arXiv (OAI Expanded)
open access
Subliminal Learning as Trait-Direction Drift: A Mechanism and Targeted Control under SFT Distillation
Beyond intended capabilities, model distillation can transfer hidden traits from a teacher. A teacher biased by a system prompt can generate semantically clean training data, such as numeric sequences, that still causes a downstream student to inherit the hidden preference, a phenomenon known as sub
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
- Subliminal Learning as Trait-Direction Drift: A Mechanism and Targeted Control under SFT Distillation#924147
- Reproducing and Evaluating the Generalizability of Subliminal Learning in Open-Weight Models#1070076
- LEGO-OPD: Factorized Teacher Composition for Multimodal On-Policy Distillation#1154956
- From Description to Explanation: Why Altered States of Consciousness Research Needs More Than Phenomenology#85177
- Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts#2631
Record · ID 919916
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