2 papers
cs.LG2025
Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment
Moxin Li, Yuantao Zhang, Wenjie Wang +4
Multi-Objective Alignment (MOA) aims to align LLMs' responses with multiple human preference objectives, with Direct Preference Optimization (DPO) emerging as a prominent approach.…
cs.CL2025
A Perplexity and Menger Curvature-Based Approach for Similarity Evaluation of Large Language Models
Yuantao Zhang, Zhankui Yang
The rise of Large Language Models (LLMs) has brought about concerns regarding copyright infringement and unethical practices in data and model usage. For instance, slight modificat…