4 papers · 1 filter
Improve Student's Reasoning Generalizability through Cascading Decomposed CoTs Distillation
Chengwei Dai, Kun Li, Wei Zhou +1
Large language models (LLMs) exhibit enhanced reasoning at larger scales, driving efforts to distill these capabilities into smaller models via teacher-student learning. Previous w…
Beyond Imitation: Learning Key Reasoning Steps from Dual Chain-of-Thoughts in Reasoning Distillation
Chengwei Dai, Kun Li, Wei Zhou +1
As Large Language Models (LLMs) scale up and gain powerful Chain-of-Thoughts (CoTs) reasoning abilities, practical resource constraints drive efforts to distill these capabilities…
CT-GAT: Cross-Task Generative Adversarial Attack based on Transferability
Minxuan Lv, Chengwei Dai, Kun Li +2
Neural network models are vulnerable to adversarial examples, and adversarial transferability further increases the risk of adversarial attacks. Current methods based on transferab…
MeaeQ: Mount Model Extraction Attacks with Efficient Queries
Chengwei Dai, Minxuan Lv, Kun Li +1
We study model extraction attacks in natural language processing (NLP) where attackers aim to steal victim models by repeatedly querying the open Application Programming Interfaces…