2 papers
cs.LG2026
CBD: API-Only LLM Black-Box Unlearning through Controlled Behavioral Divergence
Zhiqiang Xie, Yijing Lin, Zhipeng Gao +1
Edge devices increasingly invoke large language models (LLMs) through API services for context aware edge intelligence, while edge generated data may be collected to improve LLMs a…
cs.AI2026
Learner-Tailored Program Repair: A Solution Generator with Iterative Edit-Driven Retrieval Enhancement
Zhenlong Dai, Zhuoluo Zhao, Hengning Wang +5
With the development of large language models (LLMs) in the field of programming, intelligent programming coaching systems have gained widespread attention. However, most research…