Dr. Xingwei Tan

Dr. Xingwei Tan

Research Associate in NLP. I work on reasoning in large language models.

Publications

22 publications. Newest first; my name is in bold. Also on Google Scholar.

Conference Papers

Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs?
Samuel Lewis-Lim, Xingwei Tan, Zhixue Zhao, and Nikolaos Aletras
Findings of AACL-IJCNLP 2026 (to appear), 2026 Paper
Compliance vs. Sensibility: On the Reasoning Controllability in Large Language Models
Xingwei Tan, Marco Valentino, Mahmud Elahi Akhter, Yuxiang Zhou, Maria Liakata, and Nikolaos Aletras
Findings of EMNLP 2026 (to appear), 2026 Paper Code
An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift
Constantinos Karouzos, Xingwei Tan, and Nikolaos Aletras
EMNLP 2026 (to appear), 2026 Paper
Fundamental Reasoning Paradigms Induce Out-of-Domain Generalization in Language Models
Mingzi Cao, Xingwei Tan, Mahmud Elahi Akhter, Marco Valentino, Maria Liakata, Xi Wang, and Nikolaos Aletras
Findings of ACL 2026, 2026 Paper
Fine-Tuning on Noisy Instructions: Effects on Generalization and Performance
Ahmed Alajrami, Xingwei Tan, and Nikolaos Aletras
AACL-IJCNLP 2025, 2025 Paper
IntrEx: A Dataset for Modeling Engagement in Educational Conversations
Xingwei Tan, Mahathi Parvatham, Chiara Gambi, and Gabriele Pergola
Findings of EMNLP 2025, 2025 Paper Code
Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?
Samuel Lewis-Lim, Xingwei Tan, Zhixue Zhao, Nikolaos Aletras
EMNLP 2025, 2025 Paper
Enhancing logical reasoning in language models via symbolically-guided monte carlo process supervision
Xingwei Tan, Marco Valentino, Mahmud Elahi Akhter, Maria Liakata, Nikolaos Aletras
EMNLP 2025, 2025 Paper Code
What makes a conversation interesting? Linguistic features predictive of interest in educational conversations between teachers and learners of English
Mahathi Parvatham, Xingwei Tan, Gabriele Pergola, and Chiara Gambi
CogSci 2025, 2025 Paper
Cascading Large Language Models for Salient Event Graph Generation
Xingwei Tan, Yuxiang Zhou, Gabriele Pergola, and Yulan He
NAACL 2025, 2025 Paper Code
SafeSpeech: a comprehensive and interactive tool for analysing sexist and abusive language in conversations
Xingwei Tan, Chen Lyu, Hafiz Muhammad Umer, Sahrish Khan, Mahathi Parvatham, Lois Arthurs, Simon Cullen, Shelley Wilson, Arshad Jhumka, and Gabriele Pergola
NAACL 2025 System Demonstration, 2025 Paper
Set-Aligning Framework for Auto-Regressive Event Temporal Graph Generation
Xingwei Tan, Yuxiang Zhou, Gabriele Pergola, and Yulan He
NAACL 2024, 2024 Paper Code
Event Temporal Relation Extraction with Bayesian Translational Model
Xingwei Tan, Gabriele Pergola, and Yulan He
EACL 2023, 2023 Paper Code
Event-centric question answering via contrastive learning and invertible event transformation
Junru Lu, Xingwei Tan, Gabriele Pergola, Lin Gui, and Yulan He
Findings of EMNLP 2022, 2022 Paper
Extracting Event Temporal Relations via Hyperbolic Geometry
Xingwei Tan, Gabriele Pergola, and Yulan He
EMNLP 2021, 2021 Paper Code
Recognizing conflict opinions in aspect-level sentiment classification with dual attention networks
Xingwei Tan, Yi Cai, and Changxi Zhu
EMNLP 2019, 2019 Paper
A New Samples Selecting Method Based on K Nearest Neighbors
Kai Yang, Yi Cai, Zhiwei Cai, Xingwei Tan, Haoran Xie, Tak-Lam Wong, and Wai Hong Chan
IEEE BigComp 2017, 2017 Paper

Journal Articles

No Shortcuts to Culture: Indonesian Multi-hop Question Answering for Complex Cultural Understanding
Vynska Amalia Permadi, Xingwei Tan, Nafise Sadat Moosavi, and Nikolaos Aletras
Transactions of the Association for Computational Linguistics (TACL), 2026 Paper
A rapid evidence review of evaluation techniques for large language models in legal use cases: trends, gaps, and recommendations for future research
Joshua Kelsall, Xingwei Tan, Aislinn Bergin, Jiahong Chen, Maria Waheed, Tom Sorell, Rob Procter, Maria Liakata, Jenny Chim, and Serene Chi
AI & SOCIETY, 2025 Paper
Learning refined features for open-world text classification with class description and commonsense knowledge
Haopeng Ren, Zeting Li, Yi Cai, Xingwei Tan, Xin Wu
World Wide Web, 2022 Paper
Detecting dependency-related sentiment features for aspect-level sentiment classification
Xing Zhang, Jingyun Xu, Yi Cai, Xingwei Tan, and Changxi Zhu
IEEE Transactions on Affective Computing, 2021 Paper
Improving aspect-based sentiment analysis via aligning aspect embedding
Xingwei Tan, Yi Cai, Jingyun Xu, Ho-Fung Leung, Wenhao Chen, and Qing Li
Neurocomputing, 2020 Paper