
EF
Eric Frankel, Banghua Zhu, Sewoong Oh, Lillian J. Ratliff
· 1 min read
ResearcharXiv cs.LG
ABC-Align: Prediction-Powered Alignment with Adaptive Bias Control
arXiv:2609.34374v1 Announce Type: new
Abstract: 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 in a series of experiments on an increasing scale. Our code is available at https://github.com/SewoongLab/abc-align .
Original source
This story was published by arXiv cs.LG and written by Eric Frankel, Banghua Zhu, Sewoong Oh, Lillian J. Ratliff. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


