Unfair and Unsafe: Everyday Bias Triggers Emergent Misalignment
cs.CL, cs.AI, cs.LG
Submitted: 2026-10-11
Updated: 2026-10-11
Code: https://github.com/alexmartiguiu/polite-stereotypes-em
Sources
- Lessons from the Trenches on Reproducible Evaluation of Language Models
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers
- Toy Models of Superposition
- Gemma 3 Technical Report
- Shifting the Gradient: Understanding How Defensive Training Methods Protect Language Model Integrity
- The Llama 3 Herd of Models
- Narrow Fine-Tuning Erodes Safety Alignment in Vision-Language Agents
- Reinforcement Learning Can Amplify Emergent Misalignment from Harmless Rewards
- Emergent Misalignment Is Not Magical
- Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning
- Intra-Fairness Dynamics: The Bias Spillover Effect in Targeted LLM Alignment
- The Unequal Influence of Bad Advice: Using Training Data Attribution to Modulate Emergent Misalignment
- Convergent Linear Representations of Emergent Misalignment
- Steering Language Models With Activation Engineering
- Model Organisms for Emergent Misalignment
- Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating
- Qwen2.5 Technical Report
- Instruction-Following Evaluation for Large Language Models
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering