CV

Industry Experience

• Post-doctoral Researcher Assistant, 2023-2024
  • AI CoE HSBC-UK via the Allen Turing Institute
  • Project: Generative AI Evaluation package for HSBC use cases
• LLM and NLP Algorithm Engineer, 2024–Present
  • Fliggy Alibaba
  • Project: Training and deploying LLMs for real-world business use cases

Education

• Ph.D in Computer Science, Queen Mary University of London, 2020-2024
• M.A. (with Distinction) in Linguistics, University College London, 2018-2019
• Exchange student in Computational Linguistics, University of California, San Diego, 2017
• B.A. in Translation, Zhejiang University of Technology, 2014-2018

Academic/Research Experience

• Demonstrator, 2021-2023
  • ECS7001P Neural Networks and NLP. with Julia Ive, Massimo Poesio. 2023.
  • ECS763U/ECS763P Natural Language Processing. with Julian Hough. 2021 - 2022.
  • ECS421U Automata and Formal Languages. with Nikos Tzevelekos. 2020-2021.
• Guest Lecturer, 2023
  • University College London
  • Topic: An Introduction to Natural Language Processing
  • I was invited to deliver a guest lecture to postgraduate students as part of a Machine Learning module at UCL.
• Tutorial Instructor, 2022
  • Imperial College London
  • Topic: Large Language Models
  • I was invited to give a tutorial to other young researchers on computational social sciences as part of the Summer Institutes of Computational Social Science (SICSS 2022-London) https://sicss.io/2022/london/schedule
• Research Assistant, 2019-2020
  • Ubiquitous Knowledge Processing Lab, Technische Universität Darmstadt
  • Project: SciGen: a Dataset for Reasoning-Aware Text Generation from Scientific Tables
  • Supervisors: Dr. Nafise Sadat Moosavi and Dr. Andreas Rücklé
• Experimental Assistant, 2018
  • Cross-Linguistic Studies and Brain Sciences Lab, Zhejiang University of Technology
  • Project: Processing of Information Structure in Chinese
  • Supervisor: Dr. Luming Wang

Research Interests

• Reinforcement Learning
• Natural Language Processing
• Machine Learning
• Active Learning
• Automated Fact-Checking
• Formal Semantics

Publications

QMUL-SDS at SCIVER: Step-by-Step Binary Classification for Scientific Claim Verification

Zeng, X., & Zubiaga, A. (2021). QMUL-SDS at SCIVER: Step-by-step binary classification for scientific claim ver-ification. In Proceedings of the Second Workshop on Scientific Document Processing (pp. 116–123). Association for Computational Linguistics.

Automated Fact-Checking: A Survey

Zeng, X., Abumansour, A. S., & Zubiaga, A. (2021). Automated fact-checking: A survey. Language & Linguistics Compass, e12438. https://doi.org/10.1111/lnc3.12438

Aggregating pairwise semantic differences for few-shot claim verification

Zeng X, Zubiaga A. 2022. Aggregating pairwise semantic differences for few-shot claim verification. PeerJ Computer Science 8:e1137 https://doi.org/10.7717/peerj-cs.1137

Active PETs: Active Data Annotation Prioritisation for Few-Shot Claim Verification with Pattern Exploiting Training

Xia Zeng and Arkaitz Zubiaga. 2023. Active PETs: Active Data Annotation Prioritisation for Few-Shot Claim Verification with Pattern Exploiting Training. In Findings of the Association for Computational Linguistics: EACL 2023, pages 190–204, Dubrovnik, Croatia. Association for Computational Linguistics.

MAPLE: Micro Analysis of Pairwise Language Evolution for Few-Shot Claim Verification

Xia Zeng and Arkaitz Zubiaga. 2024. MAPLE: Micro Analysis of Pairwise Language Evolution for Few-Shot Claim Verification. In Findings of the Association for Computational Linguistics: EACL 2024, pages 1177–1196, St. Julian’s, Malta. Association for Computational Linguistics.

Combining Large Language Models and Crowdsourcing for Hybrid Human-AI Misinformation Detection

Xia Zeng, David La Barbera, Kevin Roitero, Arkaitz Zubiaga, and Stefano Mizzaro. 2024. Combining Large Language Models and Crowdsourcing for Hybrid Human-AI Misinformation Detection. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '24). Association for Computing Machinery, New York, NY, USA, 2332–2336. https://doi.org/10.1145/3626772.3657965

Teaching LLM to be Persuasive: Reward-Enhanced Policy Optimization for Alignment frm Heterogeneous Rewards

tbc