AI RESEARCH
MGDA-Decoupled: Geometry-Aware Multi-Objective Optimisation for DPO-based LLM Alignment
arXiv CS.LG
•
ArXi:2604.20685v1 Announce Type: new Aligning large language models (LLMs) to desirable human values requires balancing multiple, potentially conflicting objectives such as helpfulness, truthfulness, and harmlessness, which presents a multi-objective optimisation challenge. Most alignment pipelines rely on a fixed scalarisation of these objectives, which can