arXiv:2610.18638v1 Announce Type: new Abstract: Combining pretrained models is a common strategy for building AI systems, whether by aligning a vision encoder with a language model or merging fine-tu...
arXiv:2610.29110v1 Announce Type: cross Abstract: Merging different models into a single model is highly desirable for multi-task deployment, particularly in regulated domains like healthcare. In suc...
arXiv:2607. 18026v1 Announce Type: new Abstract: Can large language models with substantially different parameter spaces be merged by direct weighted averaging, without training or semantic alignment?
arXiv:2606. 27242v1 Announce Type: new Abstract: Training-free source selection for LLM families with shared vocabularies arises in scientific string domains such as SMILES, protein, and genomic sequences, where candidate corpora share a tokenizer but differ in prediction targets.
arXiv:2510. 17426v3 Announce Type: replace-cross Abstract: The "alignment tax" of post-training is typically framed as a drop in task accuracy.
arXiv:2607. 22676v1 Announce Type: new Abstract: Post-training is a key mechanism for adapting large language models to downstream tasks.
SIGMA is a self‑improving alignment framework that uses a model’s own reasoning to generate diverse alignment dilemma scenarios from a simple "Model Spec" and then fine‑tunes the model with self‑judged rewards. By performing spec‑guided task synthesis and rubric‑based reinforcement learning, SIGMA improves safety alignment in multi‑turn agentic settings, reducing harmfulness and misalignment scores while preserving general capability. The approach demonstrates that a model can autonomously strengthen its own safety reasoning without external supervision.
arXiv:2610.33483v1 Announce Type: cross Abstract: Model merging combines task-specific expert models into a single model without joint training on their original datasets, but often incurs a performa...
arXiv:2606. 12342v1 Announce Type: cross Abstract: Domain fine-tuning degrades the safety of large language models: fine-tuned specialists readily comply with harmful prompts framed in domain language.
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.
arXiv:2610.33495v1 Announce Type: new Abstract: Combining language models is usually done by averaging weights, which works only when the models share a common starting point. We ask whether five fro...
arXiv:2607. 16242v1 Announce Type: cross Abstract: Fine-Tuning-as-a-Service (FTaaS) platforms let users train large language models (LLMs) on customized tasks, but this pipeline could erode models' safety alignment.