Yuxin Jiang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Yuxin Jiang has a total of 56 co-authors. Here are the top co-authors by number of shared publications:
Lifeng Shang
6 shared publicationsLiangyou Li
Huawei Noah's Ark Lab
5 shared publications- Wei Wang
The Hong Kong University of Science and Technology ( Guangzhou
5 shared publications Xin Jiang
5 shared publicationsXingshan Zeng
Huawei Noah's Ark Lab
5 shared publications- Kam-Fai Wong
The Chinese University of Hong Kong
3 shared publications
Latest Publications
- Open Access
- 8 March 2025
- Published by Springer Nature in Journal of Nanobiotechnology
- Vol. 23 (1) , 1-21
Microenvironment-responsive NIR-IIb multifunctional nanozyme platform for bacterial imaging and specialized anti-anaerobic bacteria periodontal therapy
Periodontitis is a chronic inflammatory disease caused by plaque. In order to remove pathogens and promote tissue repair, the following steps need to be taken simultaneously: localizing the diseased area, improving the anaerobic microenvironment, as well as addressing the anti-inflammatory and osteogenic needs. This study aims to address these issues by developing a responsive near-infrared-IIb nanozyme system (DMUP), assembled from lanthanide-doped down-converted nanoparticles and multi-enzymatically active nanozyme. DMUP binds to bacterial membranes via the bacterial targeting peptide ubiquicidin29-41 (UBI29-41). Upon responding to the inflammatory microenvironment, it releases manganese (Mn) nanozyme and paeonol (Pae), and localized infected areas by fluorescent bacterial imaging in the near-infrared IIb (NIR-IIb) region. In particular, the released Mn nanozyme reacts with hydrogen peroxide in the inflammatory microenvironment to generate oxygen (O2) in situ, thereby improving the anoxic environment to inhibit anaerobic bacteria. On the other hand, as a metal oxide nanozyme, Mn nanozyme scavenges reactive oxygen species (ROS) by mimicking the cascade process of superoxide dismutase and catalase. The phenolic antioxidant Pae shifts macrophages from pro-inflammatory (M1-type) to anti-inflammatory (M2-type) through the Akt/mTOR pathway. It can synergize with Mn nanozyme to regulate the inflammatory microenvironment, thereby reducing inflammation, promoting osteogenic genes expression, and accelerating periodontal tissues regeneration.
- 8 March 2025
- Published by Springer Nature in Journal of Nanobiotechnology
- Vol. 23 (1) , 1-21
Open AccessMicroenvironment-responsive NIR-IIb multifunctional nanozyme platform for bacterial imaging and specialized anti-anaerobic bacteria periodontal therapy
Periodontitis is a chronic inflammatory disease caused by plaque. In order to remove pathogens and promote tissue repair, the following steps need to be taken simultaneously: localizing the diseased area, improving the anaerobic microenvironment, as well as addressing the anti-inflammatory and osteogenic needs. This study aims to address these issues by developing a responsive near-infrared-IIb nanozyme system (DMUP), assembled from lanthanide-doped down-converted nanoparticles and multi-enzymatically active nanozyme. DMUP binds to bacterial membranes via the bacterial targeting peptide ubiquicidin29-41 (UBI29-41). Upon responding to the inflammatory microenvironment, it releases manganese (Mn) nanozyme and paeonol (Pae), and localized infected areas by fluorescent bacterial imaging in the near-infrared IIb (NIR-IIb) region. In particular, the released Mn nanozyme reacts with hydrogen peroxide in the inflammatory microenvironment to generate oxygen (O2) in situ, thereby improving the anoxic environment to inhibit anaerobic bacteria. On the other hand, as a metal oxide nanozyme, Mn nanozyme scavenges reactive oxygen species (ROS) by mimicking the cascade process of superoxide dismutase and catalase. The phenolic antioxidant Pae shifts macrophages from pro-inflammatory (M1-type) to anti-inflammatory (M2-type) through the Akt/mTOR pathway. It can synergize with Mn nanozyme to regulate the inflammatory microenvironment, thereby reducing inflammation, promoting osteogenic genes expression, and accelerating periodontal tissues regeneration.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 6603-6618
Instruction-Tuning Data Synthesis from Scratch via Web Reconstruction
Yuxin Jiang, Yufei Wang, Chuhan Wu, Xinyi Dai, Yan Xu, Weinan Gan, Yasheng Wang, Xin Jiang, Lifeng Shang, Ruiming Tang, Wei Wang. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 6603-6618
Open AccessInstruction-Tuning Data Synthesis from Scratch via Web Reconstruction
Yuxin Jiang, Yufei Wang, Chuhan Wu, Xinyi Dai, Yan Xu, Weinan Gan, Yasheng Wang, Xin Jiang, Lifeng Shang, Ruiming Tang, Wei Wang. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- Open Access
MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models
Large language models (LLMs) are increasingly relied upon for complex multi-turn conversations across diverse real-world applications. However, existing benchmarks predominantly focus on single-turn evaluations, overlooking the models' capabilities in multi-turn interactions. To address this gap, we introduce MT-Eval, a comprehensive benchmark designed to evaluate multi-turn conversational abilities. By analyzing human-LLM conversations, we categorize interaction patterns into four types: recollection, expansion, refinement, and follow-up. We construct multi-turn queries for each category either by augmenting existing datasets or by creating new examples with GPT-4 to avoid data leakage. To study the factors impacting multi-turn abilities, we create single-turn versions of the 1170 multi-turn queries and compare performance. Our evaluation of 11 well-known LLMs shows that while closed-source models generally surpass open-source ones, certain open-source models exceed GPT-3.5-Turbo in specific tasks. We observe significant performance degradation in multi-turn settings compared to single-turn settings in most models, which is not correlated with the models' fundamental capabilities. Moreover, we identify the distance to relevant content and susceptibility to error propagation as the key factors influencing multi-turn performance. MT-Eval is released publicly to encourage future research towards more robust conversational models.
