ProofOfThought: LLM-based reasoning using Z3 theorem proving
1–10 of 182 posts
Re: ProofOfThought: LLM-based reasoning using Z3 theorem proving
#2This is an interesting approach.
My team has been prototyping something very similar with encoding business operations policies with LEAN. We have some internal knowledge bases (google docs / wiki pages) that we first convert to LEAN using LLMs.
Then we run the solver to verify consistency.
When a wiki page is changed, the process is run again and it's essentially a linter for process.
Can't say it moved beyond the prototyping stage though, since the LEAN conversion does require some engineers to look through it at least.
But a promising approach indeed, especially when you have a domain that requires tight legal / financial compliance.
Re: ProofOfThought: LLM-based reasoning using Z3 theorem proving
#3I always find it amazing how many people seem to fail to use current LLMs to the fullest, even though they apparently work with them in research settings. This benchmark pipeline simply calls the OpenAI API and then painstakingly tries to parse the raw text output into a structured json format, when in reality the OpenAI API has supported structured outputs for ages now. That already ensures your model generates schema compliant output without hallucinating keys at the inference level. Today all the major providers support this feature either directly or at least indirectly via function calling. And if you run open models, you can literally write arbitrary schema (i.e. not limited to json behind the scenes) adhering inference engines yourself with rather manageable effort. I'm constantly using this in my daily work and I'm always baffled when people tell me about their hallucination problems, because so many of them can be fixed trivially these days.
Re: ProofOfThought: LLM-based reasoning using Z3 theorem proving
#4The repo is sparse on the details unless you go digging, which perhaps makes sense if this is just meant as the artifact for the mentioned paper.
Unless I’m wrong, this is mainly an API for trying to get an LLM to generate a Z3 program which “logically” represents a real query, including known facts, inference rules, and goals. The “oversight” this introduces is in the ability to literally read the logical statement being evaluated to an answer, and running the solver to see if it holds or not.
The natural source of doubt is: who’s going to read a bunch of SMT rules manually and be able to accurately double-check them against real-world understanding? Who double checks the constants? What stops the LLM from accidentally (or deliberately, for achieving the goal) adding facts or rules that are unsound (both logically and from a real-world perspective)?
The paper reports a *51%* false positive rate on a logic benchmark! That’s shockingly high, and suggests the LLM is either bad at logical models or keeps creating unsoundnesses. Sadly, the evaluation is a bit thin on the ground about how this stacks up, and what causes it to fall short.
Re: ProofOfThought: LLM-based reasoning using Z3 theorem proving
#5This is proof of verifiable logic. Computers can not think so calling it proof of thought misrepresents what's actually happening.
Re: ProofOfThought: LLM-based reasoning using Z3 theorem proving
#6I always find it amazing how many people seem to fail to use current LLMs to the fullest, even though they apparently work with them in research settings. This benchmark pipeline simply calls the OpenAI API and then painstakingly tries to parse the raw text output into a structured json format, when in reality the OpenAI API has supported structured outputs for ages now. That already ensures your model generates sche…
I wouldn't find it amazing, there are so many new models, features, ways to use models that the minute you pause to take a deep dive into something specific, 43 other things have already passed by you.
Re: ProofOfThought: LLM-based reasoning using Z3 theorem proving
#7I always find it amazing how many people seem to fail to use current LLMs to the fullest, even though they apparently work with them in research settings. This benchmark pipeline simply calls the OpenAI API and then painstakingly tries to parse the raw text output into a structured json format, when in reality the OpenAI API has supported structured outputs for ages now. That already ensures your model generates sche…
yes this can also improve the said reasoning.
Re: ProofOfThought: LLM-based reasoning using Z3 theorem proving
#8This is a very interesting area of research. I did something similar a couple of years ago using logic and probabilistic logic inference engines to make sure conclusions followed from premises.
I also used agents to synthesize, formalize, and criticize domain knowledge. Obviously, it is not a silver bullet, but it does ensure some degree of correctness.
I think introducing some degree of symbolism and agents-as-a-judge is a promising way ahead, see e.g.: https://arxiv.org/abs/2410.10934
Re: ProofOfThought: LLM-based reasoning using Z3 theorem proving
#9I always find it amazing how many people seem to fail to use current LLMs to the fullest, even though they apparently work with them in research settings. This benchmark pipeline simply calls the OpenAI API and then painstakingly tries to parse the raw text output into a structured json format, when in reality the OpenAI API has supported structured outputs for ages now. That already ensures your model generates sche…
I wouldn't find it amazing, there are so many new models, features, ways to use models that the minute you pause to take a deep dive into something specific, 43 other things have already passed by you.
I would agree if you are a normal dev who doesn't work in the field. But even then reading the documentation once a year would have brought you insane benefits regarding this particular issue. And for ML researchers there is no excuse for stuff like that at this point.
Re: ProofOfThought: LLM-based reasoning using Z3 theorem proving
#10I always find it amazing how many people seem to fail to use current LLMs to the fullest, even though they apparently work with them in research settings. This benchmark pipeline simply calls the OpenAI API and then painstakingly tries to parse the raw text output into a structured json format, when in reality the OpenAI API has supported structured outputs for ages now. That already ensures your model generates sche…
yes this can also improve the said reasoning.
The secret the big companies don't want to tell you is that you can turn all their models into reasoning models that way. You even have full control over the reasoning process and can make it adhere to a specific format, e.g. the ones used in legal settings. I've built stuff like that using plain old gpt-4o and it was even better than the o series.