Xintong Wang (王鑫同) Ph.D. Candidate Language Technology Group Department of Informatics, Universität Hamburg Vogt-Kölln-Straße 30, 22527 Hamburg Email: xintong.wang@uni-hamburg.de   or  m.e.xintong@gmail.com [Curriculum Vitae]   [Github]   [Google Scholar]   [Twitter]

I am a fourth-year Ph.D. candidate at University of Hamburg (Universität Hamburg/Exzellenzuniversitäten), advised by Prof. Chris Biemann. Previously, I was a visiting student at SIAT, Chinese Academy of Sciences in 2018, advised by Prof. Min Yang. Then, I was a research assistant at PolyU, The Hong Kong Polytechnic University from 2018 to 2019, advised by Prof. Maggie Wenjie Li. I received my M.Eng. degree and B.Eng. degree from the School of Computer Science and Engineering, South China University of Technology (Double First-Class Universities and Disciplines) in 2019 and 2016, respectively. I also collaborate with research scientists, Dr. Ding Liang and Dr. Longyue Wang, from whom I got a lot of valuable advice and support.

We are hiring student assistants. Self-motivated students with experience in LLM and LVLM are welcome. I am always open to collaborations!

Research

I have broad interests in natural language processing (NLP), particularly in crossmodal learning and natural language generation.

• Truthfulness, safeness and explainable Large Language Models (LLMs). [COLING25'] [arXiv CoRR] [arXiv CoRR]
• Parameter-efficient fine-tuning on Vision-Language models (VLP Models). [ECAI23'] [AACL22'] [NAACL21']
• Efficient and truthful methods on Large Vision-Language Models (LVLMs). [ACL24'] [LREC22']

News

• 😊 Dec. 2024: I will serve as an Area Chair for ACL ARR!
• 🎉 Nov. 2024: One paper accepted to COLING 2025 (Oral)!
• 🎉 May 2024: One paper accepted to ACL 2024 (Findings)!
• 🎉 Mar. 2024: One paper accepted to LREC-COLING: NeusymBridge 2024!
• Aug. 2023: Co-organizer of CLEF-2024 SemEval Task: Multilingual Text Detoxification
• 🎉 Jul. 2023: One paper accepted to ECAI 2023!
• Jun. 2023: Invited talk at the University of Wuppertal.
• Dec. 2022: Visiting Researcher at the Institute of Psychology, Chinese Academy of Sciences.
• Jun. 2022: Attending LREC 2022.
• 🎉 May 2022: One paper accepted to LREC 2022!
• Apr. 2021: Ph.D. Candidate at the University of Hamburg.

Experiences

• 2022/12 - 2023/03: Visiting scholar at Chinese Academy of Sciences (Advisor: Prof. Xingshan Li)
• 2020/05 - 2021/04: Research associate at Universität Hamburg (Advisor: Prof. Chris Biemann)
• 2018/10 - 2019/08: Research assistant at PolyU (Advisor: Prof. Maggie Wenjie Li)
• 2018/03 - 2018/09: Visiting student at SIAT, Chinese Academy of Sciences (Advisor: Prof. Min Yang)

Selected Publications

Preprint

• Mitigating Biases in Chinese Toxic Language via Sentiment Polarity Consistent Rewrites: Benchmark and Evaluation
  Xintong Wang, Yixiao Liu, Jingheng Pan, and Chris Biemann. 2024
  

• CogSteer: Cognition-Inspired Selective Layer Intervention for Efficient Semantic Steering in Large Language Models
  Xintong Wang, Jingheng Pan, Longqin Jiang, Liang Ding, Xingshan Li, and Chris Biemann. 2024
  

2025

• Multilingual and Explainable Text Detoxification with Parallel Corpora
  Daryna Dementieva, Nikolay Babakov, Amit Ronen, Abinew Ali Ayele, Naquee Rizwan, Florian Schneider, Xintong Wang, Seid Muhie Yimam, Daniil Alekhseevich Moskovskiy, Elisei Stakovskii, Eran Kaufman, Ashraf Elnagar, Animesh Mukherjee and Alexander Panchenko.
  Proceedings of the 31st International Conference on Computational Linguistics (COLING 2025) (CORE Rank A) (Oral).
  

2024

• Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding
  Xintong Wang, Jingheng Pan, Liang Ding, and Chris Biemann.
  Findings of the Association for Computational Linguistics (ACL 2024). (CORE Rank A*)
  

• Probing Large Language Models from A Human Behavioral Perspective
  Xintong Wang, Xiaoyu Li, Xingshan Li, and Chris Biemann.
  Proceedings of Bridging Neurons and Symbols for Natural Language Processing and Knowledge Graphs Reasoning (Neusymbridge) at the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024).
  

2023

• Using Self-Supervised Dual Constraint Contrastive Learning for Cross-modal Retrieval
  Xintong Wang, Xiaoyu Li, Liang Ding, Sanyuan Zhao, and Chris Biemann.
  European Conference on Artificial Intelligence 2023 (ECAI 2023). (CORE Rank A 24%)
  

2022

• MOTIF: Contextualized Images for Complex Words to Improve Human Reading
  Xintong Wang*, Florian Schneider*, Özge Alaçam, Prateek Chaudhury, and Chris Biemann.
  Language Resources and Evaluation Conference 2022 (LREC 2022). (CORE Rank B) [Dataset]
  

Professional Activities

Invited Talks

• Probing Large Language Models (LLMs) for Predicting Human Behavioral Data, June 2023, University of Wuppertal

Teaching Assistant

• Instructor for Deep Learning for Natural Language Processing, Winter 2024/2025, University of Hamburg
• Project mentor for Master Project Web Interfaces for Language Processing Systems, Summer 2022/2023, University of Hamburg
• Instructor for Natural Language Processing for Web, Winter 2020, University of Hamburg

Academic Services

• Area Chair: ACL ARR

• Conference Reviewer: AISTATS 25', NAACL 25', COLING 25', NeurIPS 25', ACM MM 24', ECCV 24', ACL 24', NAACL 24', LREC-COLING 24', CVPR24', IJCNLP-AACL'23, ACM MM23', ECAI 23', AACL'22, ARR'22, EMNLP'22, ARR'21, ACL'21, NAACL'21, IJCAI'21(SPC), ACL'20, EMNLP'20, AACL-IJCNLP'20

• Session Chair of ECAI-2023.
• Senior Program Committee of IJCAI-2021.
• Program Committee of Multimodal and Multilingual Hate Speech Detection workshop at KONVENS 2021.

Misc.

🐈I have a cat called Minus. His name is a German word (subtraction/minus), with my direct hope that he can live in an easy mode.