Anna Leshinskaya
Biography
Anna Leshinskaya, Ph.D., is Assistant Professor in the Department of Cognitive Sciences and Faculty Fellow at the Center for the Neurobiology of Learning & Memory at the University of California, Irvine. Her research examines how the human brain builds relational knowledge from experiences of events, with recent work extending to the study of moral cognition in both human and artificial intelligence systems. Before joining UC Irvine, she served as Research Program Lead in Human Cognition and AI at the AI Objectives Institute and held postdoctoral and research positions at UC Davis and the University of Pennsylvania.
Leshinskaya has secured over $1.4 million in research funding as principal investigator, including grants from the National Science Foundation, Schmidt Sciences, and the John Templeton Foundation. Her NSF-funded work investigates mechanisms for causal and non-causal predictive learning, while her current projects explore mechanistic cognitive alignment for morally-guided decision-making and moral virtue in the age of AI. Her research combines cognitive neuroscience methods with computational approaches to understand how humans and artificial systems represent concepts, learn statistical patterns, and make value-based decisions.
Leshinskaya received her Ph.D. in Psychology from Harvard University, where she worked with Alfonso Caramazza. She has published research in journals including Cerebral Cortex, Cognition, and the Journal of Experimental Psychology: General, and has presented her work at conferences including NeurIPS, the Cognitive Neuroscience Society, and the Cognitive Science Society. She advises doctoral and undergraduate students and serves on departmental committees at UC Irvine.
Return to topEducation
- PhD in Psychology (Cognition, Brain & Behavior), Harvard University, 2015
- Bachelor of Arts, Honors in Cognitive Science, Carleton University, 2008
Areas of Expertise
- Cognitive Neuroscience
- Relational Memory Formation
- Concept Representation & Organization
- Statistical Learning Mechanisms
- Large Language Models
- Value Alignment
- Moral Reasoning
- Mechanistic Interpretability
Recent Publications
- Smullen, E., Thirumaligai, S., Leshinskaya, A., “Virtue semantics: Probing the consistency of moral values of large language models”, vol. 42, 2025. Presented at Workshop on Assessing World Models at International Conference on Machine Learning.
- McCoy, M., Leshinskaya, A., “Relational composition during attribute retrieval in GPT is not purely linear”, vol. 38, 2024. Presented at Compositional Learning: Perspectives, Methods, and Paths Forward workshop at NeurIPS.
- Leshinskaya, A., Chakroff, A., “Value as semantics: representations of human moral and hedonic value in large language models”, vol. 37, 2023. Presented at AI meets moral philosophy and moral psychology workshop at NeurIPS.
- Leshinskaya, A., Ranganath, C., Boorman, E., “Computational principles of predictive representation in the human brain”, 2023. Presented at Proceedings of the Computational Cognitive Neuroscience Society Meeting, Oxford, UK.
- Leshinskaya, A., Nguyen, M. A., Ranganath, C., “Integration of event experiences to build relational memory in the human brain” (opens in new tab), Cerebral Cortex, 2023.
- Leshinskaya, A., Bajaj, M., Thompson-Schill, S.L., “Novel objects with causal event schemas elicit selective responses in tool- and hand-selective lateral occipito-temporal cortex”, Cerebral Cortex, vol. 33, no. 9, pp. 5557–5573, 2023.
- Leshinskaya, A., Lambert, E., “Implications from the philosophy of concepts for the neuroscience of memory systems”, Neuroscience and Philosophy, MIT Press, 2022.
- Leshinskaya A., Bajaj, M., Thompson-Schill, S.L., “Incidental binding between predictive relations”, Cognition, vol. 199, pp. 104238, 2020.
- Leshinskaya, A., Wurm, M. F., Caramazza, A., “Concepts of actions and their objects”, The Cognitive Neurosciences, 6th edition, pp. 757–765, 2020.
- Leshinskaya, A., Thompson-Schill, S.L., “Transformation of event representations along middle temporal gyrus”, Cerebral Cortex, vol. 30, no. 5, pp. 3148–3166, 2020.
- Leshinskaya A., Lambert, E., Thompson-Schill, S.L., “Algebraic patterns as ensemble representations”, Cognitive Science Society, pp. 646-650, 2019. Presented at Proceedings of the 41st Annual Conference of the Cognitive Science Society, Montreal, QB.
- Leshinskaya, A., Thompson-Schill, S.L., “From the structure of experience to concepts of structure: how the concept 'cause' applies to objects and events”, Journal of Experimental Psychology: General, vol. 148, no. 4, pp. 619-643, 2019.
- Leshinskaya, A., Thompson-Schill, S.L., “Inferences about uniqueness in statistical learning”, Cognitive Science Society, pp. 2020-2025, 2018. Presented at Proceedings of the 40th Annual Meeting of the Cognitive Science Society.
- Leshinskaya, A., Contreras, J.M., Caramazza, A., Mitchell, J.P., “Neural representations of belief concepts: A representational similarity approach to social semantics”, Cerebral Cortex, vol. 27, no. 1, pp. 344-357, 2017.
- Leshinskaya, A., Caramazza, A., “For a cognitive neuroscience of concepts: Moving beyond the grounding issue”, Psychonomic Bulletin & Review, vol. 23, no. 4, pp. 991–1001, 2016.
- Leshinskaya, A., Caramazza, A., “Abstract categories of functions in anterior parietal lobe”, Neuropsychologia, vol. 76, pp. 27–40, 2015.
- Leshinskaya, A., Caramazza, A., “Nonmotor aspects of action concepts”, Journal of Cognitive Neuroscience, vol. 26, no. 12, pp. 2863–2879, 2014.
- Leshinskaya A., Caramazza A., “Organization and Structure of Conceptual Representations”, The Oxford handbook of language production, Oxford University Press, 2014.
Contact Information
Website: https://relcoglab.org
Email: aleshins@uci.edu
Address: 2554 Social & Behavioral Sciences Gateway, Irvine, CA 92697-5100
Return to topThis profile was created with the help of AI.
Last updated on 5/27/2026.