I don’t understand why people seem to be attacking the “non-determinism” of LLMs. First, I think most people are confusing “probabilistic” with “non-deterministic” which have very distinct meanings in CS/ML. Non-deterministic typically entails following multiple paths at once. Consider regex matching with NFAs or even the particular view of a list as a monad. The only case where LLMs are “non-deterministic” is when using sampling algorithms like beam search where multiple paths are considered simultaneously. But most LLM usage being discussed doesn’t involve beam search.
But even if one assumes people mean “probabilistic”, that’s also an odd critique given how probabilistic software has pretty much eaten the world. Most of my career has been building reliable product using probabilistic models.
Finally, there’s nothing inherently probabilistic or non-deterministic about LLM generation, these are properties of the sampler applied. I did quite a lot of LLM benchmarking in recent years and almost always used greedy sampling both for performance (doing things like GSM8K strong benefits from choosing the maximum likely path) and reproducibility. You can absolutely set up LLM tools that have perfectly reproducible results.
LLMs have many issues but their probabilistic nature is not one of them.
But even if one assumes people mean “probabilistic”, that’s also an odd critique given how probabilistic software has pretty much eaten the world. Most of my career has been building reliable product using probabilistic models.
Finally, there’s nothing inherently probabilistic or non-deterministic about LLM generation, these are properties of the sampler applied. I did quite a lot of LLM benchmarking in recent years and almost always used greedy sampling both for performance (doing things like GSM8K strong benefits from choosing the maximum likely path) and reproducibility. You can absolutely set up LLM tools that have perfectly reproducible results. LLMs have many issues but their probabilistic nature is not one of them.