AINeutralarXiv – CS AI · 10h ago6/10
🧠
On Distinguishing Capability Elicitation from Capability Creation in Post-Training: A Free-Energy Perspective
Researchers propose distinguishing between capability elicitation and capability creation in large language model post-training, arguing that the SFT vs. RL debate oversimplifies how models improve. The framework suggests post-training either reweights existing behaviors or expands what models can practically achieve, with significant implications for how AI development is understood and evaluated.