University of Hamburg - to research, to teach, to educate and form, to homepage
Language Technology Group (LT)
Department of InformaticsLanguage Technology Group (LT)

Photo: alt left

Language Technology

Xintong Wang

Name: Xintong Wang       
Position: Ph.D. Candidate
Email: xintong.wang@uni-hamburg.de
Phone: +49 40 42883-2322
Office: Monday and Friday at HCDS, Tuesday to Thursday at LT
Address:

Informatikum, Vogt-Kölln-Straße 30, 22527 Hamburg

[Curriculum Vitae] We are hiring student assistants funded by CML Project. Self-motivated students with experience in NLP and VLP are welcome. I am always open to collaborations!

I am a third-year Ph.D. candidate at the University of Hamburg (Universität Hamburg/Exzellenzuniversitäten), Language Technology Group, advised by Prof. Dr. Chris Biemann, who is the best supervisor I've ever had. My research is supported by DFG Project Crossmodal Learning for Improving Human Reading. Before I join LT group, I got the M.Eng. and B.Eng. in Computer Science at the South China University of Technology (Double First-Class Universities and Disciplines) in 2019 and 2016 respectively. I have worked with Prof. Wenjie Li (She taught me how to do research and be critical.) at the Hong Kong Polytechnic University and Prof. Min Yang (She introduced NLP to me.) at the Chinese Academy of Sciences. Since 2022, I also collaborate with Dr. Ding Liang, from whom I got a lot of valuable advice.

Research Interests:

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

  • Truthfulness, safeness and explainable Large Language Models (LLMs)
  • Parameter-efficient fine-tuning Vision-Language Models (VLP Models)
  • Hallucination mitigation in Large Vision-Language Models (LVLMs)

News:

  • May 2024: One paper accepted to ACL Findings 2024!
  • Mar. 2024: One paper accepted to NeusymBridge at LREC-COLING 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.
  • May 2022: One paper accepted to LREC 2022!
  • Apr. 2021: Ph.D. Candidate at the University of Hamburg.
  • Jun. 2020: One paper accepted to Information Sciences.

Projects: SFB TRR 169 Project C7: Crossmodal Learning for Improving Human Reading. 

               Funded by German Research Foundation: 05.2020 - 12.2024, Doctoral Researcher

Publications during PhD: [Full Publication List]

         2024

  • Xintong Wang, Jingheng Pan, Liang Ding, and Chris Biemann, Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding, Findings of  the Association for Computational Linguistic 2024. (ACL 2024). (CORE Rank A*)
  • Xintong Wang, Xiaoyu Li, Xingshan Li, and Chris Biemann. Probing Language Models from A Human Behavioral Perspective. 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).
  • Daryna Dementieva, Daniil Moskovskiy, Nikolay Babakov, Abinew Ali Ayele, Naquee Rizwan, Florian Schneider, Xintong Wang, Seid Muhie Yimam, Dmitry Ustalov, Elisei Stakovskii, Alisa Smirnova, A Elnagar, Animesh Mukherjee, Alexander Panchenko. Overview of the Multilingual Text Detoxification Task at PAN 2024. Working Notes of CLEF 2024 (CLEF 2024).
  • Abinew Ali Ayele, Nikolay Babakov, Janek Bevendorff, Xavier Bonet Casals, Berta Chulvi, Daryna Dementieva, Ashaf Elnagar, Dayne Freitag, Maik Fröbe, Damir Korenčić, Maximilian Mayerl, Daniil Moskovskiy, Animesh Mukherjee, Alexander Panchenko, Martin Potthast, Francisco Rangel, Naquee Rizwan, Paolo Rosso, Florian Schneider, Alisa Smirnova, Efstathios Stamatatos, Elisei Stakovskii, Benno Stein, Mariona Taulé, Dmitry Ustalov, Xintong Wang, Matti Wiegmann, Seid Muhie Yimam, Eva Zangerle. (authors are listed in alphabetical order). 15th International Conference of the Cross-Language Evaluation Forum for European Languages (CLEF 2024).

