Not All Misalignment Is Alike: A Decomposed Benchmark for Emergent Misalignment
cs.LG
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/afonsofsdomingues/EMERGE
Terminology
Sources
- Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
- Position: Don't Just "Fix it in Post": A Science of AI Must Study Training Dynamics
- Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning
- Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
- Subliminal Learning: Language models transmit behavioral traits via hidden signals in data
- The Devil in the Details: Emergent Misalignment, Format and Coherence in Open-Weights LLMs
- Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers
- Re-Emergent Misalignment: How Narrow Fine-Tuning Erodes Safety Alignment in LLMs
- Position: Anthropomorphic Misalignment Research Needs Stronger Evidence
- ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection
- Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models
- In-Training Defenses against Emergent Misalignment in Language Models
- A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA
- FORTRESS: Frontier Risk Evaluation for National Security and Public Safety
- LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B
- HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models
- SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation
- The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
- TruthfulQA: Measuring How Models Mimic Human Falsehoods
- Ministral 3
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- 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