DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning

· Source: Artificial Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Cybersecurity & Data Privacy · Depth: Expert, quick

Summary

DataShield is a novel method designed to efficiently identify safety-degrading samples within benign datasets used for fine-tuning large language models (LLMs). Existing methods often suffer from high computational costs and noise. DataShield's core intuition is that benign fine-tuning increases overall LLM response compliance. It quantifies each sample's contribution to this compliance behavior as a safety degradation score. Its core components include Compliance Vector Extraction and a Compliance-Aware Score (CAS) for optimal safety-critical layer identification. A Safety-degrading Sample Filtering component then quantifies the training data's projection shift along the compliance direction. Evaluations on Llama3-8B, Llama3.1-8B, and Qwen2.5-7B using Alpaca and Dolly datasets confirm its effectiveness. It identifies high-risk and low-risk data subsets. The research also notes that open-ended question answering often triggers safety degradation, leading to longer responses.

Key takeaway

ML engineers fine-tuning LLMs with benign instruction datasets should integrate data filtering methods like DataShield. This proactively identifies and mitigates safety degradation, ensuring model compliance by pinpointing high-risk samples before deployment. You should also prioritize safety reviews for open-ended question answering data, as it is more prone to triggering safety issues.

Key insights

DataShield efficiently identifies safety-degrading samples in benign LLM fine-tuning datasets by quantifying compliance behavior.

Principles

Method

DataShield extracts compliance vectors, uses a Compliance-Aware Score (CAS) to find the optimal safety-critical layer, then filters samples by quantifying projection shift along the compliance direction.

In practice

Topics

Code references

Best for: AI Engineer, NLP Engineer, Research Scientist, AI Scientist, Machine Learning Engineer, AI Security Engineer

Related on AIssential

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.