← Back to all news
arXiv Machine Learning By Qinghua Zhao, Xueling Gong, Xinyu Chen, Zhongfeng Kang, Xinlu Li

A Layer-wise Analysis of Supervised Fine-Tuning

Read the original on arXiv Machine Learning →

The paper investigates how supervised fine‑tuning (SFT) affects different layers of language models, finding that middle layers (20–80%) remain stable while the final layers are highly sensitive to changes. Using information‑theoretic, geometric, and optimization metrics across 1B‑32B models, the authors identify a depth‑dependent pattern and introduce Mid‑Block Efficient Tuning, which updates only the critical intermediate layers. Experiments show this method outperforms standard LoRA by up to 10.2 % on GSM8K (OLMo2‑7B) with lower parameter overhead, suggesting that alignment can be achieved with localized architectural changes.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Jun 5

Dominant-Layer ZO: A Single Layer Dominates Zeroth-Order Fine-Tuning of LLMs

arXiv:2606. 05516v1 Announce Type: new Abstract: Zeroth-order (ZO) optimization enables memory-efficient fine-tuning of large language models (LLMs) using only forward passes, but it remains unclear how useful adaptation is distributed across layers.

By Wanhao Yu, Ziyan Wang, Zheng Wang, Abeer Matar Almalky, Yihang Zuo, Shuteng Niu, Sen Lin, Adnan Siraj Rakin, Deliang Fan, Li Yang
llmsfine-tuningbenchmarks
More like this →
arXiv AI
4d ago

Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA

The paper investigates how memorization behaves during fine‑tuning of large language models with LoRA, a parameter‑efficient technique. It finds that LoRA fine‑tuning diverges from previous results seen in full fine‑tuning and pre‑training: factors like model size and data duplication no longer predict memorization in the same way. Using a relaxed similarity‑based metric, the authors show that LoRA substantially lowers memorization risk while preserving strong task performance.

By Fei Wang, Baochun Li
llmsfine-tuning
More like this →