no code implementations • 4 Feb 2024 • Gaurav Pandey, Yatin Nandwani, Tahira Naseem, Mayank Mishra, Guangxuan Xu, Dinesh Raghu, Sachindra Joshi, Asim Munawar, Ramón Fernandez Astudillo
Following the success of Proximal Policy Optimization (PPO) for Reinforcement Learning from Human Feedback (RLHF), new techniques such as Sequence Likelihood Calibration (SLiC) and Direct Policy Optimization (DPO) have been proposed that are offline in nature and use rewards in an indirect manner.
no code implementations • 26 May 2023 • Paulina Toro Isaza, Guangxuan Xu, Akintoye Oloko, Yufang Hou, Nanyun Peng, Dakuo Wang
Social biases and stereotypes are embedded in our culture in part through their presence in our stories, as evidenced by the rich history of humanities and social science literature analyzing such biases in children stories.
1 code implementation • 22 Oct 2022 • Guangxuan Xu, Ruibo Liu, Fabrice Harel-Canada, Nischal Reddy Chandra, Nanyun Peng
We propose EnDex, the first human-reaction based model to evaluate dialogue engagingness.
no code implementations • 17 Aug 2022 • Guangxuan Xu, Paulina Toro Isaza, Moshi Li, Akintoye Oloko, Bingsheng Yao, Cassia Sanctos, Aminat Adebiyi, Yufang Hou, Nanyun Peng, Dakuo Wang
To understand a narrative, it is essential to comprehend the temporal event flows, especially those associated with main characters; however, this can be challenging with lengthy and unstructured narrative texts.
1 code implementation • ICLR 2022 • Ruibo Liu, Chongyang Gao, Chenyan Jia, Guangxuan Xu, Soroush Vosoughi
The performance of existing text style transfer models is severely limited by the non-parallel datasets on which the models are trained.
no code implementations • 21 Jan 2022 • Guangxuan Xu, Qingyuan Hu
Model compression techniques are receiving increasing attention; however, the effect of compression on model fairness is still under explored.
1 code implementation • Findings (ACL) 2022 • Hao Sun, Guangxuan Xu, Jiawen Deng, Jiale Cheng, Chujie Zheng, Hao Zhou, Nanyun Peng, Xiaoyan Zhu, Minlie Huang
We propose a taxonomy for dialogue safety specifically designed to capture unsafe behaviors in human-bot dialogue settings, with focuses on context-sensitive unsafety, which is under-explored in prior works.
no code implementations • 30 Apr 2021 • Ruibo Liu, Chenyan Jia, Jason Wei, Guangxuan Xu, Lili Wang, Soroush Vosoughi
Current large-scale language models can be politically biased as a result of the data they are trained on, potentially causing serious problems when they are deployed in real-world settings.
no code implementations • 5 Dec 2020 • Ruibo Liu, Guangxuan Xu, Soroush Vosoughi
In this work, we present Dager (Data Augmenter), a generation-based data augmentation method, that improves the performance of classification on imbalanced and low-resource data such as the offensive language dataset.
no code implementations • EMNLP 2020 • Ruibo Liu, Guangxuan Xu, Chenyan Jia, Weicheng Ma, Lili Wang, Soroush Vosoughi
For instance, Data Boost improves F1 for the three tasks by 8. 7% on average when given only 10% of the whole data for training.