OrigaMI: An LLM Serving System with First-Class Interpretability Apps
cs.AI
Submitted: 2026-06-11
Updated: 2026-11-09
Code: https://github.com/ZJU-REAL/EasySteer-vllm-v1
Project page: https://actionable-interpretability-guide.github.io/paper.pdf
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Universal Jailbreak Suffixes Are Strong Attention Hijackers
- NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals
- Toxicity Detection for Free
- Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models
- EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering
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