Publications

2025

Y Gan, Y Liang, J Xie, Y Lin, J Yu, M Poesio (2025). Low-Hallucination and Efficient Coreference Resolution with LLMs Findings of the Association for Computational Linguistics (EMNLP).

C Madge, M Purver, M Poesio (2025). Referential ambiguity and clarification requests: comparing human and LLM behaviour.  Proceedings of the Eighth Workshop on Computational Models of Reference, Anaphora and Coreference (CRAC).

F Althani, C Madge, M Poesio (2025). Style Matters: Exploring the Role of Art Style in AI-Generated Images on Engagement in a Gamified Text Labelling Interface.  Proceedings of the 16th Biannual Conference of the Italian SIGCHI Chapter.

Y Gan, Y Liang, Y Lin, J Yu, M Poesio (2025). Improving LLMs' Learning for Coreference Resolution Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL).

X Sun, L Wang, Y Li, J Li, M Poesio, J Frommel, K Hinriks, J Pei (2025). Talking-to-Build: How LLM-Assisted Interface Shapes Player Performance and Experience in Minecraft. Proceedings of the 27th ACM International Conference on Multimodal Interaction (ICMI)

F Althani, C Madge, M Poesio (2025). How Task Complexity Moderates the Impact of AI-Generated Images on User Experience in Gamified Text Labelling Proceedings of the IEEE Conference on Games (CoG).

M Sarzotti, G Duca, C Madge, R Bernardi, M Poesio (2025). MLLMs Construction Company: Investigating Multimodal LLMs’ Communicative Skills in a Collaborative Building Task Proceedings of the ESSLLI 2025 Student Session.

C Madge, M Camilleri, P Carretero Garcia, V M Karan, J Shao, P Jayannavar, J Hough, B Roth, M Poesio (2025). MDC-R: The Minecraft Dialogue Corpus with Reference arXiv preprint arXiv:2506.22062

R Bernardi, J Hockenmaier, U Kruschwitz, P Jayannavar, M Poesio (2025). Dagstuhl Perspectives Workshop on Human in the Loop Learning through Grounded Interaction in Games. Schloß Dagstuhl Report.

2024

M Ogrodniczuk, A Nedoluzhko, M Poesio, S Pradhan, V Ng (2024). Proceedings of The Seventh Workshop on Computational Models of Reference, Anaphora and Coreference. Proceedings of The Seventh Workshop on Computational Models of Reference, Anaphora and Coreference.

Y Gan, C Li, J Xie, L Wen, M Purver, M Poesio (2024). ClarQ-LLM: A benchmark for models clarifying and requesting information in task-oriented dialog

arXiv preprint arXiv:2409.06097

C Li, Y Gan, Z Yang, Y Chen, X Qiu, Y Lin, M Purver, M Poesio (2024). Analyzing and enhancing clarification strategies for ambiguous references in consumer service interactions. Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue

W Aliady, M Poesio (2024). Master the Linguistic Landscape: Puzzle Integration in a 3D NLP Game. 2024 IEEE Conference on Games (CoG), 1-8

C Madge, M Poesio (2024). A LLM Benchmark based on the Minecraft Builder Dialog Agent Task. Proceedings of the 28th Workshop on the Semantics and Pragmatics of Dialogue

Massimo Poesio, Maciej Ogrodniczuk, Vincent Ng, Sameer Pradhan, Juntao Yu, Nafise Sadat Moosavi, Silviu Paun, Amir Zeldes, Anna Nedoluzhko, Michal Novák, Martin Popel, Zdeněk Žabokrtský, Daniel Zeman (2024). Universal anaphora: The first three years. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). 

Y Gan, M Poesio, J Yu (2024). Assessing the capabilities of large language models in coreference: An evaluation. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). 

J Hough, S Zarrieß, C Kennington, D Schlangen, M Poesio (2024). Conceptual Pacts for Reference Resolution using Small, Dynamically Constructed Language Models: A Study in Puzzle Building Dialogues. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). 

M Poesio, M Camilleri, PC Garcia, J Yu, MC Müller (2024). The ARRAU 3.0 Corpus. Proceedings of the 5th Workshop on Computational Approaches to Discourse (CODI 2024).

C Madge, M Poesio (2024). Large Language Models as Minecraft Agents. Proceedings of Wordplay

2023

S Paun, J Yu, NS Moosavi, M Poesio (2023). Scoring coreference chains with split-antecedent anaphors. Dialogue and Discourse 14 (2), 1-48.