Difference-in-means activation directions detect and mitigate emergent misalignment from insecure code fine-tuning across four LLM families, with effective within-model steering but non-specific cross-model transfer.
BLOCK-EM: Preventing Emergent Misalignment via Latent Blocking
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Emergent misalignment can arise when a language model is fine-tuned on a narrowly scoped supervised objective: the model learns the target behavior, yet also develops undesirable out-of-domain behaviors. We investigate a mechanistic approach to preventing emergent misalignment by identifying a small set of internal features that reliably control the misaligned behavior and then discouraging the model from strengthening these features during fine-tuning. Across six fine-tuning domains, blocking (i.e., constraining) a fixed set of features achieves up to 95\% relative reduction in emergent misalignment with no degradation in model quality or target-task performance. We strengthen validity with disjoint selection/evaluation splits, multiple independent judges, multiple random seeds for key settings, quality metrics, and extensive ablations demonstrating that the reduction in misalignment is specific to the identified mechanism. We also characterize a limiting regime in which misalignment re-emerges under prolonged fine-tuning, present evidence consistent with rerouting through alternative features or layers, and evaluate modifications that partially restore the misalignment-blocking effect. Overall, our results show that targeted training-time constraints on internal mechanisms can mitigate emergent misalignment without degrading target-task performance.
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Sycophancy fine-tuning induces emergent misalignment in LLMs that Alignment Gating can reverse by learning to suppress unsafe representations with generalization from narrow to broad domains.
Emergent and subliminal misalignment in LLMs arise from data structure interactions and transfer via benign distillation data, with stronger effects under shared functional structure and on-policy settings.
citing papers explorer
-
Actionable Activation Directions for Detecting and Mitigating Emergent Misalignment Across Language Model Families
Difference-in-means activation directions detect and mitigate emergent misalignment from insecure code fine-tuning across four LLM families, with effective within-model steering but non-specific cross-model transfer.
-
Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating
Sycophancy fine-tuning induces emergent misalignment in LLMs that Alignment Gating can reverse by learning to suppress unsafe representations with generalization from narrow to broad domains.
-
Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer
Emergent and subliminal misalignment in LLMs arise from data structure interactions and transfer via benign distillation data, with stronger effects under shared functional structure and on-policy settings.