Hu, Chengzhi

1. "My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models
   2024/02/22 by Xinpeng Wang, Bolei Ma, Wang, Xinpeng +13 · 18 citations
   Computer Science · #Topic Modeling #Natural Language Processing Techniques #Intelligent Tutoring Systems and Adaptive Learning
2. Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation
   2024/10/04 by Xinpeng Wang, Wang, Xinpeng, Chengzhi Hu +5 · 2 voices · 15 citations
   Computer Science · #Topic Modeling #cs.CL
3. Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Think
   2024/04/12 by Xinpeng Wang, Wang, Xinpeng, Chengzhi Hu +7 · 5 citations
   Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling