Follow the Features: SAE Feature-Guided Data-Efficient Instruction-Tuning of Large Language Models
cs.LG
Submitted: 2026-11-02
Updated: 2026-11-05
Terminology
Sources
- Enhancing Chat Language Models by Scaling High-quality Instructional Conversations
- Describing Differences in Image Sets with Natural Language
- Scaling and evaluating sparse autoencoders
- The Llama 3 Herd of Models
- LoRA: Low-Rank Adaptation of Large Language Models
- Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning
- Where Did It Go Wrong? Attributing Undesirable LLM Behaviors via Representation Gradient Tracing
- Aligning Instruction Tuning with Pre-training
- What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning
- Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
- Training language models to follow instructions with human feedback
- The Linear Representation Hypothesis and the Geometry of Large Language Models
- Improving Dictionary Learning with Gated Sparse Autoencoders
- Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders
- Layer by Layer: Uncovering Hidden Representations in Language Models
- Gemma 3 Technical Report
- Qwen3 Technical Report
- Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language Models
- Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder
- SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models
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