arXiv (All)
open access
Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations
Refusal on a safety benchmark does not reveal how stable that behavior will remain after model updates. Benign downstream fine-tuning can weaken refusal, yet behavioral evaluations typically expose this fragility only after an intervention. We introduce SKIN-DEEP, a geometric diagnostic that examine
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
- Hard Negatives Reveal What Easy Negatives Hide: Cross-Lingual Harmfulness Representations Degrade with Resource Tier Under Hard Negatives#1064302
- Apparent Psychological Profiles of Large Language Models are Largely a Measurement Artifact#290636
- A Fragility Spectrum for Recursive Language-Model Training#998701
- Refusal Localizes, the Damage Relocates: Safety Layers Under Few-Sample Fine-Tuning#1154943
- Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways#1144864
Record · ID 1156399
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