When Should an LLM Steering Edit Depend on the Input?
cs.AI
Submitted: 2026-11-03
Updated: 2026-11-03
Terminology
Sources
- Not All Language Model Features Are One-Dimensionally Linear
- $k$NN-Adapter: Efficient Domain Adaptation for Black-Box Language Models
- Discovering Language Model Behaviors with Model-Written Evaluations
- Steering Llama 2 via Contrastive Activation Addition
- Steering Language Models With Activation Engineering
- Representation Engineering: A Top-Down Approach to AI Transparency
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents