Data-Efficient LLM Safety Alignment Guided by Interpretable Features
cs.CL, cs.AI
Submitted: 2026-11-12
Updated: 2026-11-12
Terminology
Sources
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- OR-Bench: An Over-Refusal Benchmark for Large Language Models
- Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders
- Measuring Massive Multitask Language Understanding
- Measuring Mathematical Problem Solving With the MATH Dataset
- STAR-1: Safer Alignment of Reasoning LLMs with 1K Data
- Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder
- FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data