Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards

ICLR 2026 Conference Submission21636 Authors

Keywords: multi-objective alignment; process reward model

Abstract: Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single optimizeable objective. We seek to answer what it would take to simultaneously align a model across various domains spanning those with: verifiable rewards (mathematical accuracy), non-verifiable subjective preferences (human values), and complex interactive scenarios (multi-turn AI tutoring dialogues). Such multi-objective reinforcement learning setups are often plagued by the individual objectives being at odds with each other, resulting in inefficient training and little user control during inference. We propose a unified framework that: (i) standardizes {process reward model} (PRM) training across both verifiable and non-verifiable settings to better supervise models' chain-of-thought reasoning; (ii) performs {multi-objective alignment} by training the LLM with our $\textbf{M}$ulti-$\textbf{A}$ction-$\textbf{H}$ead $\textbf{DPO}$ (MAH-DPO) and a vectorized reward where the dimensions of the vector correspond to the various objectives instead of a single scalar; and (iii) demonstrates how such a system provides fine-grained inference-time user control. Experiments across math reasoning, value alignment, and multi-turn dialogue show that our framework improves performance across multiple objectives simultaneously, while minimizing cross-objective trade-offs and enabling flexible inference time user control.

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

Submission Number: 21636