Home

Hello! I am Xiang, a Research Associate in the Computational Logic and Argumentation group (CLArg) in the Department of Computing at Imperial College London. Previously, I completed my PhD at Imperial under the supervision of Prof. Francesca Toni and Dr. Nico Potyka.

My research lies at the intersection of explainable AI, computational argumentation, and trustworthy decision-making. I develop formal argumentation-based methods for making AI systems more explainable, contestable, and reliable, with a particular focus on Quantitative Bipolar Argumentation Frameworks (QBAFs). My recent work extends these methods towards evaluative AI systems, including applications in educational assessment and feedback, where transparency, robustness, and contestability are essential for responsible AI-supported decision-making.

Before starting my PhD, I worked as a machine learning research and development engineer in the Department of Search Science at Baidu for one year. During my time at Baidu, I developed AI algorithms for large-scale search systems, with the aim of improving user experience and search engine performance.

Research

• Interpretable Automated Essay Scoring via Quantitative Bipolar Argumentation
  X. Yin. Explainable Logic-Based Knowledge Representation (XLoKR) and Explanations with Constraints and Satisfiability (ExCoS) (XLoKR-ExCoS @ KR), 2026.

• Latent Debate: A Surrogate Framework for Interpreting LLM Thinking towards Binary Decisions
  L. Chen, X. Yin, F. Toni. Explainable Logic-Based Knowledge Representation (XLoKR) and Explanations with Constraints and Satisfiability (ExCoS) (XLoKR-ExCoS @ KR), 2026.

• Towards an Argumentative Foundation for Evaluative AI
  X. Yin, T. Miller, N. Potyka, A. Rago, F. Toni. IJCAI 2026 Workshop on Explainable Artificial Intelligence (XAI @ IJCAI), 2026.

• Contestability in Quantitative Bipolar Argumentation Frameworks
  X. Yin, N. Potyka, A. Rago, T. Kampik, F. Toni. The 23rd International Conference on Principles of Knowledge Representation and Reasoning (KR), 2026.

• Strength Change Explanations in Quantitative Argumentation
  T. Kampik, X. Yin, N. Potyka, F. Toni. The 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2026.

• On the Impact of Sparsification on Quantitative Argumentative Explanations in Neural Networks
  D. Peacock, Mansi, N. Potyka, F. Toni, X. Yin. The 3rd International Workshop on Argumentation for eXplainable AI (ArgXAI @ ECAI), 2025.

• Argumentative Large Language Models for Explainable and Contestable Claim Verification
  G. Freedman*, A. Dejl*, D. Gorur*, X. Yin*, A. Rago, F. Toni. The 39th AAAI Conference on Artificial Intelligence (AAAI), 2025.

• Applying Attribution Explanations in Truth-Discovery Quantitative Bipolar Argumentation Frameworks
  X. Yin, N. Potyka, F. Toni. The 2nd International Workshop on Argumentation for eXplainable AI (ArgXAI @ COMMA), 2024.

• Contribution functions for quantitative bipolar argumentation graphs: A principle-based analysis
  T. Kampik, N. Potyka, X. Yin, K. Čyras, F. Toni. International Journal of Approximate Reasoning (IJAR), 2024.

• Contestable AI Needs Computational Argumentation
  F. Leofante, H. Ayoobi, A. Dejl, G. Freedman, D. Gorur, J. Jiang, G. Paulino-Passos, A. Rago, A. Rapberger, F. Russo, X. Yin, D. Zhang, F. Toni. The 21st International Conference on Principles of Knowledge Representation and Reasoning (KR), 2024.

• CE-QArg: Counterfactual Explanations for Quantitative Bipolar Argumentation Frameworks
  X. Yin, N. Potyka, F. Toni. The 21st International Conference on Principles of Knowledge Representation and Reasoning (KR), 2024.

• Explaining Arguments’ Strength: Unveiling the Role of Attacks and Supports
  X. Yin, N. Potyka, F. Toni. The 33rd International Joint Conference on Artificial Intelligence (IJCAI), 2024.

• Argument Attribution Explanations in Quantitative Bipolar Argumentation Frameworks
  X. Yin, N. Potyka, F. Toni. The 26th European Conference on Artificial Intelligence (ECAI), 2023.

• Explaining Random Forests Using Bipolar Argumentation and Markov Networks
  N. Potyka, X. Yin, F. Toni. The 37th AAAI Conference on Artificial Intelligence (AAAI), 2023.

• On the Tradeoff Between Correctness and Completeness in Argumentative Explainable AI
  N. Potyka, X. Yin, F. Toni. The 1st International Workshop on Argumentation for eXplainable AI (ArgXAI @ COMMA), 2022.