arXiv (All)
open access
Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models
Steering vectors (SVs) offer a lightweight way to control large language models (LLMs) at inference time by shifting hidden activations, providing a practical middle ground between prompting and fine-tuning. Yet SVs can be unreliable in practice. Some concepts are unsteerable, and even when steering
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
- MetaSteer: Context-Conditioned, nonlinear Steering via Attention-Projection Adaptation#1143319
- GPTBIAS: A Comprehensive Framework for Evaluating Bias in Large Language Models#924392
- GPTBIAS: A Comprehensive Framework for Evaluating Bias in Large Language Models#920161
- Learning an Anchored Prompt Space for Continual Adaptation of Large Language Models#1116830
- Focusing Condition: Inference-Time Self-Contrastive Steering Elicits Better Conditional Text Embeddings in LLMs#1117015
Record · ID 1048568
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