陈想，男，南京航空航天大学计算机科学与技术学院研究员，入选江苏省科协青年人才托举工程、江苏青年科技人才“U35培育”对象，目前为模式分析与机器智能（工信部）重点实验室、南航百强科研团队成员。主要研究方向为大模型安全与可信人工智能、自然语言处理、知识图谱、空天具身智能等，近年来在人工智能领域顶级会议或期刊如NeurIPS、ICLR、IJCAI、ACL、EMNLP、NAACL、SIGIR、WWW、TASLP等发表学术论文50余篇，其中第一作者发表CCF/CAAI A类论文10余篇，Google Scholar引用4800余次，4篇论文入选Paper Digest评选的年度会议最具影响力论文之一，参与GitHub开源项目累计星标5千余次，曾获中国中文信息学会“博士学位论文激励计划”、江苏省信息技术应用学会青年科技奖、浙江大学优秀毕业生、阿里巴巴优秀学术实习生等荣誉。常年受邀担任ACL、NeurIPS、ICML、ICLR、TPAMI、TASLP、TNNLS、TKDD等相关会议或期刊的程序委员会委员和审稿人，以及ACL ARR、IJCAI、NeurIPS、ACM MM、ICLR等会议的高级程序委员/领域主席，主持国家自然科学基金青年项目、江苏省自然科学基金青年项目、CCF-滴滴盖亚学者科研基金、CAAI-华为MindSpore科研基金、全国重点实验室开放课题等项目。

团队目标明确：在大模型、自然语言处理、人工智能等领域顶级会议/顶刊持续产出高质量论文，同时推动技术在高价值场景中的落地。希望的学生特质：自驱力强、勇于探索、乐于沟通。课题组氛围融洽、定期组织团建活动，每周一对一直接指导，有明确的研究路线与顶会投稿规划，可推荐表现优异的同学去浙江大学/东南大学等海内外高校深造以及滴滴/蚂蚁/腾讯/美团等大厂实习，并鼓励参加各项国内外学术交流活动与专业竞赛。（在完成基本的科研和项目要求下支持研二下学期五月份开始的自由实习！）

    2027级硕士持续招募中，欢迎报考！（专硕&计科学硕）

课题组长期招收对大模型安全与可信人工智能（知识增强、幻觉治理、强化学习等）、自然语言处理、知识图谱、空天具身智能等领域感兴趣的研究生，同时也招收动手能力较强的校内大二本科生加入团队做大模型相关的大创/竞赛，若您符合上述要求且有意加入，烦请将个人简历发送至邮箱xiang_chen@nuaa.edu.cn，期待一起做出高质量的研究和应用工作！

主要获奖与荣誉

【1】 江苏省科协青年人才托举工程；

【2】江苏青年科技人才“U35培育”对象；

【3】中国中文信息学会“博士学位论文激励计划”；

【4】江苏省双创博士；

【5】江苏省信息技术应用学会青年科技奖；

【6】浙江大学优秀毕业生；

【7】阿里巴巴优秀学术实习生；

【8】2021年全国知识图谱与语义计算大会（CCKS 2021）, 最佳英文论文奖；

科研项目

【1】 国家自然科学基金青年项目："内外源知识协同驱动的多模态大模型幻觉治理方法研究"；

【2】江苏省自然科学基金青年项目："面向多模态大模型幻觉的层次化动态抑制方法"；

【3】计算机软件新技术全国重点实验室开放课题："大模型智能体幻觉治理与安全防御协同机制研究"；

【4】海洋精准感知技术全国重点实验室开放课题："知识增强的海洋具身大模型高效学习与稳健推理研究"；

【5】CCF-滴滴盖亚学者科研基金："以方案满足率为目标的基于LLM的Multi-Agent的强化学习"；

【6】CAAI-华为昇思MindSpore学术基金："基于MindSpore的动态自适应训推优化引擎研究"；

学术服务与兼职

【1】 Frontiers of Computer Science期刊（CCF-B），预备青年编委；

【2】The Knowledge Engineering Review期刊，青年编委；

【3】中国计算机学会自然语言处理专委会 委员；

【4】中国中文信息学会大模型与生成专委会 委员；

【5】中国中文信息学会语言与知识计算专委会 委员；

【6】中国中文信息学会青年工作委员会 委员；

【7】中国指挥与控制学会具身智能专委会 委员；

【8】中国人工智能学会机器学习专委会 通讯委员；

主要论文列表（^*: Equal Contribution, ^#: Corresponding Author. For more publications, you can visit Google Scholar to learn more. ）：

[26] Yadong Wang, Haodong Chen, Yu Tian, Chuanxing Geng, Dong Liang, Xiang Chen^#. Beyond Dense States: Sparse Transcoders as Causally Testable Operators for LLM Latent Reasoning, EMNLP 2026 (main conference). [CCF B]  NEW!

[25] Xianya Fang, Feiyang Ren, Xiang Chen^#, Yu Tian, Zhen Bi, Haiyang Yu, Sheng-Jun Huang. Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs, EMNLP 2026 (main conference). [CCF B]  NEW!

[24] Qinghong Yin, Yu Tian, Heming Yang, Xiang Chen, Xianlin Zhang, Yue Ming, Xueming Li, Yue Zhang. Rethinking Robust Adversarial Concept Erasure in Diffusion Models, ECCV 2026. [CCF B]  

[23] Qin-Wen Luo, Sheng Ren, Xiang Chen^#, Rui Liu, Jun Fang, Naiqiang Tan, Sheng-Jun Huang. Compress the Easy, Explore the Hard: Difficulty-aware Entropy Regularization for Efficient LLM Reasoning, KDD 2026. [CCF A] 

[22-1] Xinyi Zeng, Xue Yang, Jingyuan Zhang, Huanqian Yan, Xiang Chen, Kaiwen Wei, Hankun Kang, Yu Tian. SafeSteer: A Decoding-level Defense Mechanism for Multimodal Large Language Models, ACL 2026 (Findings).  

[22-2] Shaokai He, Kaiwen Wei, Xinyi Zeng, Xiang Chen, Xue Yang, Zhenyang Li, Jiang Zhong, Yu Tian. DiffER: Diffusion Entity-Relation Modeling for Reversal Curse in Diffusion Large Language Models, ACL 2026 (Findings).  

[22-3] Lifan Zheng, Xue Yang, Jiawei Chen, Chenyan Wu, Jingyuan Zhang, Fanheng Kong, Xinyi Zeng, Xiang Chen, Yu Tian. DPN-LE: Dual Personality Neuron Localization and Editing for Large Language Models, ACL 2026 (Findings).

[21] Shengtao Wen, Haodong Chen, Yadong Wang, Zhongying Pan, Xiang Chen^#, Yu Tian, Bo Qian, Dong Liang, Sheng-Jun Huang. MultiMedBench: A Scenario-Aware Benchmark for Evaluating Knowledge Editing in Medical VQA. AAAI 2026. [CCF A]  

[20] Dong Zhao, Yadong Wang, Xiang Chen^#, Chenxi Wang, Hongliang Dai, Chuanxing Geng, Shengzhong Zhang, Shaoyuan Li, Sheng-Jun Huang. Reflect then Learn: Active Prompting for Information Extraction Guided by Introspective Confusion. AAAI 2026. [CCF A]  

[19] Xiang Chen, Yixin Ou, Quan Feng, Lei Li, Piji Li, Haibo Ye, Sheng-Jun Huang, Shuofei Qiao, Shumin Deng, Huajun Chen, Ningyu Zhang. Retrieval-augmented Prompt Learning for Pre-trained Foundation Models. IEEE Transactions on Audio,Speech, and Language Processing (TASLP), 2025. [CCF B类期刊, 中科院1区]

[18] Changliang Xu, Yukun Kang, Quan Feng, Jinghua Hua, Piji Li, Feiran Wu, Hu Wei, Xiang Chen^#, Sheng-Jun Huang, Songcan Chen. ItemRAG: Retrieval-Augmented Generation with Item-based Knowledge Computing for E-commerce Product Question Answering. Big Data Mining and Analytics (BDMA), 2025. [CCF T1类期刊, 中科院1区]

[17] Yuxia Geng, Runkai Zhu, Jiaoyan Chen, Jintai Chen, Zhuo Chen, Xiang Chen^#, Can Xu, Yuxiang Wang, Xiaoliang Xu, Sheng-Jun Huang. Cross-composition Feature Disentanglement for Compositional Zero-shot Learning. ACL 2025 (Findings). 

