Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.05965 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918432283295744 |
|---|---|
| author | Tan, Renxuan Li, Rongpeng Zhao, Zhifeng Zhang, Honggang |
| author_facet | Tan, Renxuan Li, Rongpeng Zhao, Zhifeng Zhang, Honggang |
| contents | Transcending the single-preference paradigm, aligning LLMs with diverse human values is pivotal for robust deployment. Contemporary Multi-Objective Preference Alignment (MPA) approaches predominantly rely on static linear scalarization or rigid gradient projection to navigate these trade-offs. However, by enforcing strict conflict avoidance or simultaneous descent, these paradigms often prematurely converge to local stationary points. While mathematically stable, these points represent a conservative compromise where the model sacrifices potential global Pareto improvements to avoid transient local trade-offs. To break this deadlock, we propose Pareto-Lenient Consensus (PLC), a game-theoretic framework that reimagines alignment as a dynamic negotiation process. Unlike rigid approaches, PLC introduces consensus-driven lenient gradient rectification, which dynamically tolerates local degradation provided there is a sufficient dominant coalition surplus, thereby empowering the optimization trajectory to escape local suboptimal equilibrium and explore the distal Pareto-optimal frontier. Theoretical analysis validates PLC can facilitate stalemate escape and asymptotically converge to a Pareto consensus equilibrium. Moreover, extensive experiments show that PLC surpasses baselines in both fixed-preference alignment and global Pareto frontier quality. This work highlights the potential of negotiation-driven alignment as a promising avenue for MPA. Our codes are available at https://anonymous.4open.science/r/aaa-6BB8. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_05965 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Beyond Compromise: Pareto-Lenient Consensus for Efficient Multi-Preference LLM Alignment Tan, Renxuan Li, Rongpeng Zhao, Zhifeng Zhang, Honggang Artificial Intelligence Transcending the single-preference paradigm, aligning LLMs with diverse human values is pivotal for robust deployment. Contemporary Multi-Objective Preference Alignment (MPA) approaches predominantly rely on static linear scalarization or rigid gradient projection to navigate these trade-offs. However, by enforcing strict conflict avoidance or simultaneous descent, these paradigms often prematurely converge to local stationary points. While mathematically stable, these points represent a conservative compromise where the model sacrifices potential global Pareto improvements to avoid transient local trade-offs. To break this deadlock, we propose Pareto-Lenient Consensus (PLC), a game-theoretic framework that reimagines alignment as a dynamic negotiation process. Unlike rigid approaches, PLC introduces consensus-driven lenient gradient rectification, which dynamically tolerates local degradation provided there is a sufficient dominant coalition surplus, thereby empowering the optimization trajectory to escape local suboptimal equilibrium and explore the distal Pareto-optimal frontier. Theoretical analysis validates PLC can facilitate stalemate escape and asymptotically converge to a Pareto consensus equilibrium. Moreover, extensive experiments show that PLC surpasses baselines in both fixed-preference alignment and global Pareto frontier quality. This work highlights the potential of negotiation-driven alignment as a promising avenue for MPA. Our codes are available at https://anonymous.4open.science/r/aaa-6BB8. |
| title | Beyond Compromise: Pareto-Lenient Consensus for Efficient Multi-Preference LLM Alignment |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.05965 |