Multi-Objective Alignment of Large Language Models Through Hypervolume Maximization
Multi-objective alignment from human feedback (MOAHF) in large language models (LLMs) is a challenging problem as human preferences are complex, multifaceted, and often conflicting. Recent works on MOAHF considered a-priori multi-objective optimization (MOO), where human preferences are known at training or inference time. In contrast, when human preferences are unknown or difficult to quantify, a natural approach is to cover the Pareto front by multiple diverse solutions. We propose an algorithm HaM for learning diverse LLM policies that maximizes their hypervolume. This is the first application of a-posteriori MOO to MOAHF. HaM is computationally and space efficient, and empirically superior across objectives such as harmlessness, helpfulness, humor, faithfulness, and hallucination, on various datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
HallucinationSimilar Papers 제목 키워드 기반
Unlocking Decoding-time Controllability: Gradient-Free Multi-Objective Alignment with Contrastive Prompts
The task of multi-objective alignment aims at balancing and controlling the different alignment objectives (e.g., helpfulness, harmlessness and honesty) of large language models to meet the personalized requirements of d…
MATO: Multi-objective Personalized Alignment with Test-time Optimization for Large Language Models
Aligning large language models (LLMs) with diverse and multifaceted user preferences is a fundamental challenge in personalized AI systems. Existing multi-objective alignment methods either rely on costly training or req…
MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models
Recent advancements in large language models (LLMs) focus on aligning to heterogeneous human expectations and values via multi-objective preference alignment. However, existing methods are dependent on the policy model p…
GPUIn-Context LearningPersonalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging
While Reinforcement Learning from Human Feedback (RLHF) aligns Large Language Models (LLMs) with general, aggregate human preferences, it is suboptimal for learning diverse, individual perspectives. In this work, we stud…
Language ModelingLanguage ModellingLarge Language ModelMulti-Objective Reinforcement Learning+2FIRM: Federated In-client Regularized Multi-objective Alignment for Large Language Models
Aligning Large Language Models (LLMs) with human values often involves balancing multiple, conflicting objectives such as helpfulness and harmlessness. Training these models is computationally intensive, and centralizing…
Federated Learning