Nanyun Peng

发表

Mitigating Bias for Question Answering Models by Tracking Bias Influence

Tagyoung Chung, Jiun-Yu Kao, Mingyu Derek Ma, 2023, 2310.08795.

"Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters

Yixin Wan, Aparna Garimella, Kai-Wei Chang, 2023, ArXiv.

BOOST: Harnessing Black-Box Control to Boost Commonsense in LMs' Generation

Yufei Tian, Nanyun Peng, Felix Zhang, 2023, EMNLP.

Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks

Fan Yin, Di Wu, Po-Nien Kung, 2023, EMNLP.

On Prompt-Driven Safeguarding for Large Language Models

Fandong Meng, Chujie Zheng, Nanyun Peng, 2024, 2401.18018.

MacGyver: Are Large Language Models Creative Problem Solvers?

Lianhui Qin, R. L. Bras, Abhilasha Ravichander, 2023, ArXiv.

Model Editing Can Hurt General Abilities of Large Language Models

Jia-Chen Gu, Pan Lu, Zhen-Hua Ling, 2024, ArXiv.

DeepEdit: Knowledge Editing as Decoding with Constraints

Muhao Chen, Kai-Wei Chang, Nanyun Peng, 2024, ArXiv.

Evaluating Large Language Models on Controlled Generation Tasks

Yufei Tian, Nanyun Peng, Jiao Sun, 2023, EMNLP.

Weak-to-Strong Extrapolation Expedites Alignment

Chujie Zheng, Nanyun Peng, Ziqi Wang, 2024, ArXiv.

Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue

Jia-Chen Gu, Pan Lu, Zhen-Hua Ling, 2024, 2401.04700.

Medical Vision-Language Pre-Training for Brain Abnormalities

Zi-Yi Dou, Masoud Monajatipoor, Nanyun Peng, 2024, LREC.

LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning

Nanyun Peng, Yiwei Wang, Silin Meng, 2024, ArXiv.

Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems

Jieyu Zhao, Yixin Wan, Kai-Wei Chang, 2023, EMNLP.

Event Detection from Social Media for Epidemic Prediction

Tanmay Parekh, Kuan-Hao Huang, Kai-Wei Chang, 2024, NAACL.