←back to thread

Ask HN: Any insider takes on Yann LeCun's push against current architectures?

385 points vessenes | 1 comments | 10 Mar 25 19:41 UTC | HN request time: 0.001s | source

So, Lecun has been quite public saying that he believes LLMs will never fix hallucinations because, essentially, the token choice method at each step leads to runaway errors -- these can't be damped mathematically.

In exchange, he offers the idea that we should have something that is an 'energy minimization' architecture; as I understand it, this would have a concept of the 'energy' of an entire response, and training would try and minimize that.

Which is to say, I don't fully understand this. That said, I'm curious to hear what ML researchers think about Lecun's take, and if there's any engineering done around it. I can't find much after the release of ijepa from his group.

Show context
ActorNightly ◴[10 Mar 25 20:26 UTC] No.43325670[source]▶
Not an official ML researcher, but I do happen to understand this stuff.

The problem with LLMs is that the output is inherently stochastic - i.e there isn't a "I don't have enough information" option. This is due to the fact that LLMs are basically just giant look up maps with interpolation.

Energy minimization is more of an abstract approach to where you can use architectures that don't rely on things like differentiability. True AI won't be solely feedforward architectures like current LLMs. To give an answer, they will basically determine alogrithm on the fly that includes computation and search. To learn that algorithm (or algorithm parameters), at training time, you need something that doesn't rely on continuous values, but still converges to the right answer. So instead you assign a fitness score, like memory use or compute cycles, and differentiate based on that. This is basically how search works with genetic algorithms or PSO.

replies(10): >>43365410 #>>43366234 #>>43366675 #>>43366830 #>>43366868 #>>43366901 #>>43366902 #>>43366953 #>>43368585 #>>43368625 #
1. spmurrayzzz ◴[14 Mar 25 20:25 UTC] No.43366902[source]▶
> i.e there isn't a "I don't have enough information" option.

This is true in terms of default mode for LLMs, but there's a fair amount of research dedicated to the idea of training models to signal when they need grounding.

SelfRAG is an interesting, early example of this [1]. The basic idea is that the model is trained to first decide whether retrieval/grounding is necessary and then, if so, after retrieval it outputs certain "reflection" tokens to decide whether a passage is relevant to answer a user query, whether the passage is supported (or requires further grounding), and whether the passage is useful. A score is calculated from the reflection tokens.

The model then critiques itself further by generating a tree of candidate responses, and scoring them using a weighted sum of the score and the log probabilities of the generated candidate tokens.

We can probably quibble about the loaded terms used here like "self-reflection", but the idea that models can be trained to know when they don't have enough information isn't pure fantasy today.

[1] https://arxiv.org/abs/2310.11511

EDIT: I should also note that I generally do side with Lecun's stance on this, but not due to the "not enough information" canard. I think models learning from abstraction (i.e. JEPA, energy-based models) rather than memorization is the better path forward.