9 papers
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…
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…
MetaMoE: Diversity-Aware Proxy Selection for Privacy-Preserving Mixture-of-Experts Unification
Weisen Jiang, Shuhao Chen, Sinno Jialin Pan
Mixture-of-Experts (MoE) models scale capacity by combining specialized experts, but most existing approaches assume centralized access to training data. In practice, data are dist…
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…
MetaDefense: Defending Finetuning-based Jailbreak Attack Before and During Generation
Weisen Jiang, Sinno Jialin Pan
This paper introduces MetaDefense, a novel framework for defending against finetuning-based jailbreak attacks in large language models (LLMs). We observe that existing defense mech…
MTMamba++: Enhancing Multi-Task Dense Scene Understanding via Mamba-Based Decoders
Baijiong Lin, Weisen Jiang, Pengguang Chen +2
Multi-task dense scene understanding, which trains a model for multiple dense prediction tasks, has a wide range of application scenarios. Capturing long-range dependency and enhan…