oct 24 12:56 UTC] No.41879003[source]▶
Minsky is right. The "rift" between symbolic and sub-symbolic, or learning and reasoning has only impeded progress. The problem is it's very hard to be an expert on both at once, and it's getting harder and harder as more and more work is done on both.

Since you mentioned Hinton, he has worked hard to entrench the idea that symbolic AI failed. I was listening to a lecture he gave [1] and he went on and On and ON about how symbolic AI was a stupid idea and it was conclusively proved wrong by neural nets. He went on for so long bashing symbolic AI to the ground that at some point I started wondering whether he's deep down worried that there might be a resurgence of it right on time to address the limitations of neural nets with respect to reasoning, before he and his mates have the chance to figure out how to overcome it. Which, well, good luck with that.

_________________

[1] https://youtu.be/N1TEjTeQeg0?si=OIYY3wnDbi7rzJt3

replies(2): >>41887898 #>>41893704 #
2. infinite8s ◴[19 Oct 24 14:19 UTC] No.41887898[source]▶
Completely agree. The next revolution in AI will be the person who can successfully combine both symbolic and connectionist architectures.
3. larodi ◴[20 Oct 24 07:49 UTC] No.41893704[source]▶
You’d be astonished how correct is this. I know several top PHD ppl well versed in ML who openly admin they know nothing about SQL which implies they also know very little PROLOG and very likely are ignorant about everything that is grammars and state automata.

Top surprise was when my high school classmate who went on to win two gold medals in IoM and has been doing quant mathematics for finance more than 16years openly admitted he knew nothing about grammars and was like ‘is this useful at all…’. I was amazed how is this even possible. But it is - he went the probabilistic and symbolic way, I went the discret and graph way.

On the other side I’m completely oblivious of what people use complex analysis for, even though I know a little DSP, some electronics, even some nano opto-electronics, and also can explain Fourier Transform to people. Even though I know what dérivâtes, nabla and vector field is, I can’t put them to work for me…

Science is never done in isolation, and the whole LLM thing seems from another planet to many people cause it was devised in a ML silo and also enterprise silo.

replies(1): >>41894591 #
4. YeGoblynQueenne ◴[20 Oct 24 11:16 UTC] No.41894591[source]▶
>> You’d be astonished how correct is this.

No I know it first hand :)

I'm also not a cross-disciplinary expert, to be clear. When I say it's hard, it's because I find it hard! My strength is in discrete maths and logic. I can deal with continuous maths because I need to keep abreast with the latest statistical machine learning developments but I don't think I would ever be able to contribute directly to say neural networks research, unless I turned it into a logic-based approach (as has been done in the past). To be perfectly honest, if deep learning didn't happen to be the dominant approach to machine learning, which forces me to pay attention to it, I doubt I would have followed my own advice and looked far beyond my narrow band of expertise.

But, that's why we're supposed to have collaborations, right? I can pair up with an expert on neural nets and we can make something new together that's more than what we can each do on our own. In the process we can learn from each other. That stuff works, I've seen that, too, in practice. I'm working with some roboticists now and I've learned a hell lot about their discipline and hopefully they're learning something about mine. I am convinced that in order to make progress in AI we need broad and wide collaborations, and not just between symbolists and connectionists, but also between computer scientists and biologists, cognitive scientists, whoever has any idea about what we're trying to achieve. After all, a computer scientist can only tell you something about the "artificial" in "artificial intelligence". We study computation, not intelligence. If we're going to create artificial intelligence we need to collaborate with someone who understands what that is.

The hard part is to kick people out of their comfort zone and to convince them that the other experts are also, well, experts, and that they have useful knowledge and skills that can improve your own results. And seen from the other side of the coin, from my point of view, it's very difficult for me, as an early career researcher, to convince anyone that I have useful knowledge and skills and something to contribute. It takes time and you have to make your name somehow otherwise nobody will want to work with you. But that's how academia works.

It's just not a great mechanism to ensure knowledge is shared and reused, unfortunately.