Our Research
We conduct human-AI interaction research across the disciplines of computer science, HCI and design. We focus on explainability, interpretability, fairness, data visualization, human-centered AI, and ML for scientific discovery.
Papers | Interactive Blog Posts and Websites
Papers
2024
AutoMix: Automatically Mixing Language Models
Pranjal Aggarwal, Aman Madaan, Ankit Anand, Srividya Pranavi Potharaju, Swaroop Mishra, Pei Zhou, Aditya Gupta, Dheeraj Rajagopal, Karthik Kappaganthu, Yiming Yang, Shyam Upadhyay, Manaal Faruqui, Mausam - NeurIPS 2024
Who’s asking? User personas and the mechanics of latent misalignment
Asma Ghandeharioun*, Ann Yuan*, Marius Guerard, Emily Reif, Michael A. Lepori, Lucas Dixon - NeurIPS 2024
ATTRIB 2024: 2nd Workshop on Attributing Model Behavior at Scale
Tolga Bolukbasi, Logan Engstrom, Andrew Ilyas, Sadhika Malladi, Elisa Nguyen, Sung Min Park - NeurIPS 2024 Workshop
How Far Can We Extract Diverse Perspectives from Large Language Models?
Shirley Anugrah Hayati, Minhwa Lee, Dheeraj Rajagopal, Dongyeop Kang - EMNLP 2024
Scalable Influence and Fact Tracing for Large Language Model Pretraining
Tyler A. Chang, Dheeraj Rajagopal, Tolga Bolukbasi, Lucas Dixon, Ian Tenney - arXiv
LLM Comparator: Interactive Analysis of Side-by-Side Evaluation of Large Language Models
Minsuk Kahng, Ian Tenney, Mahima Pushkarna, Michael Xieyang Liu, James Wexler, Emily Reif, Krystal Kallarackal, Minsuk Chang, Michael Terry, Lucas Dixon - IEEE VIS 2024
LLM Attributor: Interactive Visual Attribution for LLM Generation
Seongmin Lee, Zijie J. Wang, Aishwarya Chakravarthy, Alec Helbling, ShengYun Peng, Mansi Phute, Duen Horng Chau, Minsuk Kahng - IEEE VIS 2024 Poster
The Moral Turing Test: Evaluating Human-LLM Alignment in Moral Decision-Making
Basile Garcia, Crystal Qian, Stefano Palminteri - arXiv
Automata-based constraints for language model decoding
Terry Koo, Frederick Liu, Luheng He - COLM 2024
In Situ AI Prototyping: Infusing Multimodal Prompts into Mobile Settings with MobileMaker
Michael Xieyang Liu*, Savvas Petridis*, Alex Fiannaca, Vivian Tsai, Michael Terry, Carrie Cai - VL/HCC 2024
ConstitutionalExperts: Training a Mixture of Principle-based Prompts
Savvas Petridis*, Ben Wedin*, Ann Yuan*, James Wexler, Nithum Thain - ACL 2024
Gemma 2: Improving Open Language Models at a Practical Size
Gemma Team (including Lucas Dixon, Minsuk Kahng, Ryan Mullins) - arXiv
Can Generative Multimodal Models Count to Ten?
Sunayana Rane, Alexander Ku, Jason Baldridge, Ian Tenney, Tom Griffiths, Been Kim - CogSci 2024
A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity
Andrew Lee, Xiaoyan Bai, Itamar Pres, Martin Wattenberg, Jonathan K. Kummerfeld, Rada Mihalcea - ICML 2024
Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
Asma Ghandeharioun, Avi Caciularu, Adam Pearce, Lucas Dixon, Mor Geva - ICML 2024
Interpretability Illusions in the Generalization of Simplified Models
Dan Friedman, Andrew Lampinen, Lucas Dixon, Danqi Chen, Asma Ghandeharioun - ICML 2024
Decoding-time Realignment of Language Models
Tianlin Liu, Shangmin Guo, Leonardo Bianco, Daniele Calandriello, Quentin Berthet, Felipe Llinares, Jessica Hoffmann, Lucas Dixon, Michal Valko, Mathieu Blondel - ICML 2024
Relational Composition in Neural Networks: A Survey and Call to Action
Martin Wattenberg, Fernanda B. Viégas - ICML 2024 Mechanistic Interpretability Workshop
PromptInfuser: How Tightly Coupling AI and UI Design Impacts Designers' Workflows
Savvas Petridis, Michael Terry, Carrie J. Cai - DIS 2024
LaMPost: AI Writing Assistance for Adults with Dyslexia Using Large Language Models
