arXiv (All)
open access
When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-Tuning
Benign fine-tuning severely weakens the safety alignment of large language models (LLMs), so we study why refusal behavior is so fragile. While prior work often attributes this failure to gradient conflict, we propose a fundamentally different Fisher-geometric explanation: safety Fisher is low-rank,
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging#160867
- ALTSTEER: Selective Safety Steering for Moving Beyond Hard Refusals to Constructive Alternatives#799418
- ALTSTEER: Selective Safety Steering for Moving Beyond Hard Refusals to Constructive Alternatives#797995
- Laissez-Faire Harms: Algorithmic Biases in Generative Language Models#189183
- Laissez-Faire Harms: Algorithmic Biases in Generative Language Models#189133
Record · ID 821494
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive