Search Results for author:
Found 4 papers, 4 papers with code
Beyond Imitation: Learning Key Reasoning Steps from Dual Chain-of-Thoughts in Reasoning Distillation
Further analysis shows that EDIT can generate high-quality CoTs with more correct key reasoning steps.
Improve Student's Reasoning Generalizability through Cascading Decomposed CoTs Distillation
Specifically, by restructuring the training objectives -- removing the answer from outputs and concatenating the question with the rationale as input -- CasCoD's two-step learning process ensures that students focus on learning rationales without interference from the preset answers, thus improving reasoning generalizability.
CT-GAT: Cross-Task Generative Adversarial Attack based on Transferability
Neural network models are vulnerable to adversarial examples, and adversarial transferability further increases the risk of adversarial attacks.
MeaeQ: Mount Model Extraction Attacks with Efficient Queries
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 (APIs).
