GEPA: Reflective prompt evolution can outperform reinforcement learning
arxiviq.substack.com
GEPA: Reflective prompt evolution can outperform reinforcement learning
1–10 of 26 posts
Re: GEPA: Reflective prompt evolution can outperform reinforcement learning
#2And then you use self-distillation to wire the improved prompts back into the LLM. Bam, free metacognitive skills.
Re: GEPA: Reflective prompt evolution can outperform reinforcement learning
#3anyone working on an dspy optimizer for this?
Re: GEPA: Reflective prompt evolution can outperform reinforcement learning
#4anyone working on an dspy optimizer for this?
they’ve already written one! see omar’s x account for details!
Re: GEPA: Reflective prompt evolution can outperform reinforcement learning
#5anyone working on an dspy optimizer for this?
This is a DSPy optimizer, built by the DSPy core team. Just wait for open sourcing.
Re: GEPA: Reflective prompt evolution can outperform reinforcement learning
#6And then you use self-distillation to wire the improved prompts back into the LLM. Bam, free metacognitive skills.
Self-distillation generally refers to training a smaller model, right? I suppose for full metacognition you would use it fine-tune the existing model based on its older self?
Re: GEPA: Reflective prompt evolution can outperform reinforcement learning
#7These models / nets / whatever are much "smarter" (loaded term) than we think, we just don't know how to plug-in properly yet.
"We are not interested in the fact that the brain has the consistency of cold porridge." — Alan Turing
Re: GEPA: Reflective prompt evolution can outperform reinforcement learning
#8These models / nets / whatever are much "smarter" (loaded term) than we think, we just don't know how to plug-in properly yet. "We are not interested in the fact that the brain has the consistency of cold porridge." — Alan Turing
This is not how science and engineering work and an arxiv should not be taken at face value.
Re: GEPA: Reflective prompt evolution can outperform reinforcement learning
#9And then you use self-distillation to wire the improved prompts back into the LLM. Bam, free metacognitive skills.
Self-distillation generally refers to training a smaller model, right? I suppose for full metacognition you would use it fine-tune the existing model based on its older self?
No, training a smaller model off a more capable larger model (or an ensemble of models) is the "usual" distillation.
"Self-distillation" refers to distilling from a model into a copy of itself. Which is of limited use - unless you can steer the teacher, and want the student to internalize that steering.
The reason for doing self-distillation here is that we have both access to a richer representation (logit stream), and want to capture a richer behavior - not the answers themselves, but better reasoning techniques that are downstream from better prompts.