跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 26 天前AI 評分63

《Follow the Gradient》提出以梯度追溯訓練資料中的安全性退化

Follow the Gradient: Tracing Safety Degradation Back to Training Data

AI 導讀

論文提出 SimpleLoRIF,以梯度對齊找出會削弱大語言模型安全性的微調指令資料,並據此建立移除梯度最貼近不安全回應的 20% 樣本的 SafeTulu。在 Qwen、Llama 和 Olmo 上以 SafeTulu 訓練,GCG 攻擊成功率最多下降 22%,同時大致保留甚至提升模型能力。

正文

Published on Oct 27

Authors:

,

,

,

,

Abstract

SimpleLoRIF uses gradient alignment to filter instruction data that silently degrades LLM safety, yielding a safer dataset that reduces adversarial success while preserving capabilities.

Fine-tuning Large Language Models (LLMs) on instruction data can quietly erode their safety, even when no training example looks harmful. Because this safety-degrading data looks benign, standard content filters struggle to catch it. We tackle this problem by developing SimpleLoRIF, a scalable gradient embedding method that identifies fine-tuning examples whose gradients align with unsafe behavior. By simplifying a low-rank attribution method and restricting backpropagation to the final four transformer blocks, SimpleLoRIF can embed datasets on the order of a million examples, boosting gradient attribution from a small-scale analysis tool into a practical filter for full post-training datasets. We first validate it on emergent misalignment, where we find that gradients can connect insecure-code training data to the broadly harmful behaviors that appear after fine-tuning, with AUC as high as 0.865 in the gradient space of misaligned models. We then use SimpleLoRIF to build SafeTulu, a version of Tulu 3 with the 20% of examples most gradient-aligned with unsafe responses removed. Training on SafeTulu reduces GCG attack success rate by up to 22% across Qwen, Llama, and Olmo, outperforming both LLM-as-a-judge and prior gradient-based filtering, while largely preserving or even improving capability. Finally, we analyzed the removed data and identify possibly under-studied sources of safety degradation, such as tool-execution failures and narrative arithmetic. We release SafeTulu along with a Hugging Face Space that lets researchers build their own customized versions of SafeTulu to fine-tune on, such as by changing the removal fraction or filtering only certain subsets.

View arXiv page View PDF Project page Add to collection

Get this paper in your agent:

hf papers read 2610.37481

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.37481 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.37481 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.37481 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co