Professional Summary
Tianyu Jiang is an assistant professor in the Computer Science department at the University of Cincinnati, where he established and directs the CincyNLP Lab. His research covers multiple aspects of how AI understands and interacts with people, including meaning, emotion, and social behavior, studied through where they live in the model’s representations, what that geometry tells us about model behavior, and how to make the findings actionable. He believes that better interpretability methods are still needed to turn the study of AI into a science, and thus make AI safer and more trustworthy.
Learn more at: https://jiangtianyu.com/
Education
Ph.D.: University of Utah 2023 (Computer Science)
B.S.: Nanjing University 2016 (Mathematics)
Research and Practice Interests
Natural language processing; large language models (LLM); LLM interpretability; computational semantics; emotion understanding; social behavior and alignment of LLMs; AI safety and trustworthiness; LLM efficiency.
Research Support
Investigators:Jiang, Tianyu; Tang, Ming 04-01-2024 -12-31-2024 Siemens Corporation Minimal Data Needs for GenAI Design Role:Collaborator 25000.00
Investigators:Jiang, Tianyu 04-01-2025 -12-31-2025 MME Industry 4.0/5.0 Institute Cost-efficient Large Language Model Deployment Role:PI 40000.00
Investigators:Anand, Sam; Jiang, Tianyu 03-02-2026 -12-31-2026 MME Industry 4.0/5.0 Institute AI-Assisted Process Selection and Manufacturability Constraints in Early Design Role:Collaborator 40000.00 Hold Level:Industry
Investigators:Jiang, Tianyu; Xie, Chenxing 07-01-2026 -01-10-2027 Procter & Gamble Digital Accelerator at UC P&G Digital Accelerator @ UC: Refining and validating a proof-of-concept for AI-driven digitization of P&G analytical method training Role:Collaborator 49547.00 Hold Level:Industry
Publications
Peer Reviewed Publications
Daniel Vennemeyer, Phan Anh Duong, Tiffany Zhan, Tianyu Jiang (2026. ) Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs.EMNLP 2026, , More Information
Divyesh Bommana, Mohammad Saim, Tianyu Jiang (2026. ) Chiaroscuro for Emotions: A Contrastive Emotion Benchmark Grounded in Appraisal Theory .EMNLP 2026, ,
Mohammad Saim, Tianyu Jiang (2026. ) Emotional Labor Strategy Preferences in LLM Personas .Findings of EMNLP 2026, ,
Yagna Manasa Boyapati, Chong Yu, Tianyu Jiang, Justin Zhan (2026. ) Privacy-Preserving Heterogeneous Multi-LLM Federated Inference for Cognitive Diagnosis .Findings of EMNLP 2026, ,
Louie Hong Yao, Nicholas Jarvis, Tiffany Zhan, Saptarshi Ghosh, Linfeng Liu, Tianyu Jiang (2026. ) A Geometric Lens on LLM Abilities through Joint Embedding Item Response Theory.Transactions on Machine Learning Research, , More Information
Linfeng Liu, Saptarshi Ghosh, Tianyu Jiang (2026. ) Evaluating the Impact of Verbal Multiword Expressions on Machine Translation.ACL 2026, , More Information
Saptarshi Ghosh, Tianyu Jiang (2026. ) Exploring Concreteness Through a Figurative Lens.ACL 2026, , More Information
Saptarshi Ghosh, Tianyu Jiang (2026. ) MetFuse: Figurative Fusion between Metonymy and Metaphor.ACL 2026, , More Information
Louie Hong Yao, Vishesh Anand, Yuan Zhuang, Tianyu Jiang (2026. ) Rhetorical Questions in LLM Representations: A Linear Probing Study.ACL 2026, , More Information
Mohammad Saim, Tianyu Jiang (2026. ) Do Emotions Influence Moral Judgment in Large Language Models?.Findings of ACL 2026, , More Information
Saptarshi Ghosh, Linfeng Liu, Tianyu Jiang (2026. ) A Computational Approach to Visual Metonymy.EACL 2026, , More Information
Louie Hong Yao, Nicholas Jarvis, Tianyu Jiang (2026. ) Towards Robust Evaluation of Visual Activity Recognition: Resolving Verb Ambiguity with Sense Clustering.Findings of EACL 2026, , More Information
Dylan Hutson, Daniel Vennemeyer, Aneesh Deshmukh, Justin Zhan, Tianyu Jiang (2025. ) GuessingGame: Measuring the Informativeness of Open-Ended Questions in Large Language Models.EMNLP 2025, , More Information
Jayanth Krishna Chundru, Rudrashis Poddar, Jie Cao, Tianyu Jiang (2025. ) Do LLMs Encode Frame Semantics? Evidence from Frame Identification.EMNLP 2025, , More Information
Mohammad Saim, Phan Anh Duong, Cat Luong, Aniket Bhanderi, Tianyu Jiang (2025. ) Anatomy of a Feeling: Narrating Embodied Emotions via Large Vision-Language Models.Findings of EMNLP 2025, , More Information
Phan Anh Duong, Cat Luong, Divyesh Bommana, Tianyu Jiang (2025. ) CHEER-Ekman: Fine-grained Embodied Emotion Classification.ACL 2025, , More Information
Saptarshi Ghosh, Tianyu Jiang (2025. ) ConMeC: A Dataset for Metonymy Resolution with Common Nouns.NAACL 2025, , More Information
Yuan Zhuang, Tianyu Jiang, Ellen Riloff (2024. ) My Heart Skipped a Beat! Recognizing Expressions of Embodied Emotion in Natural Language.NAACL 2024, , More Information
Tianyu Jiang, Ellen Riloff (2023. ) Exploiting Commonsense Knowledge about Objects for Visual Activity Recognition.Findings of ACL 2023, , More Information
Tianyu Jiang, Ellen Riloff (2022. ) Identifying Physical Object Use in Sentences.EMNLP 2022, , More Information
Tianyu Jiang, Ellen Riloff (2021. ) Learning Prototypical Functions for Physical Artifacts.ACL 2021, , More Information
Tianyu Jiang, Ellen Riloff (2021. ) Exploiting Definitions for Frame Identification.EACL 2021, , More Information
Yuan Zhuang, Tianyu Jiang, Ellen Riloff (2020. ) Affective Event Classification with Discourse-enhanced Self-training.EMNLP 2020, , More Information
Tianyu Jiang, Ellen Riloff (2018. ) Learning Prototypical Goal Activities for Locations.ACL 2018, , More Information
Haibo Ding, Tianyu Jiang, Ellen Riloff (2018. ) Why is an Event Affective? Classifying Affective Events based on Human Needs .AFCON 2018, ,
Honors and Awards
03-2025 URC Faculty Scholars Research Awards https://research.uc.edu/news/2025/03/25/meet-the-2025-urc-faculty-scholars-awardees