The main lines of my recent research (with selected publications) (Full List on [Google Scholar]):

Investigating conversational abilities of LLMs

• Wang, S. F., Huang, R. S., Hsieh, S. K., & Prévot, L. (2025). Zero-Shot Evaluation of Conversational Language Competence in Data-Efficient LLMs Across English, Mandarin, and French. In Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL). [URL]
• Wang, S. F., Prévot, L., Chi, J. A., Huang, R. S., & Hsieh, S. K. (2025). Spontaneous Speech Variables for Evaluating LLMs’ Cognitive Plausibility. Presented at the 14th Workshop on Cognitive Modeling and Computational Linguistics (CMCL). [URL]
• Prévot, L., Wang, S. F., Chi, J. A., & Hsieh, S. K. (2024). Extending the BabyLM initiative: Promoting diversity in datasets and metrics through high-quality linguistic corpora. In The 2nd BabyLM Challenge at the 28th Conference on Computational Natural Language Learning. [URL]

Linguistic units in conversation

Linguistic Units in Conversation. I take discourse units (individual ideas, speech acts) as crucial in linking how grammar combines atomic multimodal elements into elementary "ideas" and "actions" and how these are used for larger communicative and extra-communicative objectives.  A pivot between language structure and language use in world.

• Prévot, L., & Muller, P. (2025). A Few Shades of Supervision for Discourse Segmentation: Experiments on a French conversational corpus. Dialogue & Discourse, 16(2), 35–73. [DOI]
• Prévot, L., Bertrand, R., & Hunter, J. (2025). Segmenting a Large French Meeting Corpus into Elementary Discourse Units. In Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL). [URL]
• Prévot, L., Muller, P., Tseng, S.-C., & Wang, S.-F. (2025). LLM-based Elementary Discourse Units Segmentation for Spontaneous Speech in French, Taiwan Mandarin, and Taiwan Southern Min. International Journal of Computational Linguistics and Chinese Language Processing. [PDF]
• Prévot, L., Bertrand, R., & Rauzy, S. (2021). Investigating disfluencies contribution to discourse–prosody mismatches in French conversations. In The 10th Workshop on Disfluency in Spontaneous Speech (DiSS). [PDF]
• Prévot, L., Tseng, S.-C., Peshkov, K., & Chen, A. C. H. (2015). Processing units in conversation: A comparative study of French and Mandarin data. Language and Linguistics, 16(1), 69–92. [PDF] [DOI]

Investigating the biais against genuine conversational speech in computational approaches

• Pilan, I., Prévot, L., Buschmeier, H., & Lison, P. (2024). Conversational feedback in scripted versus spontaneous dialogues: A comparative analysis. In Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL). [URL]
• Prévot, L., Magistry, P., & Lison, P. (2019). Should we use movie subtitles to study linguistic patterns of conversational speech? A study based on French, English and Taiwan Mandarin. In Third International Symposium on Linguistic Patterns of Spontaneous Speech. [PDF]

Conversational feedback

• Nikolaus, M., Prévot, L., & Fourtassi, A. (2023). Communicative feedback in response to children’s grammatical errors. In Proceedings of the Annual Meeting of the Cognitive Science Society (CogSci). [PDF]
• Prévot, L., Gorisch, J., & Mukherjee, S. (2015). Annotation and classification of French feedback communicative functions. In Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation (PACLIC). [PDF]
• Muller, P., & Prévot, L. (2003). An empirical study of acknowledgment structures. In 7th Workshop on the Semantics and Pragmatics of Dialogue (SEMDIAL). [[PDF]]

Producing language corpora and resources

• Hunter, J., Yamasaki, H., Granier, O., Louradour, J., Bertrand, R., Thompson, K., & Prévot, L. (2024). SUMM-RE: A corpus of French meeting-style conversations. In 31ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN). [PDF] [Corpus]
• Hervé, E., François, C., & Prévot, L. (2024). Daily auditory environments in French-speaking infants: A longitudinal dataset. Workshop on Cognitive Modeling and Computational Linguistics (CMCL). [[URL]]
• Bodur, K., Nikolaus, M., Kassim, F., Prévot, L., & Fourtassi, A. (2021). Chico: A multimodal corpus for the study of child conversation. In Companion Proceedings of the International Conference on Multimodal Interaction (ICMI). [URL]
• Rauchbauer, B., Hmamouche, Y., Bigi, B., Prévot, L., Ochs, M., & Chaminade, T. (2020). Multimodal corpus of bidirectional conversation of human–human and human–robot interaction during fMRI scanning. In Proceedings of the Language Resources and Evaluation Conference (LREC). [PDF] [Corpus]
• Prévot, L., Gorisch, J., & Bertrand, R. (2016). A CUP of CoFee: A large collection of feedback utterances provided with communicative function annotations. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC). [[URL]]