avatar

Guanhua CHEN

Tenure-track Assistant Professor in SUSTech

Biography

Here is Guanhua Chen (陈冠华). I am a tenure-track assistant professor in the Department of Statistics and Data Science in Southern University of Science and Technology (SUSTech). I received Ph.D. from the Department of Computer Science, The University of Hong Kong in 2022, under the supervision of Prof. Jia Pan and Prof. Wenping Wang. I obtained the Bachelor and Master degree from Tsinghua University in 2012 and 2014, respectively. I was a research intern in Microsoft Research Asia and Huawei Noah’s Ark Lab. Currently, I am an area chair of ACL, EMNLP and CCL, also the reviewer for top AI conferences and journal like ICML, NeurIPS, ICLR, ACL, EMNLP, NAACL, and TASLP. I was awarded as Microsoft Research Asia StarTrack Scholar in 2025. My research interests are natural language processing (NLP) and large language models (LLMs), especially LLM data synthesis, multimodal LLMs, and reasoning LLMs, etc.


Positions available: I am looking for self-motivated PostDoc/PhD/Master/visiting students to join our lab. If you are interested, please send me an email with your CV. For your reference, here are the latest information of the PhD and Master application process of this year. Currently, we have 16 RTX 4090 GPUs (24GB), 16 NVIDIA L40 GPUs (48GB), and 4 A100 GPUs (40GB) available for students. APIs of open-sourced/proprietary LLMs are also provided for students.

Publications

（* denotes corresponding author）

  • Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations

    • Peng Lai, Jianjie Zheng, Sijie Cheng, Yun Chen, Peng Li, Yang Liu, Guanhua Chen*.
    • In Proceedings of NeurIPS 2025 (CCF A, poster) [arxiv]

  • G2: Guided Generation for Enhanced Output Diversity in LLMs

    • Zhiwen Ruan, Yixia Li, Yefeng Liu, Yun Chen, Weihua Luo, Peng Li, Yang Liu, Guanhua Chen*.
    • In Proceedings of EMNLP 2025 (CCF B, long paper in main conference)

  • Pi-SQL: Enhancing Text-to-SQL with Fine-Grained Guidance from Pivot Programming Languages

    • Yongdong Chi, Hanqing Wang, Yun Chen, Yan Yang, Jian Yang, Zonghan Yang, Xiao Yan, Guanhua Chen*. [arxiv]
    • In Findings of EMNLP 2025 (long paper)

  • ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs

    • Yan Yang, Yixia Li, Hongru Wang, Xuetao Wei, James Jianqiao Yu, Yun Chen, Guanhua Chen*.
    • In Proceedings of ACL 2025 (CCF A, long paper in main conference) [pdf] [code]

  • PlanGPT: Enhancing Urban Planning with Tailored Language Model and Efficient Retrieval

    • He Zhu, Guanhua Chen*，Wenjia Zhang*.
    • In Proceedings of ACL 2025 (industry track) (CCF A, oral, long paper) [pdf]

  • Fanno: Augmenting High-Quality Instruction Data with Open-Sourced LLMs Only

    • He Zhu, Yifan Ding, Yicheng Tao, Zhiwen Ruan, Yixia Li, Wenjia Zhang, Yun Chen, Guanhua Chen*.
    • In Findings of ACL 2025 (long paper) [pdf] [code]

  • Tag-Instruct: Controlled Instruction Complexity Enhancement through Structure-based Augmentation

    • He Zhu, Zhiwen Ruan, Junyou Su, Xingwei He, Yun Chen, Wenjia Zhang*, Guanhua Chen*.
    • In Findings of ACL 2025 (long paper) [pdf] [code]

  • MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning

    • Hanqing Wang, Yixia Li, Shuo Wang, Guanhua Chen*, Yun Chen*.
    • In Proceedings of NAACL 2025 (CCF B, long paper in main conference) [pdf] [code]

  • SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters

    • Yan Yang, Zeguan Xiao, Xin Lu, Hongru Wang, Xuetao Wei, Hailiang Huang, Guanhua Chen*, Yun Chen*.
    • In Proceedings of NAACL 2025 (CCF B, long paper in main conference) [pdf] [code]

  • Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions

    • Hongru Wang, Boyang Xue, Baohang Zhou, Tianhua Zhang, Cunxiang Wang, Huimin Wang, Guanhua Chen*, Kam-Fai Wong*
    • In Proceedings of NAACL 2025 (CCF B, long paper in main conference) [pdf]

  • LayAlign: Enhancing Multilingual Reasoning in LLMs via Layer-Wise Adaptive Fusion and Alignment Strategy

    • Zhiwen Ruan, Yixia Li, He Zhu, Longyue Wang, Weihua Luo, Kaifu Zhang, Yun Chen, Guanhua Chen*.
    • In Findings of NAACL 2025 (long paper) [pdf] [code]

  • SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation

    • Yixia Li, Boya Xiong, Guanhua Chen*, Yun Chen*
    • In Proceedings of NeurIPS 2024 (CCF A, long paper) [pdf] [code]

  • Distract Large Language Models for Automatic Jailbreak Attack

    • Zeguan Xiao, Yan Yang, Guanhua Chen*, Yun Chen*
    • In Proceedings of EMNLP 2024 (CCF B, long paper in main conference) [pdf]

  • PACIT: Unlocking the Power of Examples for Better In-Context Instruction Tuning

    • Tianci Xue, Ziqi Wang, Yixia Li, Yun Chen, Guanhua Chen*
    • In Findings of ACL 2024 (long paper) [pdf] [code]

  • mCLIP: Multilingual CLIP via Cross-lingual Transfer

    • Guanhua Chen, Lu Hou, Yun Chen, Wenliang Dai, Lifeng Shang, Xin Jiang, Qun Liu, Jia Pan, Wenping Wang
    • In Proceedings of ACL 2023 (CCF A, long paper in main conference, oral) [pdf] [code]

  • XLM-D: Decorate Cross-lingual Pre-training Model as Non-Autoregressive Neural Machine Translation

    • Yong Wang, Shilin He, Guanhua Chen*, Yun Chen, Daxin Jiang*.
    • In Proceedings of EMNLP 2022 (CCF B, long paper in main conference) [pdf]

  • Multilingual Sentence Transformer as A Multilingual Word Aligner

    • Weikang Wang†, Guanhua Chen†, Hanqing Wang, Yue Han, Yun Chen.
    • In Findings of EMNLP 2022 (CCF B, short paper) [pdf] [code]

  • Towards Making the Most of Cross-Lingual Transfer for Zero-Shot Neural Machine Translation

    • Guanhua Chen, Shuming Ma, Yun Chen, Dongdong Zhang, Jia Pan, Wenping Wang, Furu Wei
    • In Proceedings of ACL 2022 (CCF A, long paper in main conference) [pdf] [code]

  • Zero-shot Cross-lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoders

    • Guanhua Chen, Shuming Ma, Yun Chen, Li Dong, Dongdong Zhang, Jia Pan, Wenping Wang, Furu Wei
    • In Proceedings of EMNLP 2021 (CCF B, long paper in main conference, oral) [pdf] [code]

  • Lexically Constrained Neural Machine Translation with Explicit Alignment Guidance

    • Guanhua Chen, Yun Chen, Victor O.K. Li
    • In Proceedings of AAAI 2021 (CCF A, long paper) [pdf] [code]

  • Lexical-Constraint-Aware Neural Machine Translation via Data Augmentation

    • Guanhua Chen, Yun Chen, Yong Wang, Victor O.K. Li
    • In Proceedings of IJCAI 2020 (CCF A, long paper) [pdf] [code]

  • PlanGPT-VL: Enhancing Urban Planning with Domain-Specific Vision-Language Models

    • He Zhu, Junyou Su, Minxin Chen, Wen Wang, Yijie Deng, Guanhua Chen, Wenjia Zhang
    • In Proceedings of EMNLP 2025 (industry track) (CCF B, poster)

