arXiv (All)
open access
Genesis Steering: Better Activation Steering Through Training Data
Activation steering controls large language models at inference time, but its effectiveness depends on the choice of reference data. We introduce genesis steering, which derives a genesis vector from contrastive examples in the model's own fine-tuning data. When these data are unavailable, we draw o
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
- LocUS: Head Selection and Subspace Projection for Targeted Activation Steering#1105680
- Conflict-Aware Federated Fine-Tuning of Large Language Models with Mixture-of-Experts#280152
- IronLLM: Forging Compact Edge-Native Language Models for Real-Time Embodied Intelligence#1132061
- Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs#1141599
- Language Models Can Control Their Own Attention#924873
Record · ID 1344937
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