Natural language understanding
At CALM, we apply puzzles in language to the design of AI systems: pragmatic reasoning · numerical representations of meaning · surprisal.
See Google Scholar for most recent research output.
- Cong, Y. (2024). Manner implicatures in large language models. Scientific Reports. [PDF].
- Cong, Y. and Rayz, R. (2025). Language models demonstrate the good-enough processing seen in humans. In Proceedings of CogSci. [PDF] [Poster]
- Li, Y.; Cong, Y.; Francis, E.J. (2025). Beyond Binary Animacy: A Multi-Method Investigation of LMs' Sensitivity in English Object Relative Clauses. In Proceedings of CMCL [PDF]
- Pranav, A.; Cong, Y.; Chersoni, E.; Hsu, Y-Y.; and Lenci, A. (2024). Comparing Static and Contextual Distributional Semantic Models on Intrinsic Tasks: An Evaluation on Mandarin Chinese Datasets. Proceedings of LREC-COLING. [PDF].
- Cong, Y.; Chersoni, E.; Hsu, Y-Y.; and Blache, P. (2023). Investigating the Effect of Discourse Connectives on Transformer Surprisal: Language Models Understand Connectives, Even So They Are Surprised. Proceedings of BlackboxNLP. [PDF].
- Cong, Y.; Chersoni, E.; Hsu, Y-Y.; and Lenci, A. (2023). Are Language Models Sensitive to Semantic Attraction? A Study on Surprisal. Proceedings of *SEM. [PDF].
- Cong, Y. (2022). Psycholinguistic Diagnosis of Language Models' Commonsense Reasoning. Proceedings of CSRR. [PDF] [VIDEO].
- Cong, Y. (2022). Pre-trained Language Models' Interpretation of Evaluativity Implicature: Evidence from Gradable Adjectives Usage in Context. Proceedings of UnImplicit. [PDF] [VIDEO].
- Pandia, L.; Cong, Y.; and Ettinger, A. (2021). Pragmatic competence of pre-trained language models through the lens of discourse connectives. Proceedings of CoNLL. [PDF].
Computational approach to language function and disfunction
At CALM, we translate NLP methods to study language learners · individuals living with disorders and illness.
See Google Scholar for most recent research output.
- Cong, Y. (2025). Demystifying large language models in second language development research. Computer Speech & Language. [PDF].
- Cong, Y. (2024). Second language learning of degree expressions: A computational approach. Cambridge Natural Language Processing. [PDF].
- Cong, Y. (2024). AI Language Models: An Opportunity to Enhance Language Learning. Informatics. [PDF].
- Hu, J.; Cong, Y. (2025). Modeling Chinese L2 Writing Development: The LLM-Surprisal Perspective. In Proceedings of CMCL. [PDF].
- Godara, T.; He, R.; Hinzen, W.; Cong, Y. (2026). Exploring the Semantic Space of Second Language Learners. In Proceedings of EACL-SRW [PDF].
- Cong, Y.; Hu, J.; Reese, T.; Liu, H. (2026). How robust are linguistic markers of aging? The case of aging-related social media text. Natural Language Processing Journal. [PDF].
- Cong, Y. and Lee, J. (2025). Tracking priming-induced language recovery in aphasia with pre-trained language models. Frontiers in Artificial Intelligence. [PDF].
- Cong, Y.; LaCroix, A.N.; Lee, J. (2024). Clinical efficacy of pre-trained large language models through the lens of aphasia. Nature Scientific Reports. [PDF].
- Cho, S.; Cong, Y.; Mehta, A.; Nikzad, AH.; Berretta, S.; Behbehani, L.; Liberman, M.Y.; Tang, X.S. (2025). Unique signatures in verbal fluency task performance in schizophrenia and depression. Schizophrenia Research: Cognition. [PDF].
- Tang, S.X.; Cong, Y.; Mercep, G.; Bhatti, M.; Serpe, G.; Gromova, V.; Berretta, S.; John, M.; Liberman, M.Y.; Sinvani, L. (2023). Characterizing and Detecting Delirium with Clinical and Computational measures of Speech and Language Disturbance. Journal of Psychiatry and Neuroscience. [PDF].
- Tang, S.X.; Cong, Y.; Nikzad, AH.; Mehta, A.; Cho, S.; Hänsel, K.; Berretta, S.; Dhar, A.; Kane, JM.; and Malhotra, A. (2022). Clinical and Computational Speech Measures are Associated with Social Cognition in Schizophrenia Spectrum Disorders. Schizophrenia research. [PDF].
- Nikzad, AH.; Cong, Y.; Berretta, S.; Hänsel, K.; Cho, S.; Pradhan, S.; Behbehani, L.; DeSouza, D.; Liberman, MY. and Tang, S.X. (2022). Who Does What to Whom? Graph Representations of Action-Predication in Speech Relate to Psychopathological Dimensions of Psychosis. Schizophrenia. [PDF].
Description and experiments in linguistic meaning
At CALM, we study language to make better predictions about the possibilities and the impossibilities in language: ambiguity · implicature · comparatives.
See Google Scholar for most recent research output.
- Cong, Y. (2022). Judge-Dependence in Quality Nouns: A Semantic Analysis of The Mandarin Chinese you NP Structure. Asian Languages and Linguistics. [PDF].
- Cong, Y. (2021). Competition in Natural Language Meaning: The Case of Adjective Constructions in Mandarin Chinese and Beyond. Doctoral dissertation, Michigan State University. [PDF] [Artificial language learning experiment - speaker perspective VIDEO] [listener perspective VIDEO] [Design document].
- Cong, Y. and Buccola, B. (2021). Alternatives in non-scalar implicature: The case of Mandarin adjective constructions. Presentation at PLC. [Poster] [Abstract] [Truth-Value Judgment survey experiment script].
- Cong, Y. and Ngonyani, D. (2022). A syntactic analysis of the cooccurrence of stative and passive in Kiswahili. Proceedings of ACAL. [PDF].
- Smith, K.; Ma, Y.; Cong, Y. and Beretta, A. (2019). Semantic attraction in sentence processing. Presentation at CUNY. [Abstract].
- Cong, Y. (2018). The Non-canonical argument realization of Chinese alternations. Proceedings of NACCL. [PDF].
- Parrish, A.; Kelley, P.; Smith, K.; Cong, Y. and Beretta, A. (2017). Prosodic lengthening and boundary prediction in nominal compounds: An ERP study. Presentation at SNL. [Poster].
- Cong, Y.; Huang, C.-R.; and Wee, L.-H. (2015). The invertible construction in Chinese. Proceedings of PACLIC. [PDF].