Open AccessMT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models
Large language models (LLMs) are increasingly relied upon for complex multi-turn conversations across diverse real-world applications. However, existing benchmarks predominantly focus on single-turn evaluations, overlooking the models' capabilities in multi-turn interactions. To address this gap, we introduce MT-Eval, a comprehensive benchmark designed to evaluate multi-turn conversational abilities. By analyzing human-LLM conversations, we categorize interaction patterns into four types: recollection, expansion, refinement, and follow-up. We construct multi-turn queries for each category either by augmenting existing datasets or by creating new examples with GPT-4 to avoid data leakage. To study the factors impacting multi-turn abilities, we create single-turn versions of the 1170 multi-turn queries and compare performance. Our evaluation of 11 well-known LLMs shows that while closed-source models generally surpass open-source ones, certain open-source models exceed GPT-3.5-Turbo in specific tasks. We observe significant performance degradation in multi-turn settings compared to single-turn settings in most models, which is not correlated with the models' fundamental capabilities. Moreover, we identify the distance to relevant content and susceptibility to error propagation as the key factors influencing multi-turn performance. MT-Eval is released publicly to encourage future research towards more robust conversational models.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 20153-20177
MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models
Wai-Chung Kwan, Xingshan Zeng, Yuxin Jiang, Yufei Wang, Liangyou Li, Lifeng Shang, Xin Jiang, Qun Liu, Kam-Fai Wong. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 20153-20177
Open AccessMT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models
Wai-Chung Kwan, Xingshan Zeng, Yuxin Jiang, Yufei Wang, Liangyou Li, Lifeng Shang, Xin Jiang, Qun Liu, Kam-Fai Wong. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 4689-4705
Learning to Edit: Aligning LLMs with Knowledge Editing
Yuxin Jiang, Yufei Wang, Chuhan Wu, Wanjun Zhong, Xingshan Zeng, Jiahui Gao, Liangyou Li, Xin Jiang, Lifeng Shang, Ruiming Tang, Qun Liu, Wei Wang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 4689-4705
Open AccessLearning to Edit: Aligning LLMs with Knowledge Editing
Yuxin Jiang, Yufei Wang, Chuhan Wu, Wanjun Zhong, Xingshan Zeng, Jiahui Gao, Liangyou Li, Xin Jiang, Lifeng Shang, Ruiming Tang, Qun Liu, Wei Wang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 15568-15592
M4LE: A Multi-Ability Multi-Range Multi-Task Multi-Domain Long-Context Evaluation Benchmark for Large Language Models
Wai-Chung Kwan, Xingshan Zeng, Yufei Wang, Yusen Sun, Liangyou Li, Yuxin Jiang, Lifeng Shang, Qun Liu, Kam-Fai Wong. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 15568-15592
Open AccessM4LE: A Multi-Ability Multi-Range Multi-Task Multi-Domain Long-Context Evaluation Benchmark for Large Language Models
Wai-Chung Kwan, Xingshan Zeng, Yufei Wang, Yusen Sun, Liangyou Li, Yuxin Jiang, Lifeng Shang, Qun Liu, Kam-Fai Wong. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- Top Cited PapersOpen Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 4667-4688
FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models
Yuxin Jiang, Yufei Wang, Xingshan Zeng, Wanjun Zhong, Liangyou Li, Fei Mi, Lifeng Shang, Xin Jiang, Qun Liu, Wei Wang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 4667-4688
Top Cited PapersOpen AccessFollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models
Yuxin Jiang, Yufei Wang, Xingshan Zeng, Wanjun Zhong, Liangyou Li, Fei Mi, Lifeng Shang, Xin Jiang, Qun Liu, Wei Wang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- Open Access
Global and Local Hierarchy-aware Contrastive Framework for Implicit Discourse Relation Recognition
Due to the absence of explicit connectives, implicit discourse relation recognition (IDRR) remains a challenging task in discourse analysis. The critical step for IDRR is to learn high-quality discourse relation representations between two arguments. Recent methods tend to integrate the whole hierarchical information of senses into discourse relation representations for multi-level sense recognition. Nevertheless, they insufficiently incorporate the static hierarchical structure containing all senses (defined as global hierarchy), and ignore the hierarchical sense label sequence corresponding to each instance (defined as local hierarchy). For the purpose of sufficiently exploiting global and local hierarchies of senses to learn better discourse relation representations, we propose a novel GlObal and Local Hierarchy-aware Contrastive Framework (GOLF), to model two kinds of hierarchies with the aid of multi-task learning and contrastive learning. Experimental results on PDTB 2.0 and PDTB 3.0 datasets demonstrate that our method remarkably outperforms current state-of-the-art models at all hierarchical levels. Our code is publicly available at https://github.com/YJiangcm/GOLF_for_IDRR
Open AccessGlobal and Local Hierarchy-aware Contrastive Framework for Implicit Discourse Relation Recognition
Due to the absence of explicit connectives, implicit discourse relation recognition (IDRR) remains a challenging task in discourse analysis. The critical step for IDRR is to learn high-quality discourse relation representations between two arguments. Recent methods tend to integrate the whole hierarchical information of senses into discourse relation representations for multi-level sense recognition. Nevertheless, they insufficiently incorporate the static hierarchical structure containing all senses (defined as global hierarchy), and ignore the hierarchical sense label sequence corresponding to each instance (defined as local hierarchy). For the purpose of sufficiently exploiting global and local hierarchies of senses to learn better discourse relation representations, we propose a novel GlObal and Local Hierarchy-aware Contrastive Framework (GOLF), to model two kinds of hierarchies with the aid of multi-task learning and contrastive learning. Experimental results on PDTB 2.0 and PDTB 3.0 datasets demonstrate that our method remarkably outperforms current state-of-the-art models at all hierarchical levels. Our code is publicly available at https://github.com/YJiangcm/GOLF_for_IDRR
- Open Access
Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning
Contrastive learning has been demonstrated to be effective in enhancing pre-trained language models (PLMs) to derive superior universal sentence embeddings. However, existing contrastive methods still have two limitations. Firstly, previous works may acquire poor performance under domain shift settings, thus hindering the application of sentence representations in practice. We attribute this low performance to the over-parameterization of PLMs with millions of parameters. To alleviate it, we propose PromCSE (Prompt-based Contrastive Learning for Sentence Embeddings), which only trains small-scale \emph{Soft Prompt} (i.e., a set of trainable vectors) while keeping PLMs fixed. Secondly, the commonly used NT-Xent loss function of contrastive learning does not fully exploit hard negatives in supervised learning settings. To this end, we propose to integrate an Energy-based Hinge loss to enhance the pairwise discriminative power, inspired by the connection between the NT-Xent loss and the Energy-based Learning paradigm. Empirical results on seven standard semantic textual similarity (STS) tasks and a domain-shifted STS task both show the effectiveness of our method compared with the current state-of-the-art sentence embedding models. Our code is publicly avaliable at https://github.com/YJiangcm/PromCSE
Open AccessImproved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning
Contrastive learning has been demonstrated to be effective in enhancing pre-trained language models (PLMs) to derive superior universal sentence embeddings. However, existing contrastive methods still have two limitations. Firstly, previous works may acquire poor performance under domain shift settings, thus hindering the application of sentence representations in practice. We attribute this low performance to the over-parameterization of PLMs with millions of parameters. To alleviate it, we propose PromCSE (Prompt-based Contrastive Learning for Sentence Embeddings), which only trains small-scale \emph{Soft Prompt} (i.e., a set of trainable vectors) while keeping PLMs fixed. Secondly, the commonly used NT-Xent loss function of contrastive learning does not fully exploit hard negatives in supervised learning settings. To this end, we propose to integrate an Energy-based Hinge loss to enhance the pairwise discriminative power, inspired by the connection between the NT-Xent loss and the Energy-based Learning paradigm. Empirical results on seven standard semantic textual similarity (STS) tasks and a domain-shifted STS task both show the effectiveness of our method compared with the current state-of-the-art sentence embedding models. Our code is publicly avaliable at https://github.com/YJiangcm/PromCSE
- 1 February 2022
- Vol. 44 (1) , 118-122
[Research Progress of Targeted Ultrasound Contrast Agent BR55].
BR55 is an ultrasound contrast agent targeting vascular endothelial growth factor receptor 2,which can be used to detect tumor neovascularization and improve the diagnostic accuracy.Overseas researchers have used BR55 for human ultrasound molecular imaging,which showed good safety and tolerance.We reviewed the research progress on BR55 applied in the evaluation of tumor neovascularization from the composition,characteristics,animal experiments,and clinical studies of BR55.
- 1 February 2022
- Vol. 44 (1) , 118-122
[Research Progress of Targeted Ultrasound Contrast Agent BR55].
BR55 is an ultrasound contrast agent targeting vascular endothelial growth factor receptor 2,which can be used to detect tumor neovascularization and improve the diagnostic accuracy.Overseas researchers have used BR55 for human ultrasound molecular imaging,which showed good safety and tolerance.We reviewed the research progress on BR55 applied in the evaluation of tumor neovascularization from the composition,characteristics,animal experiments,and clinical studies of BR55.