Papers2

#entropy dynamics

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger

Big language models can get stuck after fine-tuning because they become too sure of themselves, so normal training stops helping.

#weak-driven learning#logit mixing#weak agents

On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models

Intermediate

Shumin Wang, Yuexiang Xie et al.Feb 3arXiv

The paper builds a simple, math-light rule to predict whether training makes a language model more open-minded (higher entropy) or more sure of itself (lower entropy).

#reinforcement fine-tuning#entropy dynamics#GRPO