Подписаться
Guangxuan Xu
Guangxuan Xu
IBM Research, T. J. Watson Research Center
Подтвержден адрес электронной почты в домене ibm.com - Главная страница
Название
Процитировано
Процитировано
Год
Data boost: Text data augmentation through reinforcement learning guided conditional generation
R Liu, G Xu, C Jia, W Ma, L Wang, S Vosoughi
EMNLP 2020, 2020
1172020
Mitigating Political Bias in Language Models through Reinforced Calibration
R Liu, C Jia, J Wei, G Xu, L Wang, S Vosoughi
Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 2021
1092021
On the safety of conversational models: Taxonomy, dataset, and benchmark
H Sun*, G Xu*, J Deng, J Cheng, C Zheng, H Zhou, N Peng, X Zhu, ...
ACL Findings 2022, 2021
742021
Quantifying and alleviating political bias in language models
R Liu, C Jia, J Wei, G Xu, S Vosoughi
Artificial Intelligence 304, 103654, 2022
672022
Can Model Compression Improve NLP Fairness
G Xu, Q Hu
https://arxiv.org/pdf/2201.08542.pdf, 2022
272022
Non-Parallel Text Style Transfer with Self-Parallel Supervision
R Liu, C Gao, C Jia, G Xu, S Vosoughi
ICLR 2022, 2022
132022
Enhanced Offensive Language Detection Through Data Augmentation
R Liu, G Xu, S Vosoughi
The International AAAI Conference on Web and Social Media, 2020
122020
Are Fairy Tales Fair? Analyzing Gender Bias in Temporal Narrative Event Chains of Children's Fairy Tales
PT Isaza, G Xu, A Oloko, Y Hou, N Peng, D Wang
ACL 2023, 2023
9*2023
EnDex: Evaluation of Dialogue Engagingness at Scale
G Xu, R Liu, F Harel-Canada, NR Chandra, N Peng
Findings of EMNLP 2022, https://arxiv.org/pdf/2210.12362.pdf, 2022
82022
BRAIn: Bayesian Reward-conditioned Amortized Inference for natural language generation from feedback
G Pandey, Y Nandwani, T Naseem, M Mishra, G Xu, D Raghu, S Joshi, ...
arXiv preprint arXiv:2402.02479, 2024
22024
NECE: Narrative Event Chain Extraction Toolkit
G Xu, PT Isaza, M Li, A Oloko, B Yao, A Adebiyi, Y Hou, N Peng, D Wang
arXiv preprint arXiv:2208.08063, 2022
22022
A Grounded Preference Model for LLM Alignment
T Naseem, G Xu, S Swaminathan, A Yehudai, S Chaudhury, R Florian, ...
Findings of the Association for Computational Linguistics ACL 2024, 151-162, 2024
12024
CDR: Customizable Density Ratios of Strong-over-weak LLMs for Preference Annotation
Guangxuan Xu, Kai Xu, Shivchander Sudalairaj, Hao Wang, Akash Srivastava
arXiv preprint arXiv:2411.02481, https://arxiv.org/pdf/2411.02481, 2024
2024
The Joint Training of Transition-Based AMR Parser
G Xu
University of California, Los Angeles, 2022
2022
В данный момент система не может выполнить эту операцию. Повторите попытку позднее.
Статьи 1–14