CSE 599H: Human-AI Interaction Research

Spring 2026 · TuTh 11:30am-12:50pm · CSE2 271
Instructor: Jeffrey Heer

Course Description

We will make sense of the landscape of Human-AI Interaction research, characterizing key challenges, opportunities, and perils. We will attempt a comprehensive view, covering historical context, technical underpinnings, and current systems and methods that incorporate AI into people’s work and lives. Affected application areas range across “white collar” work, data analysis, programming, creative expression, and social and mental well-being.

Students will (1) select, read, and present on relevant research papers and projects; (2) engage via in-person class activities; (3) complete warm-up assignments; and (4) develop an open-ended final project, which may advance existing research efforts.

There are no formal prerequisites beyond comfort reading and dissecting research papers. Any CS graduate student with HCI or applied AI research interests is welcome. Familiarity with HCI or AI methods is encouraged. Non-CSE students and interested undergraduates (ideally with some research experience) are invited to petition.

Schedule

Readings in bold face are required and you should be prepared to discuss them in class. The other readings are optional: you are encouraged to read the abstracts, skim the articles, and come to class with questions!

---

Tu 3/31: Agency + Automation

• J. Heer. (2019) Agency plus Automation: Designing Artificial Intelligence into Interactive Systems. Proceedings of the National Academy of Sciences, 116(6):1844–1850
• T. Winograd & F. Flores (1986) Understanding Computers and Cognition. Chapters 2, 3, and 6.
• A. Satyanarayan & G. M. Jones. (2024) Intelligence as Agency: Evaluating the Capacity of Generative AI to Empower or Constrain Human Action.

Th 4/2: Historical Context

• J. Grudin. (2009) AI and HCI: Two Fields Divided by a Common Focus. AI Magazine, 30(4), 48.
• B. Shneiderman & P. Maes. (1997) Direct manipulation vs. interface agents. interactions 4, 6 (Nov./Dec. 1997), 42–61.
• R. Sutton. (2019) The Bitter Lesson.
• S. Green, J. Heer & C. Manning. (2015) Natural Language Translation at the Intersection of AI and HCI. Communications of the ACM, 58(9): 46–53

---

Tu 4/7: Prompting

• J.D. Zamfirescu-Pereira, R. Y. Wong, B. Hartmann & Q. Yang. (2023) Why Johnny Can’t Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts. ACM Conference on Human Factors in Computing Systems (CHI ‘23).
• H. Subramonyam, R. Pea, C. Pondoc, M. Agrawala & C. Seifert. (2024) Bridging the Gulf of Envisioning: Cognitive Challenges in Prompt Based Interactions with LLMs. ACM Conference on Human Factors in Computing Systems (CHI).
• M. Agrawala. (2023) Unpredictable Black Boxes are Terrible Interfaces.

Th 4/9: Agentic Workflows

• I. Arawjo, C. Swoopes, P. Vaithilingam, M. Wattenberg & E. L. Glassman. (2024) ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing. ACM Conference on Human Factors in Computing Systems (CHI ‘24).
• S. Shankar, J.D. Zamfirescu-Pereira, B. Hartmann, A. Parameswaran & I. Arawjo. (2024) Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences. ACM Symposium on User Interface Software and Technology (UIST).
• T. Wu, M. Terry & C. Cai. (2022) AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts. ACM Conference on Human Factors in Computing Systems (CHI ‘22).

---

Tu 4/14: Design Considerations

• S. Amershi, D. S. Weld, M. Vorvoreanu, A. Fourney, B. Nushi, P. Collisson, J. Suh, S. Iqbal, P. N. Bennett, K. Inkpen, J. Teevan, R. Kikin-Gil & E. Horvitz. (2019) Guidelines for Human-AI Interaction. ACM Conference on Human Factors in Computing Systems (CHI ‘19).
• E. Horvitz. (1999) Principles of Mixed-Initiative User Interfaces. ACM Conference on Human Factors in Computing Systems (CHI ‘99), pp. 159-166.
• G. Bansal, J. Wortman Vaughan, S. Amershi, E. Horvitz, A. Fourney, H. Mozannar, V. Dibia & D. S. Weld. (2024) Challenges in Human-Agent Communication. arXiv.

Th 4/16: Perspectives on AI

• H. Farrell, A. Gopnik, C. Shalizi & J. Evans. (2025) Large AI Models are Cultural and Social Technologies. Science, 387(6739), pp. 1153–1156.
• A. Narayanan & S. Kapoor. (2025) AI as Normal Technology: An Alternative to the Vision of AI as a Potential Superintelligence.
• S. Huang, S. Carter, et al. (2026). What 81,000 people want from AI.

---

Tu 4/21: Designing with AI

• Y. Cao, P. Jiang & H. Xia. (2025) Generative and Malleable User Interfaces with Generative and Evolving Task-Driven Data Model. ACM Conference on Human Factors in Computing Systems (CHI ‘25).
• X. Shi, L.-Y. Wei, N. Zhao, J. Zhao & R. H. Kazi. (2026) Notational Animating: An Interactive Approach to Creating and Editing Animation Keyframes. ACM Conference on Human Factors in Computing Systems (CHI’26).
• H. Kumar, J. Vincentius, E. Jordan & A. Anderson. (2025) Human Creativity in the Age of LLMs: Randomized Experiments on Divergent and Convergent Thinking. ACM Conference on Human Factors in Computing Systems (CHI ‘25).
• Q. Yang, A. Steinfeld, C. Rosé & J. Zimmerman. (2020) Re-examining Whether, Why, and How Human-AI Interaction Is Uniquely Difficult to Design. ACM Conference on Human Factors in Computing Systems (CHI’20).

Th 4/23: Human-AI Co-Creation

• K. J. Feng, K. Pu, M. Latzke, T. August, P. Siangliulue, J. Bragg, D.S. Weld, A. X. Zhang, J. C. Chang. (2026) Cocoa: Co-Planning and Co-Execution with AI Agents. ACM Conference on Human Factors in Computing Systems (CHI ‘26).
• H. H. Clark & S. E. Brennan. (1991) Grounding in Communication. In L. B. Resnick, J. M. Levine, S. D. Teasley (editors), Perspectives on Socially Shared Cognition. (pp. 127-149).
• Y. Cao, Y. Huang, A. Truong, H. V. Shin & H. Xia. (2025) Compositional Structures as Substrates for Human-AI Co-creation Environment: A Design Approach and A Case Study. ACM Conference on Human Factors in Computing Systems (CHI ‘25).
• G. Bansal, T. Wu, J. Zhou, R. Fok, B. Nushi, E. Kamar, M.T. Ribeiro & D. Weld. (2021) Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance. ACM Conference on Human Factors in Computing Systems (CHI ‘21).
• M. Vaccaro, A. Almaatouq & T. Malone. (2024) When combinations of humans and AI are useful: A systematic review and meta-analysis. Nature Human Behaviour, 8, 2293–2303.

---

Tu 4/28: User Modeling

• O. Shaikh, S. Sapkota, S. Rizvi, E. Horvitz, J. S. Park, D. Yang & M. S. Bernstein. (2025) Creating General User Models from Computer Use. ACM User Interface Software and Technology (UIST ‘25).
• M. S. Lam, O. Shaikh, H. Xu, A. Guo, D. Yang, J. Heer, J. A. Landay, M. S. Bernstein. (2026) Just-In-Time Objectives: A General Approach for Specialized AI Interactions. ACM Conference on Human Factors in Computing Systems (CHI ’26).
• J. Fogarty, A. J. Ko, H. H. Aung, E. Golden, K. P. Tang, S. E. Hudson. (2005) Examining Task Engagement in Sensor-Based Statistical Models of Human Interruptibility. ACM Conference on Human Factors in Computing Systems (CHI ’05). pp. 331-340.

Th 4/30: Social Simulation

• J. S. Park, J. C. O’Brien, C. J. Cai, M. R. Morris, P. Liang, M. S. Bernstein. (2023) Generative Agents: Interactive Simulacra of Human Behavior. ACM User Interface Software and Technology (UIST ‘23).
• S. Kapania, W. Agnew, M. Eslami, H. Heidari, S. E. Fox. (2025) Simulacrum of Stories: Examining Large Language Models as Qualitative Research Participants. ACM Conference on Human Factors in Computing Systems (CHI ‘25).
• J. S. Park, C. Q. Zou, A. Shaw, B. M. Hill, C. Cai, M. R. Morris, R. Willer, P. Liang, M. S. Bernstein. Generative Agent Simulations of 1,000 People. arXiv.
• W. Agnew, A. S. Bergman, J. Chien, M. Díaz, S. El-Sayed, J. Pittman, S. Mohamed & K. R. McKee. (2024) The Illusion of Artificial Inclusion. ACM Conference on Human Factors in Computing Systems (CHI ‘24).

