.png){kind=icon}
Return
Pareto Multi-objective Alignment for Language Models
.png){kind=icon}
PRE
AI
DOI：10.1007/978-3-032-06078-5_15.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Large language models (LLMs) are increasingly deployed in real-world applications that require careful balancing of multiple, often conflicting, objectives, such as informativeness versus conciseness, or helpfulness versus creativity. However, current alignment methods, primarily based on reinforcement learning from human feedback (RLHF), optimize LLMs toward a single reward function, resulting in rigid behavior that fails to capture the complexity and diversity of human preferences. This limitation hinders the adaptability of LLMs to practical scenarios, making multi-objective alignment (MOA) a critical yet underexplored area. To bridge this gap, we propose PAreto Multi-Objective Alignment (PAMA), a principled and computationally efficient algorithm designed explicitly for MOA in LLMs. In contrast to computationally prohibitive gradient-based multi-objective optimization (MOO) methods, PAMA transforms multi-objective RLHF into a convex optimization problem with a closed-form solution, significantly enhancing scalability. Traditional gradient-based MOO approaches suffer from prohibitive O(n(2)d) complexity, where d represents the number of model parameters, typically in the billions for LLMs, rendering direct optimization infeasible. PAMA reduces this complexity to O(n) where n is the number of objectives, enabling optimization to be completed within milliseconds. We provide theoretical guarantees that PAMA converges to a Pareto stationary point, where no objective can be improved without degrading at least one other. Extensive experiments across language models ranging from 125M to 7B parameters demonstrate PAMA's robust and effective multi-objective alignment capabilities, consistently outperforming baseline methods, aligning with its theoretical advantages. PAMA provides a highly efficient solution to the MOA problem that was previously considered intractable, offering a practical and theoretically grounded approach to aligning LLMs with diverse human values, paving the way for versatile and adaptable real-world AI deployments.
Keywords:
Language Models
Multi-objective Alignment
Journal
M
IF:
0
Papers:
29
Citations:
0
Organization
Cited Papers
.png){kind=icon}
ShareSave
ShareSaveShareSave no more
no more