no code implementations • COLING 2022 • Mengru Wang, Jianming Zheng, Fei Cai, Taihua Shao, Honghui Chen
Specifically, DRK adopts a logic-aware inference module to ease the word-overlap confusion, which introduces a logic rule to constrain the inference process, thereby avoiding the adverse effect of shallow text features.
1 code implementation • 21 Mar 2024 • Mengru Wang, Ningyu Zhang, Ziwen Xu, Zekun Xi, Shumin Deng, Yunzhi Yao, Qishen Zhang, Linyi Yang, Jindong Wang, Huajun Chen
This paper investigates using knowledge editing techniques to detoxify Large Language Models (LLMs).
2 code implementations • 2 Jan 2024 • Ningyu Zhang, Yunzhi Yao, Bozhong Tian, Peng Wang, Shumin Deng, Mengru Wang, Zekun Xi, Shengyu Mao, Jintian Zhang, Yuansheng Ni, Siyuan Cheng, Ziwen Xu, Xin Xu, Jia-Chen Gu, Yong Jiang, Pengjun Xie, Fei Huang, Lei Liang, Zhiqiang Zhang, Xiaowei Zhu, Jun Zhou, Huajun Chen
In this paper, we first define the knowledge editing problem and then provide a comprehensive review of cutting-edge approaches.
Ranked #1 on knowledge editing on zsRE (using extra training data)
1 code implementation • 3 Oct 2023 • Zhoubo Li, Ningyu Zhang, Yunzhi Yao, Mengru Wang, Xi Chen, Huajun Chen
This paper pioneers the investigation into the potential pitfalls associated with knowledge editing for LLMs.
1 code implementation • 3 Oct 2023 • Shengyu Mao, Xiaohan Wang, Mengru Wang, Yong Jiang, Pengjun Xie, Fei Huang, Ningyu Zhang
This task seeks to adjust the models' responses to opinion-related questions on specified topics since an individual's personality often manifests in the form of their expressed opinions, thereby showcasing different personality traits.
2 code implementations • 14 Aug 2023 • Peng Wang, Ningyu Zhang, Bozhong Tian, Zekun Xi, Yunzhi Yao, Ziwen Xu, Mengru Wang, Shengyu Mao, Xiaohan Wang, Siyuan Cheng, Kangwei Liu, Yuansheng Ni, Guozhou Zheng, Huajun Chen
Large Language Models (LLMs) usually suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to outdated/noisy data.