[16] Shuofei Qiao, Zhisong Qiu, Baochang Ren, Xiaobin Wang, Xiangyuan Ru, Ningyu Zhang, Xiang Chen, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen. Agentic Knowledgeable Self-awareness. ACL 2025. [CCF A]

[15] Chenxi Wang*, Xiang Chen*,  Ningyu Zhang, et al. MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation, ICLR 2025. [CCF A]

[14] Shuofei Qiao, Runnan Fang, Ningyu Zhang, Yuqi Zhu, Xiang Chen, Shumin Deng, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen. Agent Planning with World Knowledge Model. NeurIPS 2024. [CCF A]

[13] Xiang Chen, Lei Li, Yuqi Zhu, Shumin Deng, Chuanqi Tan, Fei Huang, Luo Si, Ningyu Zhang, Huajun Chen. Sequence Labeling as Non-Autoregressive Dual-Query Set Generation, IEEE Transactions on Audio,Speech, and Language Processing (TASLP), 2024. [CCF B类期刊, 中科院1区]

[12] Xiang Chen, Chenxi Wang, Yida Xue, Ningyu Zhang, Xiaoyan Yang, Qiang Li, Yue Shen, Jinjie Gu, Huajun Chen. Unified Hallucination Detection for Multimodal Large Language Models. ACL 2024. [CCF A]

[11] Xiang Chen, Duanzheng Song, Honghao Gui, Chengxi Wang, Ningyu Zhang, Fei Huang, Chengfei Lv, Dan Zhang, Huajun Chen. FactCHD: Benchmarking Fact-Conflicting Hallucination Detection, IJCAI 2024. [CCF A]

[10] Xiang Chen, Jintian Zhang, Xiaohan Wang, Tongtong Wu, Shumin Deng, Yongheng Wang, Luo Si, Huajun Chen, Ningyu Zhang. Continual Multimodal Knowledge Graph Construction, IJCAI 2024. [CCF A]

[9] Xiang Chen, Lei Li, Qiaoshuo Fei, Ningyu Zhang, Chuanqi Tan, Yong Jiang, Fei Huang, Huajun Chen. One Model for All Domains: Collaborative Domain-Prefix Tuning for Cross-Domain NER, IJCAI 2023. [CCF A]

[8] Xiang Chen, Lei Li, Ningyu Zhang, Xiaozhuan Liang, Shumin Deng, Chuanqi Tan, Fei Huang, Luo Si, Huajun Chen. Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning, NeurIPS 2022 (Spotlight). [CCF A]

[7] Xiang Chen, Lei Li, Ningyu Zhang, Chuanqi Tan, Fei Huang, Luo Si, Huajun Chen. Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt Tuning, SIGIR 2022. [CCF A]

[6] Xiang Chen, Ningyu Zhang, Lei Li, Shumin Deng, Chuanqi Tan, Changliang Xu, Fei Huang, Luo Si, Huajun Chen. Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion, SIGIR 2022（Most Influential SIGIR'22 Papers）. [CCF A]

[5] Xiang Chen, Ningyu Zhang, Xin Xie, Shumin Deng, Yunzhi Yao, Chuanqi Tan, Fei Huang, Luo Si, Huajun Chen. Knowprompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction, WWW 2022 (Most Influential WWW'22 Papers）. [CCF A] 

[4] Xiang Chen, Ningyu Zhang, Lei Li, Yunzhi Yao, Shumin Deng, Chuanqi Tan, Fei Huang, Luo Si, Huajun Chen. Good Visual Guidance Makes A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction, NAACL 2022. [CCF B]

[3] Xiang Chen, Lei Li, Shumin Deng, Chuanqi Tan, Changliang Xu, Fei Huang, Luo Si, Huajun Chen, Ningyu Zhang. LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable Prompting, COLING 2022. [CCF B]

[2] Ningyu Zhang*, Xiang Chen*, Xin Xie, Shumin Deng, Chuanqi Tan, Mosha Chen, Fei Huang, Luo Si, Huajun Chen. Document-level Relation Extraction as Semantic Segmentation, IJCAI 2021 (Most Influential IJCAI'21 Papers）. [CCF A]

[1] Luoqiu Li*, Xiang Chen*, Hongbin Ye, Zhen Bi, Shumin Deng, Ningyu Zhang, Huajun Chen. On robustness and bias analysis of bert-based relation extraction. China Conference on Knowledge Graph and Semantic Computing (CCKS 2021) [Best Paper Award]

• 2020.9 -- 2024.6

  浙江大学       计算机科学与技术       博士研究生毕业       工学博士学位      导师：陈华钧教授

• 2023.11 -- 2024.6

  蚂蚁集团      智能引擎技术部      研究型实习生

• 2021.9 -- 2023.11

  阿里巴巴      达摩院/通义实验室      研究型实习生

• 2022.6 -- 至今

  青源会会员

• 2024.7 -- 至今

  中文信息学会青年工作委员会
  

• [1]大模型安全
• [2]多模态大模型
• [3]具身智能
• [4]自然语言处理