See it, Say it, Sorted: Mechanistic Diagnosis and Parameter-Space Mitigation of Emergent Misalignment in LLMs
cs.LG, cs.CL
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/WeiqiaoQUE/mechanistic-emergent-misalignment
Terminology
Sources
- Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment
- Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation
- Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
- Persona-Model Collapse in Emergent Misalignment
- DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
- Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers
- The Llama 3 Herd of Models
- Natural Emergent Misalignment from Reward Hacking in Production RL
- Assessing Domain-Level Susceptibility to Emergent Misalignment from Narrow Finetuning
- gpt-oss-120b & gpt-oss-20b Model Card
- Qwen2.5 Technical Report
- Gemma 3 Technical Report
- Model Organisms for Emergent Misalignment
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks