I’m Xinyi Chen, a PhD student at the IRLab at the University of Amsterdam, supervised by Maarten de Rijke. My research focuses on leveraging cognitive-inspired methods to better understand and enhance large language models. Currently, I am exploring how multi-agent systems can collaborate to tackle complex tasks, drawing inspiration from human learning, reasoning, and problem-solving processes. Additionally, my work spans multi-modal models (integrating vision and text) and benchmarking large language models.

I’m looking for internships during Summer 2025—send me a message if you have any opportunities to share!

News

November 2024: I attend EMNLP 2024 in person and present our paper during the poster session on November 12, 16:00–17:30!

November 2024: I’m excited to present my ongoing project on Multimodal Representation Alignment for Othello Game Learning at the CoAStaL group at the University of Copenhagen!

September 2024: Our paper on evaluating LLM instruction following and reasoning is accepted by EMNLP 2024 findings!

Publications

Xinyi Chen, Baohao Liao, Jirui Qi, Panagiotis Eustratiadis, Christof Monz, Arianna Bisazza, and Maarten de Rijke. 2024. The SIFo Benchmark: Investigating the Sequential Instruction Following Ability of Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2024. (EMNLP 2024 Findings) [code]

Xinyi Chen, Raquel Fernández, and Sandro Pezzelle. 2023. The BLA Benchmark: Investigating Basic Language Abilities of Pre-Trained Multimodal Models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. (EMNLP 2023) [code]

Ivo Verhoeven, Xinyi Chen, Qingzhi Hu, and Mario Holubar. (2021). Replication Study of ‘Generative causal explanations of black-box classifiers. Rescience C. [code]