I’m Xinyi Chen, an ELLIS PhD student jointly supervised by Maarten de Rijke at the University of Amsterdam and Anders Søgaard at the University of Copenhagen. My research investigates how cognitive principles can inform the development of large language models. I am particularly interested in how multi-agent systems can collaborate to solve complex tasks, inspired by human learning, reasoning, and problem-solving strategies. Beyond this, my work also spans multimodal representation learning (vision + language) and the evaluation and benchmarking of large language models.

I’m looking for internships during Summer 2026—send me a message if you have any opportunities to share!

News

November 2025: I will present our paper on multimodal representation learning at EMNLP 2025 (poster session: November 7, 12:00–13:00).

July 2025: I will present our paper at the ICML 2025 Assessing World Models Workshop in Vancouver.

March 2025: I will visit the CoAStaL NLP group at the University of Copenhagen (March–June 2025) through the ELLIS program.

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

November 2024: I will 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 will be published in EMNLP 2024 Findings.

Publications

Xinyi Chen, Yifei Yuan, Jiaang Li, Serge Belongie, Maarten de Rijke, and Anders Søgaard. 2025.
What if Othello-Playing Language Models Could See?. In Findings of the Association for Computational Linguistics: EMNLP 2025. (EMNLP 2025 Findings) [code] (*Co-first authors.)

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]

Teaching & Student Supervision

Teaching Assistant

• IR1 (Information Retrieval 1), University of Amsterdam — 2022, 2024

Student Supervision

• Yanxu Chen (MSc Artificial Intelligence, UvA, 2025): Master AI Project on data selection and efficient fine-tuning.
• Gregory Go (MSc Artificial Intelligence, UvA, 2025): MSc thesis on multi-agent systems. This work led to a publication at AAAI 2026 Innovative Applications of AI.