This repository accompanies the paper:

ABC-Align: Prediction-Powered Alignment with Adaptive Bias Control Eric Frankel, Banghua Zhu, Sewoong Oh, Lillian J. Ratliff University of Washington, Seattle

📄 arXiv: coming soon (placeholder)

Language model post-training is often bottlenecked by the need for human-collected preference data, which is expensive and difficult to scale. Reinforcement learning from AI feedback (RLAIF) style approaches that leverage pseudo labels offer an abundant alternative but introduce systematic biases that degrade downstream alignment. Recent general-purpose semi-supervised methods correct for teacher bias using a small set of human-labeled examples, but suffer from high variance especially when human annotations are scarce. To this end, we propose ABC-Align, leveraging abundant pseudo label signal to minimize variance and applying a lightweight, adaptive correction grounded in the human-labeled subset. The correction strength is tuned automatically during training using plug-in estimates of the relevant bias–variance quantities. On LLM alignment with RLHF, DPO, and GRPO where human feedback is scarce, we empirically demonstrate that ABC-Align achieves superior performance over prior semi-supervised baselines.

🚧 Code coming soon. The implementation for reproducing the experiments in the paper will be released here. Check back for updates.

A BibTeX entry will be added once the paper is available on arXiv.