1
Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs
微调LLM看似无害的数据集可能暗含意识形态泛化，这项研究揭示了隐藏风险。
arXiv:2607.14888v1 Announce Type: new Abstract: Finetuning language models on small, curated datasets is standard practice for adapting them to specif…