Steven M. Goodman, Erin Buehler, Patrick Clary, Andy Coenen, Aaron Donsbach, Tiffanie N. Horne, Michal Lahav, Robert MacDonald, Rain Breaw Michaels, Ajit Narayanan, Mahima Pushkarna, Joel Riley, Alex Santana, Lei Shi, Rachel Sweeney, Phil Weaver, Ann Yuan, and Meredith Ringel Morris - CACM
Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation
Jessica Quaye, Alicia Parrish, Oana Inel, Charvi Rastogi, Hannah Rose Kirk, Minsuk Kahng, Erin van Liemt, Max Bartolo, Jess Tsang, Justin White, Nathan Clement, Rafael Mosquera, Juan Ciro, Vijay Janapa Reddi, Lora Aroyo - FAccT 2024
Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics
Tyler Chang, Jessica Hoffmann, Erin van Liemt, Nithum Thain, Kathy Meier-Hellstern, Lucas Dixon, Katrin Tomanek - LREC-COLING 2024
Farsight: Fostering Responsible AI Awareness During AI Application Prototyping
Jay Wang, Chinmay Kulkarni, Lauren Wilcox, Michael Terry, Michael Madaio - CHI 2024
From Provenance to Aberrations: Image Creator and Screen Reader User Perspectives on Alt Text for AI-Generated Images
Maitraye Das, Alexander J. Fiannaca, Meredith Ringel Morris, Shaun K. Kane, Cynthia L. Bennett - CHI 2024
Automatic Histograms: Leveraging Language Models for Text Dataset Exploration
Emily Reif, Crystal Qian, James Wexler, Minsuk Kahng - CHI 2024 EA
LLM Comparator: Visual Analytics for Side-by-Side of Evaluation of Large Language Models
Minsuk Kahng, Ian Tenney, Mahima Pushkarna, Michael Xieyang Liu, James Wexler, Emily Reif, Krystal Kallarackal, Minsuk Chang, Michael Terry, Lucas Dixon - CHI 2024 EA
Understanding the Dataset Practitioners Behind Large Language Model Development
Crystal Qian, Emily Reif, Minsuk Kahng - CHI 2024 EA
”We Need Structured Output”: Towards User-centered Constraints on Large Language Model Output
Michael Xieyang Liu, Frederick Liu, Alexander J. Fiannaca, Terry Koo, Lucas Dixon, Michael Terry, Carrie J. Cai - CHI 2024 EA
Designing for Human-Agent Alignment: Understanding what humans want from their agents
Tesh Goyal, Minsuk Chang, Michael Terry - CHI 2024 EA
Believing Anthropomorphism: Examining the Role of Anthropomorphic Cues on Trust in Large Language Models
Michelle Cohn, Mahima Pushkarna, Gbolahan O. Olanubi, Joseph M. Moran, Daniel Padgett, Zion Mengesha, Courtney Heldreth - CHI 2024 EA
Sensemaking: What is it today?
Daniel M. Russell, Laura Koesten, Aniket Kittur, Nitesh Goyal, Pengyi Zhang, Michael Xieyang Liu - CHI 2024 Workshop
Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics
Tyler A. Chang, Katrin Tomanek, Jessica Hoffmann, Nithum Thain, Erin MacMurray van Liemt, Kathleen Meier-Hellstern, Lucas Dixon - LREC-COLING
Interactive Prompt Debugging with Sequence Salience
Ian Tenney, Ryan Mullins, Bin Du, Shree Pandya, Minsuk Kahng, Lucas Dixon - arXiv
Take It, Leave It, or Fix It: Measuring Productivity and Trust in Human-AI Collaboration
Crystal Qian, James Wexler - IUI 2024
ConstitutionMaker: Interactively Critiquing Large Language Models by Converting Feedback into Principles
Savvas Petridis, Benjamin D Wedin, James Wexler, Mahima Pushkarna, Aaron Donsbach, Nitesh Goyal, Carrie J Cai, Michael Terry - IUI 2024
PERL: Parameter Efficient Reinforcement Learning from Human Feedback
Hakim Sidahmed, Samrat Phatale, Alex Hutcheson, Zhuonan Lin, Zhang Chen, Zac Yu, Jarvis Jin, Roman Komarytsia, Christiane Ahlheim, Yonghao Zhu, Simral Chaudhary, Bowen Li, Saravanan Ganesh, Bill Byrne, Jessica Hoffmann, Hassan Mansoor, Wei Li, Abhinav Rastogi, Lucas Dixon - arXiv
ConstitutionalExperts: Training a Mixture of Principle-based Prompts
Savvas Petridis, Ben Wedin, Ann Yuan, James Wexler, Nithum Thain - ACL 2024
A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity
Shayne Longpre, Gregory Yauney, Emily Reif, Katherine Lee, Adam Roberts, Barret Zoph, Denny Zhou, Jason Wei, Kevin Robinson, David Mimno, Daphne Ippolito - NAACL 2024
2023
