no code implementations • COLING 2022 • Xuantao Lu, Jingping Liu, Zhouhong Gu, Hanwen Tong, Chenhao Xie, Junyang Huang, Yanghua Xiao, Wenguang Wang
In this paper, we propose a scoring model to automatically learn a model-based reward, and an effective training strategy based on curriculum learning is further proposed to stabilize the training process.
1 code implementation • 20 Mar 2024 • Zhouhong Gu, Xiaoxuan Zhu, Haoran Guo, Lin Zhang, Yin Cai, Hao Shen, Jiangjie Chen, Zheyu Ye, Yifei Dai, Yan Gao, Yao Hu, Hongwei Feng, Yanghua Xiao
Language significantly influences the formation and evolution of Human emergent behavior, which is crucial in understanding collective intelligence within human societies.
no code implementations • 12 Mar 2024 • Jianchen Wang, Zhouhong Gu, Zhuozhi Xiong, Hongwei Feng, Yanghua Xiao
Large Language Models have revolutionized numerous tasks with their remarkable efficacy. However, the editing of these models, crucial for rectifying outdated or erroneous information, often leads to a complex issue known as the ripple effect in the hidden space.
no code implementations • 11 Jan 2024 • Xintao Wang, Zhouhong Gu, Jiaqing Liang, Dakuan Lu, Yanghua Xiao, Wei Wang
In this paper, we propose ConcEPT, which stands for Concept-Enhanced Pre-Training for language models, to infuse conceptual knowledge into PLMs.
2 code implementations • 17 Sep 2023 • Qianyu He, Jie Zeng, Wenhao Huang, Lina Chen, Jin Xiao, Qianxi He, Xunzhe Zhou, Lida Chen, Xintao Wang, Yuncheng Huang, Haoning Ye, Zihan Li, Shisong Chen, Yikai Zhang, Zhouhong Gu, Jiaqing Liang, Yanghua Xiao
To bridge this gap, we propose CELLO, a benchmark for evaluating LLMs' ability to follow complex instructions systematically.
no code implementations • 17 Aug 2023 • Xintao Wang, Qianwen Yang, Yongting Qiu, Jiaqing Liang, Qianyu He, Zhouhong Gu, Yanghua Xiao, Wei Wang
Large language models (LLMs) have demonstrated impressive impact in the field of natural language processing, but they still struggle with several issues regarding, such as completeness, timeliness, faithfulness and adaptability.
no code implementations • 11 Jul 2023 • Zhouhong Gu, Lin Zhang, Jiangjie Chen, Haoning Ye, Xiaoxuan Zhu, Zihan Li, Zheyu Ye, Yan Gao, Yao Hu, Yanghua Xiao, Hongwei Feng
We introduces the DetectBench, a reading comprehension dataset designed to assess a model's ability to jointly ability in key information detection and multi-hop reasoning when facing complex and implicit information.
2 code implementations • 9 Jun 2023 • Zhouhong Gu, Xiaoxuan Zhu, Haoning Ye, Lin Zhang, Jianchen Wang, Yixin Zhu, Sihang Jiang, Zhuozhi Xiong, Zihan Li, Weijie Wu, Qianyu He, Rui Xu, Wenhao Huang, Jingping Liu, Zili Wang, Shusen Wang, Weiguo Zheng, Hongwei Feng, Yanghua Xiao
New Natural Langauge Process~(NLP) benchmarks are urgently needed to align with the rapid development of large language models (LLMs).
no code implementations • 23 Apr 2023 • Zhouhong Gu, Xiaoxuan Zhu, Haoning Ye, Lin Zhang, Zhuozhi Xiong, Zihan Li, Qianyu He, Sihang Jiang, Hongwei Feng, Yanghua Xiao
Domain knowledge refers to the in-depth understanding, expertise, and familiarity with a specific subject, industry, field, or area of special interest.
no code implementations • 25 Mar 2023 • Zhouhong Gu, Sihang Jiang, Wenhao Huang, Jiaqing Liang, Hongwei Feng, Yanghua Xiao
The model's ability to understand synonymous expression is crucial in many kinds of downstream tasks.
no code implementations • 25 Mar 2023 • Zhouhong Gu, Sihang Jiang, Jingping Liu, Yanghua Xiao, Hongwei Feng, Zhixu Li, Jiaqing Liang, Jian Zhong
The previous methods suffer from low-efficiency since they waste much time when most of the new coming concepts are indeed noisy concepts.
1 code implementation • 28 Mar 2022 • Sijie Cheng, Zhouhong Gu, Bang Liu, Rui Xie, Wei Wu, Yanghua Xiao
Specifically, i) to fully exploit user behavioral information, we extract candidate hyponymy relations that match user interests from query-click concepts; ii) to enhance the semantic information of new concepts and better detect hyponymy relations, we model concepts and relations through both user-generated content and structural information in existing taxonomies and user click logs, by leveraging Pre-trained Language Models and Graph Neural Network combined with Contrastive Learning; iii) to reduce the cost of dataset construction and overcome data skews, we construct a high-quality and balanced training dataset from existing taxonomy with no supervision.