token-masking

Tag

Cards List
#token-masking

Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models

arXiv cs.AI · 2026-05-29 Cached

Proposes EKSFT, a selective fine-tuning method for large language models that masks tokens with high entropy or high KL divergence from a reference model, preserving pre-trained distribution while injecting task knowledge. Experiments on mathematical reasoning benchmarks show it outperforms standard SFT and improves subsequent RL fine-tuning.

0 favorites 0 likes
← Back to home

Submit Feedback