CoMerge is a conflict‑driven preference optimization framework for merging multiple expert language models into a single multi‑task model without full retraining. It treats model merging as a preference optimization problem, using self‑supervised, conflict‑driven hard negative samples derived from naive merging defects to refine lightweight, tensor‑wise merging coefficients. Experiments show CoMerge achieves near‑perfect performance on MergeBench and improves instruction‑following and safety on Llama‑3.1‑8B‑Instruct while optimizing only 1,445 scalar coefficients.
By Mingjie Zheng, Zihao Chen, Wenqing Chen, Weile Yuan, Zhixuan Chu, Jianxing Yu, Zibin Zheng
CAMFT is a Conflict‑Aware Mergeable Fine‑Tuning method designed to make task adaptation efficient and merge‑aware for large language models. Unlike existing approaches that only resolve parameter conflicts after fine‑tuning, CAMFT shapes mergeability during training by guiding each task to update sparse coordinates with lower cross‑task conflict. Experiments show that CAMFT outperforms standard fine‑tuning baselines in multi‑task merging scenarios.
By Jingang Zhou, Haiyang Guo, Yuan Ma, Han Zhu, Xu-Yao Zhang
arXiv:2605. 20803v2 Announce Type: replace-cross Abstract: Continual learning (CL) aims to train models sequentially on multiple tasks while mitigating catastrophic forgetting of previously learned knowledge.
By Kei Hiroshima, Kento Uchida, Shinichi Shirakawa
arXiv:2608. 12842v1 Announce Type: new Abstract: Model merging has recently attracted significant attention as a promising paradigm for constructing unified multi-task models without requiring additional retraining.
By Yuchen Liu, Zongzhen Yang, Binhang Qi, Hailong Sun, Xiang Gao
arXiv:2512. 01461v2 Announce Type: replace Abstract: Model merging has emerged as a promising paradigm for enabling multi-task capabilities without additional training.
By Kuangpu Guo, Aijing Yu, Jian Liang, Yuhe Ding, Zilei Wang, Ran He, Tieniu Tan
arXiv:2606. 19549v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) makes it cheap to train many domain- and task-specific language model adapters, but whether two adapters can be merged is usually discovered only after both have been fully trained and evaluated.
By Lin Tang, Wei Zhang, Jing Li, Hongyu Chen, Ming Zhao, Yuxuan Wang
arXiv:2504.20106v4 Announce Type: replace
Abstract: Ensuring that large language models (LLMs) are both helpful and harmless is a critical challenge, as overly strict constraints can lead to excessiv...
By Ren-Wei Liang, Chin-Ting Hsu, Chan-Hung Yu, Saransh Agrawal, Shih-Cheng Huang, Chieh-Yen Lin, Shang-Tse Chen, Kuan-Hao Huang, Shao-Hua Sun
arXiv:2506. 14126v2 Announce Type: replace-cross Abstract: Modern deep learning is increasingly characterized by the use of open-weight foundation models that can be fine-tuned on specialized datasets.
By Stefan Horoi, Guy Wolf, Eugene Belilovsky, Gintare Karolina Dziugaite
arXiv:2509. 03647v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly serve as automated evaluators, yet they suffer from "self-preference bias": a tendency to favor their own outputs over those of other models.
By Dani Roytburg, Matthew Bozoukov, Matthew Nguyen, Jou Barzdukas, Simon Fu, Narmeen Oozeer
arXiv:2509. 23982v2 Announce Type: replace-cross Abstract: Preference alignment is a critical step in making Large Language Models (LLMs) useful and aligned with (human) preferences.
By Lucio La Cava, Andrea Tagarelli
GroupDPO introduces a memory‑efficient approach to group‑wise direct preference optimization for aligning large language models. By using first‑order linearization with per‑response coefficients, the method decouples samples during backpropagation, dramatically reducing peak memory usage and enabling scalable training with larger groups. Experiments in both offline and online settings show that leveraging multiple responses consistently outperforms single‑pair training, and adding a negative log‑likelihood term on positive responses is essential for performance gains and training stability.
By Jixuan Leng, Si Si, Hsiang-Fu Yu, Vinod Raman, Inderjit S. Dhillon
arXiv:2510. 05342v2 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) has emerged as a simple and effective method for aligning large language models.
By Hyung Gyu Rho