1 code implementation • COLING 2022 • Lele Sha, Yuheng Li, Dragan Gasevic, Guanliang Chen
Pretrained Language Models (PLMs), though popular, have been diagnosed to encode bias against protected groups in the representations they learn, which may harm the prediction fairness of downstream models.
no code implementations • 6 Mar 2024 • Zijie Zeng, Shiqi Liu, Lele Sha, Zhuang Li, Kaixun Yang, Sannyuya Liu, Dragan Gašević, Guanliang Chen
Our empirical findings highlight (1) detecting AI-generated sentences in hybrid texts is overall a challenging task because (1. 1) human writers' selecting and even editing AI-generated sentences based on personal preferences adds difficulty in identifying the authorship of segments; (1. 2) the frequent change of authorship between neighboring sentences within the hybrid text creates difficulties for segment detectors in identifying authorship-consistent segments; (1. 3) the short length of text segments within hybrid texts provides limited stylistic cues for reliable authorship determination; (2) before embarking on the detection process, it is beneficial to assess the average length of segments within the hybrid text.
2 code implementations • 23 Jul 2023 • Zijie Zeng, Lele Sha, Yuheng Li, Kaixun Yang, Dragan Gašević, Guanliang Chen
Then we proposed a two-step approach where we (1) separated AI-generated content from human-written content during the encoder training process; and (2) calculated the distances between every two adjacent prototypes and assumed that the boundaries exist between the two adjacent prototypes that have the furthest distance from each other.
no code implementations • 17 Mar 2023 • Lixiang Yan, Lele Sha, Linxuan Zhao, Yuheng Li, Roberto Martinez-Maldonado, Guanliang Chen, Xinyu Li, Yueqiao Jin, Dragan Gašević
Educational technology innovations leveraging large language models (LLMs) have shown the potential to automate the laborious process of generating and analysing textual content.