arXiv (All)
open access
On Mitigation of Subliminal Learning in Large Language Models
Knowledge distillation can transmit unintended behavioral traits from a teacher model to a student through training data that appear semantically unrelated to those traits, a phenomenon known as subliminal learning. Although recent work has established this effect, its training dynamics and mitigati
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
- Verbalizing Subliminal Learning Effects Using Text Optimization#1123339
- Verbalizing Subliminal Learning Effects Using Text Optimization#919421
- Reproducing and Evaluating the Generalizability of Subliminal Learning in Open-Weight Models#1070076
- Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning#353114
- How to Backdoor Image Knowledge Distillation#984852
Record · ID 1036898
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