  • Alleviating Hallucinations in Large Language Models through Multi-Model Contrastive Decoding and Dynamic Hallucination Detection

    • Chenyu Zhu, YEFENG LIU, Hao Zhang, Aowen Wang, Yangxue, Guanhua Chen, Longyue Wang, Weihua Luo, Kaifu Zhang
    • In Proceedings of NeurIPS 2025 (CCF A, poster)

  • A Joint Learning of Force Feedback of Robotic Manipulation and Textual Cues for Granular Materials Classification

    • Zeqing Zhang, Guanqi Chen, Peng Zhou, Wentao Chen, Ruixing Jia, Guanhua Chen, Liangjun Zhang, Jia Pan
    • IEEE Robotics and Automation Letters (2025). [paper]

  • LLMs Trust Humans More, That’s a Problem! Unveiling and Mitigating the Authority Bias in Retrieval-Augmented Generation

    • Yuxuan LI, Xinwei Guo, Jiashi Gao, Guanhua Chen, Xiangyu Zhao, Jiaxin Zhang, Quanying Liu, Haiyan Wu, Xin Yao, Xuetao Wei.
    • In Proceedings of ACL 2025 (CCF A, long paper in main conference) [paper]

  • The Elephant in the Room: Exploring the Role of Neutral Words in Language Model Group-Agnostic Debiasing

    • Xinwei Guo, Jiashi Gao, Junlei Zhou, Jiaxin Zhang, Guanhua Chen, Xiangyu Zhao, Quanying Liu, Haiyan Wu, Xin Yao, Xuetao Wei.
    • In Findings of ACL 2025 (long paper) [paper]

  • Understanding Particles from Video: Property Estimation of Granular Materials via Visuo-Haptic Learning

    • Zeqing Zhang, Guangze Zheng, Xuebo Ji, Guanqi Chen, Ruixing Jia, Wentao Chen, Guanhua Chen, Liangjun Zhang, Jia Pan
    • IEEE Robotics and Automation Letters (2025). [paper]

  • StyleBART: Decorate Pretrained Model with Style Adapters for Unsupervised Stylistic Headline Generation

    • Hanqing Wang, Yajing Luo, Boya Xiong, Guanhua Chen, Yun Chen
    • In Findings of EMNLP 2023 (long paper) [pdf] [code]

  • Evaluating Explanation Methods for Vision-and-Language Navigation

    • Guanqi Chen, Lei Yang, Guanhua Chen, Jia Pan
    • In Proceedings of ECAI 2023 (CCF B, long paper in main conference) [pdf]

  • Accurate Word Alignment Induction from Neural Machine Translation

    • Yun Chen, Yang Liu, Guanhua Chen, Xin Jiang, Qun Liu
    • In Proceedings of EMNLP 2020 (CCF B, long paper in main conference, oral) [pdf] [code]

Working Papers

（all are corresponding authored papers）

  • Anchored Supervised Fine-Tuning

  • Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks

  • Enhancing Delta Compression in LLMs via SVD-based Quantization Error Minimization

  • Automatic Robustness Stress Testing of LLMs as Mathematical Problem Solvers

  • Towards Bridging the Reward-Generation Gap in Direct Alignment Algorithms

  • Enhancing Uncertainty Estimation in LLMs with Expectation of Aggregated Internal Belief

  • CompoundQA: A Benchmark for Evaluating LLMs on Compound Questions

Teaching

  • Undergraduate course STA323: Big Data Analysis Software and Application (Hadoop or Spark)
  • Graduate course STA5007: Advanced Natural Language Processing

Group Members

  • PhD candidates: Yunpeng Sun(SLAI,2025), Zhiwen Ruan(2024), Yixia Li(2023)
  • Master students: Qi Wang(2025), Youxin Zhu(2025), Peng Lai(2024), Xiaodong Lao(2024), Jianjie Zheng(2024)

(Last updated on Sep. 27, 2025)