arXiv:2606. 11201v1 Announce Type: cross Abstract: The wide deployment of LLMs has made model alignment necessary to make newly trained models safely and effectively respond to user instructions.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2510. 17426v3 Announce Type: replace-cross Abstract: The "alignment tax" of post-training is typically framed as a drop in task accuracy.
arXiv:2603. 07445v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data.
arXiv:2406. 01514v4 Announce Type: replace-cross Abstract: We introduce a training-free safety enhancement method for aligning large language models (LLMs) without the need for supervised fine-tuning or reinforcement learning from human feedback.
arXiv:2606. 03810v1 Announce Type: cross Abstract: Consistency training encourages a model to produce similar outputs across related inputs or sampling procedures.
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.
Domain fine-tuning degrades the safety of large language models: fine-tuned specialists readily comply with harmful prompts framed in domain language. Existing inference-time defenses that mix logits from a safe anchor model require both models to share a vocabulary, which rules them out for the cross-family specialists where safety is most degraded.