3 papers
cs.LG2026
SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance-Diversity Data Selection
Shuhao Chen, Weisen Jiang, Yeqi Gong +5
Fine-tuning large language models often undermines their safety alignment, a problem further amplified by harmful fine-tuning attacks in which adversarial data removes safeguards a…
cs.LG2026
RxEval: A Prescription-Level Benchmark for Evaluating LLM Medication Recommendation
Shuhao Chen, Weisen Jiang, Changmiao Wang +4
Inpatient medication recommendation requires clinicians to repeatedly select specific medications, doses, and routes as a patient's condition evolves. Existing benchmarks formulate…
cs.LG2025
Dual-Balancing for Multi-Task Learning
Baijiong Lin, Weisen Jiang, Feiyang Ye +6
Multi-task learning aims to learn multiple related tasks simultaneously and has achieved great success in various fields. However, the disparity in loss and gradient scales among t…