         2023

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

         2022

  • Xintong Wang*, Florian Schneider*, Özge Alaçam, Prateek Chaudhury, and Chris Biemann. MOTIF: Contextualized Images for Complex Words to Improve Human Reading. Language Resources and Evaluation Conference 2022. (LREC 2022). (CORE Rank B)  [MOTIF Dataset]
  • Anton Orell Wiehe, Florian Schneider, Sebastian Blank, Xintong Wang, Hans-Peter Zorn, and Chris Biemann, Language over Labels: Contrastive Language Supervision Exceeds Purely Label-Supervised Classification Performance on Chest X-Rays, Asia-Pacific Chapter of the Association for Computational Linguistics: Student Research Workshop 2022. (AACL-IJCNLP SRW 2022).

         2021

  • Florian Schneider, Özge Alacam, Xintong Wang, and Chris Biemann, "Towards Multi-Modal Text-Image Retrieval to Improve Human Reading", Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop 2021. (NAACL SRW 2021). 

Teaching:

  • Project Mentor: Master Project Web Interfaces for Language Processing Systems, Summer 2022, 2023.
  • Co-instructor: Master Course Natural Language for the Web Winter semester, Winter 2020.

Supervision:

          Master Theses:

  • Xiaoyu Li, MSc, at Technische Universität Berlin & Beijing Institute of Technology, 06.03.2024
    • Thesis: Methods towards Understanding and Application of Foundation Models
  • Fabian Meyer MSc, at Universität Hamburg, 16.04.2023
    • Thesis: On the Potential and Limits of Zero-Shot Out-of-Distribution of Detection
  • Anton Orell Wiehe, MSc, at Universität Hamburg, 10.07.2022
    • Thesis: Domain Adaptation for Multi-Modal Foundation Models
  • Matthew Ng Cher-Wai, MSc, at Universität Hamburg, 06.06.2022
    • Thesis: Multi-modal Fictional Backstory Generation using Transformer-Aspect-Backstory Generator
  • Ankit Srivastava, MSc, at Universität Hamburg, 13.03.2022
    • Thesis: Complex Word Identification for Language Learners
  • Florian Schneider,  MSc, at Universität Hamburg, 27.07.2021
    • Thesis: Self-Supervised Multi-Modal Text-Image Retrieval Methods to Improve Human Reading

          Research Assistants and Interns:

  • Longqin Jiang, MSc, Research assistant, at Universität Hamburg, 01.05.2024 - Current
    • Topic: Trustful and Explainable Large Language Models
  • Yixiao Liu, BSc, Remote intern, at Southwest University, 01.10.2023 - Current
    • Topic: Mitigating Biases in Chinese Toxic Language
  • Jingheng Pan, MSc, Research assistant, at Universität Hamburg, 15.09.2023 - Current
    • Topic:  Mitigating Hallucinations in Large Vision-Language Models
  • Xiaoyu Li, MSc, Research assistant, at Technische Universität Berlin, 01.10.2022 - 30.09.2023
    • Topic: Dual Constraint Contrastive in Cross-modal Retrieval
  • Prateek Chaudhury BSc, Remote intern, at Indian Institute of Technology Delhi, 01.06.2021 - 31.08.2021
    • Topic: Reading Material Analysis for Second Language Learners

Professional Activities:

  • Invited Talk: Probing Large Language Models (LLMs) for Predicting Human Behavioral Data, June 2022, University of Wuppertal
  • Conference Reviewer: EMNLP 24', NeurIPS 24', ECCV 24', ACM MM 24', ACL 24', LREC-COLING 24', CVPR24', AACL23', EMNLP 23', ECAI 23', ACM MM23', ACL23‘, EACL 22', AACL 22', EMNLP 22', EMNLP 21', ACL 21', NAACL 21', IJCAI 21' (Senior PC), ACL 20', EMNLP 20', AACL-IJCNLP 20', EMNLP-IJCNLP 19', NLPCC 19'
  • Journal Reviewer: ACL Rolling Review, ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), IEEE Access