An arXiv paper reports that fine-tuning GPT-4o, Gemini 2.5 Pro, and DeepSeek-V3.1 on summary-to-text expansion tasks increases verbatim reproduction of copyrighted books.
An introduction to Gradience, a tool that quantifies whether a LoRA rank setting is excessive using singular value decomposition. In experiments on Mistral-7B, halving the rank improved accuracy.
