BIRD: Behavior Induction via Representation-structure Distillation

ICLR 2026 Conference Submission14558 Authors

Keywords: Knowledge Distillation, AI Alignment, Weak-to-strong generalization

Abstract: Human-aligned deep learning models exhibit behaviors consistent with human values, such as robustness, safety, and fairness. Transferring these behavioral properties to models trained on different tasks or data distributions remains challenging: aligned behavior is easily forgotten during fine-tuning, and collecting task-specific data that preserves this behavior can be prohibitively costly. We introduce BIRD, a flexible framework for transferring aligned behavior by matching the internal representation structure of a student model to that of a teacher. Applied to out-of-distribution robustness in image classification, BIRD outperforms fine-tuning, transfer learning, and continual learning methods, improving robust accuracy by up to 18\% over the next strongest baseline. It remains effective even when the teacher is trained on a much simpler dataset and is $25\times$ smaller in parameter count than the student. In a large-scale study of over 400 teacher-student pairs, we show that three interpretable and computable properties of the teacher's representations explain up to 85\% of the variance in transfer success, offering practical guidance for teacher selection and design. We further show that BIRD generalizes beyond applications in vision by enhancing safety alignment in language models when paired with Direct Preference Optimization and improving weak-to-strong generalization when combined with soft-label distillation. BIRD turns small, well-aligned models into scalable alignment seeds, mitigating challenges from key bottlenecks in deploying safe AI systems.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 14558