Paper recorded by Signals 4 on 2026-10-16 in cs.AI. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-16 on arXiv · recorded by Signals 4 on 2026-10-19
Category: cs.AI · 人工智能 · first seen 2026-10-19
Fine-tuning large language models (LLMs) can induce behaviors beyond those explicitly targeted. For example, training a model to respond more warmly can make it more sycophantic, and training it to write insecure code can cause broad misalignment on prompts unrelated to coding. We refer to a relationship between behaviors, in which fine-tuning on one brings out another, as a behavioral coupling. I