arXiv:2607. 07023v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) is often treated as a capability-adaptation step, while alignment is attributed to later preference optimization or reinforcement learning.
By Aoxiong Zeng, Yuxin Yang, Xiangquan Yang
Supervised fine-tuning (SFT) is often treated as a capability-adaptation step, while alignment is attributed to later preference optimization or reinforcement learning. This separation is incomplete: when examples are scored and kept online during fine-tuning, the choice of which data to train on already changes the model's behavioral preferences.
arXiv:2607. 16240v1 Announce Type: cross Abstract: Direct Alignment Algorithms (DAAs) such as DPO have become a common way to post-train and align LLMs with human preferences.
By Shawn Im, Federico Danieli, Skyler Seto, Barry-John Theobald, Katherine Metcalf
arXiv:2610. 41588v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) treats every reported comparison as correct, yet preference data contain reversed, tied or otherwise noisy comparisons.
By Bin Luo, Param Venkat Vivek Kesireddy, Anil Vallepu
arXiv:2510. 26707v2 Announce Type: replace-cross Abstract: As LLMs occupy an increasingly important role in society, they are more and more confronted with questions that require them not only to draw on their general knowledge but also to align with certain human value systems.
By Mehar Bhatia, Shravan Nayak, Gaurav Kamath, Marius Mosbach, Karolina Sta\'nczak, Vered Shwartz, Siva Reddy
arXiv:2606. 19744v1 Announce Type: cross Abstract: Aligning language models with human preferences often requires optimising multiple behavioural objectives.
By Pranav Bhandari, Nicolas Fay, Amitava Datta, Usman Naseem, Mehwish Nasim