Qwen-3

Five researchers posted a preprint describing SEAG, a framework that uses a small local model to replace sensitive entities with aliases before forwarding RAG queries to external large language models…

Researchers propose Moir, a method that estimates the preservation covariance directly from a language model's own decoding distribution to prevent capability erosion during knowledge editing. In test…

A study of Llama-3 and Qwen-3 models found that supervised fine-tuning (SFT) establishes a model's value system, while subsequent preference optimization algorithms do not significantly alter alignmen…