CS 294-286: Machine Learning & Human Behavior

University of California, Berkeley | Fall 2025

Instructor: Serina Chang (serinac@berkeley.edu)

Time: TuTh 2:00-3:30pm

Location: Wheeler 200

Office Hours: By appointment

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
09/09 Tue Steerability: fine-tuning, steering vectors
09/11 Thu Validation and generalization
09/16 Tue GUEST LECTURE: Joon Sung Park
09/18 Thu Limits to prediction
09/23 Tue Social interactions and networks
09/25 ThuAgent-based modeling and policy-planning
Unit II. Algorithmically Infused Societies
09/30 Tue Recommendation systems Also see Wagner et al (Nature 2021): "Measuring algorithmically infused societies"
10/02 Thu Social media algorithms
10/07 Tue GUEST LECTURE: Jonathan Stray
10/09 ThuAlgorithmic awareness & strategic behavior
10/14 TueAlgorithms for human decision-making I Also see Kleinberg et al (QJE 2018): "Human Decisions and Machine Predictions"
10/16 ThuAlgorithms for human decision-making II
10/21 Tue GUEST LECTURE: Diag Davenport
Unit III. Adapting AI to Human Behavior
10/23 ThuHuman-AI interactions in the wild
10/28 TueEvaluating human-AI interactions
10/30 ThuUnderstanding human intents
11/04 TuePersonalization, learning individual preferences
11/06 ThuGUEST LECTURE: Katie Collins
11/11 TueAcademic and Administrative Holiday
11/13 ThuHuman-AI complementarity I
11/18 TueHuman-AI complementarity II
11/20 ThuProject presentations
11/25 TueProject presentations
11/27 ThuThanksgiving Break
12/02 Tue GUEST LECTURE: Jessy Lin
12/04 ThuCourse 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.