Task Vectors Can Be Linearly Decomposed into Interpretable and Controllable Components
cs.LG, cs.CL
Submitted: 2026-10-30
Updated: 2026-10-30
Terminology
Sources
- BOReFT: Manifold Steering of Language Models for Black-box Optimization
- The Llama 3 Herd of Models
- Ebisu: Benchmarking Large Language Models in Japanese Finance
- Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs
- Larger language models do in-context learning differently
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning