Does Context Compression Preserve Refusal Alignment?
cs.AI, cs.CL
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/ant-8/Context-Compression-Alignment
Terminology
Sources
- ARC-Encoder: learning compressed text representations for large language models
- Universal and Transferable Adversarial Attacks on Aligned Language Models
- Steering Language Models With Activation Engineering
- Programming Refusal with Conditional Activation Steering
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- The Llama 3 Herd of Models
- Mistral 7B
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