Paper recorded by Signals 4 on 2026-10-19 in cs.CL. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-19 on arXiv · recorded by Signals 4 on 2026-10-20
Category: cs.CL · 自然语言处理 · first seen 2026-10-20
Safety alignment for large language models (LLMs) is primarily performed during post-training, while recent work has also begun incorporating safety data into pre-training. Yet safety can degrade when later training no longer includes safety data, and gains in safety often come at the cost of general capability. This tension suggests that safety and general reasoning should not be treated as separ