Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning
cs.LG, cs.AI, cs.CY
Submitted: 2026-05-31
Updated: 2026-10-01
Terminology
Sources
- A General Language Assistant as a Laboratory for Alignment
- Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
- Training Verifiers to Solve Math Word Problems
- Assessing BERT's Syntactic Abilities
- The Llama 3 Herd of Models
- Narrow Fine-Tuning Erodes Safety Alignment in Vision-Language Agents
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
- Editing Models with Task Arithmetic
- Mistral 7B
- In-Training Defenses against Emergent Misalignment in Language Models
- LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B
- Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models
- Natural Emergent Misalignment from Reward Hacking in Production RL
- The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
- Large Language Models Often Know When They Are Being Evaluated
- The Linear Representation Hypothesis and the Geometry of Large Language Models
- Qwen2.5 Technical Report
- Convergent Linear Representations of 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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks