Summary

This course will explore the intersection of machine learning (ML) and human behavior. The format of the course will be a mix of paper presentations, lectures, and a final project. We will cover three units:

Unit I: Modeling Human Behavior with ML. Predicting or simulating human behaviors is useful when behaviors are difficult to observe (e.g., for cost or privacy reasons) or cannot be observed (e.g., future or counterfactual behaviors). In this unit, we'll begin with recent efforts to simulate behaviors with LLMs, including survey responses, experimental results, and social interactions. We will discuss challenges in this domain, such as bias, diversity, validation, generalization, and scalability, along with approaches to address these challenges. We will start from the individual-level and scale up to entire networks and societies, exploring both LLM-based and more traditional approaches to modeling human societies.

Unit II: Algorithmically Infused Societies. In this unit, we'll discuss the interplay between algorithms and social systems: how algorithms shape human behaviors and human behaviors feed back into algorithms, resulting in feedback loops. We will study these loops in different contexts, such as recommender systems and social media feeds, and explore human awareness of algorithms and strategic shifts in behavior. We will end with a discussion about automating human decision-making, including how to compare human vs. algorithmic decisions under selective labels and the validity and risks of such automation.

Unit III: Adapting AI to Human Behavior. In this final unit, we will focus on how humans behave in interaction with AI systems and how we should adapt generative AI systems to work more effectively with humans. We will begin with analyses of human-AI interactions in the wild and discuss how to evaluate human-AI interactions. We will then explore various ways in which AI needs to adapt to humans in order to improve human-AI outcomes, such as how to understand human intents (e.g., given ambiguous user queries), learn individual preferences and personalize models, mitigate overreliance and provide explanations, and strive for complementarity.

Schedule

Date	Topic
8/28 Thu	Introduction to course
Unit I. Modeling Human Behaviors with ML
09/02 Tue	Introduction to LLM social simulation and agent-based modeling
09/04 Thu	Bias and diversity Santurkar et al (ICML 2023): "Whose Opinions Do Language Models Reflect?" Bisbee et al (Political Analysis 2024): "Synthetic Replacements for Human Survey Data? The Perils of Large Language Models"
09/09 Tue	Steerability: fine-tuning, steering vectors Chu et al (arXiv 2023): "Language Models Trained on Media Diets Can Predict Public Opinion" Kim et al (ICLR 2025): "Linear Representations of Political Perspective Emerge in Large Language Models"
09/11 Thu	Validation and generalization Hewitt et al (preprint 2024): "Predicting results of social science experiments using large language models" Binz et al (Nature 2025): "A foundation model to predict and capture human cognition"
09/16 Tue	GUEST LECTURE: Joon Sung Park Park et al (UIST 2023): "Generative Agents: Interactive Simulacra of Human Behavior" Park et al (arXiv 2024): "Generative Agent Simulations of 1,000 People"
09/18 Thu	Limits to prediction Salganik et al (PNAS 2020): "Measuring the predictability of life outcomes with a scientific mass collaboration" Lundberg et al (PNAS 2024): "The origins of unpredictability in life outcome prediction tasks"
09/23 Tue	Social interactions and networks Zhou et al (ICLR 2024): "SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents" Jia et al (NeurIPS 2024): "Can Large Language Model Agents Simulate Human Trust Behavior?"
09/25 Thu	Agent-based modeling and policy-planning Aleta et al (Nature Hum Behav 2020): "Modelling the impact of testing, contact tracing and household quarantine on second waves of COVID-19" Chopra et al (AAMAS 2025): "On the Limits of Agency in Agent-based Models"
Unit II. Algorithmically Infused Societies
09/30 Tue	Recommendation systems Su et al (WWW 2016): "The Effect of Recommendations on Network Structure" Chaney et al (RecSys 2018): "How algorithmic confounding in recommendation systems increases homogeneity and decreases utility" Also see Wagner et al (Nature 2021): "Measuring algorithmically infused societies"
10/02 Thu	Social media algorithms Huszár et al (PNAS 2021): "Algorithmic amplification of politics on Twitter" Guess et al (Science 2023): "How do social media feed algorithms affect attitudes and behavior in an election campaign?"
10/07 Tue	GUEST LECTURE: Jonathan Stray Thorburn et al (Medium 2023): "When You Hear 'Filter Bubble', 'Echo Chamber', or 'Rabbit Hole' — Think 'Feedback Loop'" Stray et al (Knight First Amendment Institute 2023): "The Algorithmic Management of Polarization and Violence on Social Media"
10/09 Thu	Algorithmic awareness & strategic behavior Eslami et al (CHI 2016): "First I 'like' it, then I hide it: Folk Theories of Social Feeds" Hron et al (ICLR 2023): "Modeling content creator incentives on algorithm-curated platforms"
10/14 Tue	Algorithms for human decision-making I Lakkaraju et al (KDD 2017): "The Selective Labels Problem: Evaluating Algorithmic Predictions in the Presence of Unobservables" Perdomo et al (ICML 2020): "Performative Prediction" Also see Kleinberg et al (QJE 2018): "Human Decisions and Machine Predictions"
10/16 Thu	Algorithms for human decision-making II Kleinberg et al (American Economic Review 2015): "Prediction Policy Problems" Wang et al (ACM Journal on Responsible Computing 2024): "Against Predictive Optimization: On the Legitimacy of Decision-making Algorithms That Optimize Predictive Accuracy"
10/21 Tue	GUEST LECTURE: Diag Davenport Agan et al (NBER working paper, 2023): "Automating Automaticity: How the Context of Human Choice Affects the Extent of Algorithmic Bias"
Unit III. Adapting AI to Human Behavior
10/23 Thu	Human-AI interactions in the wild Zhao et al (ICLR 2024): "WildChat: 1M ChatGPT Interaction Logs in the Wild" Handa et al (arXiv 2025): "Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations"
10/28 Tue	Evaluating human-AI interactions Lee et al (TMLR 2023): "Evaluating Human-Language Model Interaction" Collins et al (PNAS 2024): "Evaluating language models for mathematics through interactions"
10/30 Thu	Understanding human intents Shaikh et al (ACL 2025): "Navigating Rifts in Human-LLM Grounding: Study and Benchmark" Wu et al (ICML 2025): "CollabLLM: From Passive Responders to Active Collaborators"
11/04 Tue	Personalization, learning individual preferences Poddar et al (NeurIPS 2024): "Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning" Kirk et al (Nature Mach Intell 2024): "The benefits, risks and bounds of personalizing the alignment of large language models to individuals"
11/06 Thu	GUEST LECTURE: Katie Collins Collins et al (Nature Hum Behav 2024): "Building machines that learn and think with people"
11/11 Tue	Academic and Administrative Holiday
11/13 Thu	Human-AI complementarity I Vaccaro et al (Nature Hum Behav 2024): "When combinations of humans and AI are useful: A systematic review and meta-analysis" Zhang et al (FAccT 2020): "Effect of confidence and explanation on accuracy and trust calibration in AI-assisted decision making"
11/18 Tue	Human-AI complementarity II Wilder et al (IJCAI 2020): "Learning to complement humans" Mozannar et al (NeurIPS 2023): "Effective Human-AI Teams via Learned Natural Language Rules and Onboarding"
11/20 Thu	Project presentations
11/25 Tue	Project presentations
11/27 Thu	Thanksgiving Break
12/02 Tue	GUEST LECTURE: Jessy Lin Lin et al (TACL 2024): "Decision-Oriented Dialogue for Human-AI Collaboration"
12/04 Thu	Course wrap-up

Acknowledgements

Course topics were inspired in part by Johan Ugander's course on Social Algorithms and Joon Sung Park's course on AI Agents and Simulations. The course form was adapted from Sewon Min's course on Data-Centric Large Language Models.