---

Tu 5/5: Final Project Proposals

• No readings

Th 5/7: Pluralistic AI

• M. L. Gordon, M. S. Lam, J. S. Park, K. Patel, J. Hancock, T. Hashimoto, M. S. Bernstein. (2022) Jury Learning: Integrating Dissenting Voices into Machine Learning Models. ACM Conference on Human Factors in Computing Systems (CHI ‘22).
• N. Oliveira, J. Li, K. Khalvati, R. C. Barragan, K. Reinecke, A. N. Meltzoff & R. P. N. Rao. (2025) Culturally-attuned AI: Implicit learning of altruistic cultural values through inverse reinforcement learning. PLOS One.
• T. Sorensen, J. Moore, J. Fisher, M. Gordon, N. Mireshghallah, C. M. Rytting, A. Ye, L. Jiang, X. Lu, N. Dziri, T. Althoff, Y. Choi. (2024) A Roadmap to Pluralistic Alignment. arXiv.
• J. Basoah, D. Chechelnitsky, T. Long, K. Reinecke, C. Zerva, K. Zhou, M. Díaz & M. Sap. (2025) Not Like Us, Hunty: Measuring Perceptions and Behavioral Effects of Minoritized Anthropomorphic Cues in LLMs. ACM Conference on Fairness, Accountability, and Transparency (FAccT).

---

Tu 5/12: Model Interpretation

• A. Boggust, B. Hoover, A. Satyanarayan, H. Strobelt (2022). Shared Interest: Measuring Human-AI Alignment to Identify Recurring Patterns in Model Behavior. ACM Human Factors in Computing Systems (CHI ‘22).
• A. Templeton, et al. (2024) Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet. Transformer Circuits Thread.
• C. Olah, N. Cammarata, L. Schubert, G. Goh, M. Petrov & S. Carter. (2020) Zoom In: An Introduction to Circuits. Distill.
• K. Li, A. Hopkins, D. Bau, F. Viégas, H. Pfister & M. Wattenberg. (2022) Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
• M. Wattenberg, F. Viégas & I. Johnson. (2016) How to Use t-SNE Effectively. Distill.

Th 5/14: Model Post-Training

• L. Ouyang, J. Wu, X. Jiang, D. Almeida, C. L. Wainwright, P. Mishkin, et al. (2022) Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35.
• R. Rafailov, A. Sharma, E. Mitchell, C. D. Manning, S. Ermon, C. Finn. (2023) Direct Preference Optimization: Your Language Model is Secretly a Reward Model. Advances in Neural Information Processing Systems, 36.
• P. F. Christiano, J. Leike, T. Brown, M. Martic, S. Legg & D. Amodei. (2017) Deep reinforcement learning from human preferences. Advances in neural information processing systems, 30.

---

Tu 5/19: Embodied AI

• R. A. Brooks. (1991) Intelligence without representation. Artificial intelligence, 47(1-3), 139-159.
• P. Fung, Y. Bachrach, A. Celikyilmaz, K. Chaudhuri, D. Chen, W. Chung, E. Dupoux, H. Gong, H. Jégou, A. Lazaric, A. Majumdar, A. Madotto, F. Meier, F. Metze, L.-P. Morency, T. Moutakanni, J. Pino, B. Terver, J. Tighe, P. Tomasello, J. Malik. (2025) Embodied AI Agents: Modeling the World. arXiv.
• Y. Mu, Q. Zhang, M. Hu, W. Wang, M. Ding, J. Jin, B. Wang, J. Dai, Y. Qiao & P Luo. (2023) EmbodiedGPT: Vision-language pre-training via embodied chain of thought. Advances in Neural Information Processing Systems.
• P. Anderson, Q.i Wu, D. Teney, J. Bruce, M. Johnson, N. Sünderhauf, I. Reid, S. Gould & A. van den Hengel. (2018) Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real Environments. Proc.IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3674-3683.
• M. Savva, A. Kadian, O. Maksymets, Y. Zhao, E. Wijmans, B. Jain, J. Straub, J. Liu, V. Koltun, J. Malik, D. Parikh & D. Batra. (2019) Habitat: A Platform for Embodied AI Research. Proc. International Conference on Computer Vision (ICCV), pp. 9339-9347.

Th 5/21: Accessibility & AI

• S. Cai, S. Venugopalan, K. Seaver, X. Xiao, K. Tomanek, S. Jalasutram, M. R. Morris, S. Kane, A. Narayanan, R. L. MacDonald, E. Kornman, D. Vance, B. Casey, S. M. Gleason, P. Q. Nelson & M. P. Brenner. (2024) Using large language models to accelerate communication for eye gaze typing users with ALS. Nature Communications, 15(9449).
• C. Li, R. Y. Pang, A. Chheda-Kothary, A. Sharif, H. Assalif, J. Heer, J. E. Froehlich. (2026) GeoVisA11y: An AI-based Geovisualization Question-Answering System for Screen-Reader Users. ACM Conference on Human Factors in Computing Systems (CHI ‘26).
• X. Zhang, L. de Greef, A, Swearngin, S. White, K. Murray, L. Yu, Q. Shan, J. Nichols, J. Wu, C. Fleizach, A. Everitt & J. P. Bigham. (2021) Screen Recognition: Creating Accessibility Metadata for Mobile Applications from Pixels. ACM Conference on Human Factors in Computing Systems (CHI ‘21).

---

Tu 5/26: Reliance

• Z. Buçinca, M. B. Malaya & K. Z. Gajos. (2021) To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making. Proceedings of the ACM on Human-Computer Interaction, Volume 5, Issue CSCW1.
• Z. Guo, Y. Wu, J. D. Hartline & J. Hullman. (2024). A decision theoretic framework for measuring AI reliance. ACM Conference on Fairness, Accountability, and Transparency (FAccT), pp. 221-236.
• H. Vasconcelos, M. Jörke, M. Grunde-McLaughlin, T. Gerstenberg, M. S. Bernstein, R. Krishna. (2024) Explanations Can Reduce Overreliance on AI Systems During Decision-Making. Proceedings of the ACM on Human-Computer Interaction, Volume 7, Issue CSCW1.

Th 5/28: Software Dev & AI

• M.-A. Storey. (2026) How Generative and Agentic AI Shift Concern from Technical Debt to Cognitive Debt.
• A. Sarkar. (2024) Intention Is All You Need. Proc. Conference of the Psychology of Programming Interest Group.
• J. H. Shen & A. Tamkin. (2026) How AI Assistance Impacts the Formation of Coding Skills.
• J.D. Zamfirescu-Pereira, E. Jun, M. Terry, Q. Yang & B. Hartmann. (2025) Beyond Code Generation: LLM-supported Exploration of the Program Design Space. ACM Conference on Human Factors in Computing Systems (CHI ‘25).

---

Tu 6/2: Science & AI

• Q. Hao, F. Xu, Y. Li & J. Evans. (2026) Artificial intelligence tools expand scientists’ impact but contract science’s focus. Nature, 649, pp. 1237–1243.
• K. Gu et al. (2024) BLADE: Benchmarking Language Model Agents for Data-Driven Science. Proc. Empirical Methods in Natural Language Processing.
• K. Baker. (2025) Context Windows or, of GPUs, LPUs, and Goal Displacement.

Th 6/4: Final Project Presentations

• No readings

---

Assignments

• Course Participation 40%
• Exercise 1: Talk to a Human 10%
• Exercise 2: Theories of Mind 10%
• Final Project 40%

Policies

Plagiarism Policy: Assignments should consist primarily of original work. Building off of others’ work—including 3rd party libraries, public source code examples, and design ideas—is acceptable and in most cases encouraged. However, failure to cite such sources will result in score deductions proportional to the severity of the oversight.

Religious Accommodation: Washington state law requires that UW develop a policy for accommodation of student absences or significant hardship due to reasons of faith or conscience, or for organized religious activities. The UW’s policy, including more information about how to request an accommodation, is available here: Religious Accommodations Policy. Accommodations must be requested within the first two weeks of this course using the Religious Accommodations Request form.