Publications

2024

1. arXiv

   

   GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models

   Tao Zhang, Ziqian Zeng, Yuxiang Xiao, Huiping Zhuang, Cen Chen, James Foulds, and Shimei Pan

   arXiv preprint arXiv:2406.13925, 2024

   Abs Bib HTML Code

   Large Language Models (LLMs) are prone to generating content that exhibits gender biases, raising significant ethical concerns. Alignment, the process of fine-tuning LLMs to better align with desired behaviors, is recognized as an effective approach to mitigate gender biases. Although proprietary LLMs have made significant strides in mitigating gender bias, their alignment datasets are not publicly available. The commonly used and publicly available alignment dataset, HH-RLHF, still exhibits gender bias to some extent. There is a lack of publicly available alignment datasets specifically designed to address gender bias. Hence, we developed a new dataset named GenderAlign, aiming at mitigating a comprehensive set of gender biases in LLMs. This dataset comprises 8k single-turn dialogues, each paired with a "chosen" and a "rejected" response. Compared to the "rejected" responses, the "chosen" responses demonstrate lower levels of gender bias and higher quality. Furthermore, we categorized the gender biases in the "rejected" responses of GenderAlign into 4 principal categories. The experimental results show the effectiveness of GenderAlign in reducing gender bias in LLMs.

   @article{zhang2024genderalign,
     title = {GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models},
     author = {Zhang, Tao and Zeng, Ziqian and Xiao, Yuxiang and Zhuang, Huiping and Chen, Cen and Foulds, James and Pan, Shimei},
     journal = {arXiv preprint arXiv:2406.13925},
     year = {2024},
   }

2. LREC-COLING

   

   Zero-shot Event Detection Using a Textual Entailment Model as an Enhanced Annotator

   Ziqian Zeng, Runyu Wu, Yuxiang Xiao, Xiaoda Zhong, Hanlin Wang, Zhengdong Lu, and Huiping Zhuang

   In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), May 2024

   Abs Bib HTML PDF Code Poster Slides

   We treat the TE model as an annotator that can be enhanced. We propose to use TE models to annotate large-scale unlabeled text and use annotated data to finetune the TE model, yielding an improved TE model. Finally, the improved TE model is used for inference on the test set. To improve the efficiency, we propose to use keywords to filter out sentences with a low probability of expressing event(s). To improve the coverage of keywords, we expand limited number of seed keywords using WordNet, so that we can use the TE model to annotate unlabeled text efficiently. The experimental results show that our method can outperform other baselines by 15% on the ACE05 dataset.

   @inproceedings{zeng-etal-2024-zero,
     title = {Zero-shot Event Detection Using a Textual Entailment Model as an Enhanced Annotator},
     author = {Zeng, Ziqian and Wu, Runyu and Xiao, Yuxiang and Zhong, Xiaoda and Wang, Hanlin and Lu, Zhengdong and Zhuang, Huiping},
     editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen},
     booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
     month = may,
     year = {2024},
     address = {Torino, Italia},
     publisher = {ELRA and ICCL},
     pages = {17851--17857},
   }

2023

1. Biomimetics

   

   Lightweight soft robotic glove with whole-hand finger motion tracking for hand rehabilitation in virtual reality

   Fengguan Li, Jiahong Chen, Zhitao Zhou, Jiefeng Xie, Zishu Gao, Yuxiang Xiao, Pei Dai, Chanchan Xu, Xiaojie Wang, and Yitong Zhou

   Biomimetics, May 2023

   Abs Bib HTML PDF

   Soft robotic gloves have attracted significant interest in hand rehabilitation in the past decade. However, current solutions are still heavy and lack finger-state monitoring and versatile treatment options. To address this, we present a lightweight soft robotic glove actuated by twisted string actuators (TSA) that provides whole-hand finger motion tracking. We have developed a virtual reality environment for hand rehabilitation training, allowing users to interact with various virtual objects. Fifteen small inertial measurement units are placed on the glove to predict finger joint angles and track whole-hand finger motion. We performed TSA experiments to identify design and control rules, by understanding how their response varies with input load and voltages. Grasping experiments were conducted to determine the grasping force and range of motion. Finally, we showcase an application of the rehabilitation glove in a Unity-based VR interface, which can actuate the operator’s fingers to grasp different virtual objects.

   @article{li2023lightweight,
     title = {Lightweight soft robotic glove with whole-hand finger motion tracking for hand rehabilitation in virtual reality},
     author = {Li, Fengguan and Chen, Jiahong and Zhou, Zhitao and Xie, Jiefeng and Gao, Zishu and Xiao, Yuxiang and Dai, Pei and Xu, Chanchan and Wang, Xiaojie and Zhou, Yitong},
     journal = {Biomimetics},
     volume = {8},
     number = {5},
     pages = {425},
     year = {2023},
     publisher = {MDPI},
   }