Visualizing Linguistic Diversity of Text Datasets Synthesized by Large Language Models
Emily Reif, Minsuk Kahng, Savvas Petridis - IEEE VIS 2023
Large language models are competitive near cold-start recommenders for language-and item-based preferences
Scott Sanner, Krisztian Balog, Filip Radlinski, Ben Wedin, Lucas Dixon - RecSys 2023
From Discovery to Adoption: Understanding the ML Practitioners’ Interpretability Journey
Narges Ashtari, Ryan Mullins, Crystal Qian, James Wexler, Ian Tenney, Mahima Pushkarna - DIS 2023
Large Language Models for User Interest Journeys
Konstantina Christakopoulou, Alberto Lalama, Cj Adams, Iris Qu, Yifat Amir, Samer Chucri, Pierce Vollucci, Fabio Soldo, Dina Bseiso, Sarah Scodel, Lucas Dixon, Ed H. Chi, Minmin Chen - arXiv
Large Language Models for User Interest Journeys
Konstantina Christakopoulou, Alberto Lalama, Cj Adams, Iris Qu, Yifat Amir, Samer Chucri, Pierce Vollucci, Fabio Soldo, Dina Bseiso, Sarah Scodel, Lucas Dixon, Ed H. Chi, Minmin Chen - arXiv
Investigating How Practitioners Use Human-AI Guidelines: A Case Study on the People + AI Guidebook
Nur Yildirim, Mahima Pushkarna, Nitesh Goyal, Martin Wattenberg, Fernanda Viégas - CHI 2023
PromptInfuser: Bringing User Interface Mock-ups to Life with Large Language Models
Savvas Petridis, Michael Terry, Carrie Cai - CHI 2023
Programming without a Programming Language: Challenges and Opportunities for Designing Developer Tools for Prompt Programming
Alex Fiannaca, Chinmay Kulkarni, Carrie Cai, Michael Terry - CHI 2023
A Word is Worth a Thousand Pictures: Prompts as AI Design Material
Chinmay Kulkarni, Stefania Druga, Minsuk Chang, Alex Fiannaca, Carrie Cai, Michael Terry - arXiv
The Prompt Artists
Minsuk Chang, Stefania Druga, Alex Fiannaca, Pedro Vergani, Chinmay Kulkarni, Carrie Cai, Michael Terry - arXiv, C&C
DRIP: Domain Refinement Iteration with Polytopes for Backward Reachability Analysis of Neural Feedback Loops
Michael Everett; Rudy Bunel; Shayegan Omidshafiei - IEEE L-CSS
Towards Agile Text Classifiers for Everyone
Maximilian Mozes, Jessica Hoffmann, Katrin Tomanek, Muhamed Kouate, Nithum Thain, Ann Yuan, Tolga Bolukbasi, Lucas Dixon - arXiv
Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning
Maximilian Mozes, Tolga Bolukbasi, Ann Yuan, Frederick Liu, Nithum Thain, Lucas Dixon - arXiv
Simfluence: Modeling the Influence of Individual Training Examples by Simulating Training Runs
Kelvin Guu, Albert Webson, Ellie Pavlick, Lucas Dixon, Ian Tenney, Tolga Bolukbasi - arXiv
KNNs of Semantic Encodings for Rating Prediction
Léo Laugier, Thomas Bonald, Lucas Dixon, Raghuram Vadapalli - arXiv
Large Scale Qualitative Evaluation of Generative Image Model Outputs
Yannick Assogba, Adam Pearce, Madison Elliott - arXiv
Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models
Peter Hase, Mohit Bansal, Been Kim, Asma Ghandeharioun - arXiv
Synthetic APIs: Enabling Language Models to Act as Interlocutors Between Natural Language and Code
Ryan Mullins, Michael Terry - HICSS 2023
2022
Multi-Agent Reinforcement Learning for Microprocessor Design Space Exploration
Srivatsan Krishnan, Natasha Jaques, Shayegan Omidshafiei, Dan Zhang, Izzeddin Gur, Vijay Janapa Reddi, Aleksandra Faust - NeurIPS ML4Sys Workshop 2022
Beyond Rewards: a Hierarchical Perspective on Offline Multiagent Behavioral Analysis
Shayegan Omidshafiei, Andrei Kapishnikov, Yannick Assogba, Lucas Dixon, Been Kim - NeurIPS 2022
Concept-based Understanding of Emergent Multi-Agent Behavior
Niko Grupen, Natasha Jaques, Been Kim, Shayegan Omidshafiei - NeurIPS DeepRL Workshop 2022
Acquisition of chess knowledge in AlphaZero
Thomas McGrath,Andrei Kapishnikov, Nenad Tomaševa, Adam Pearce, Martin Wattenberg, Demis Hassabis, Been Kim, Ulrich Paquet, and Vladimir Kramnik - PNAS
Is Your Toxicity My Toxicity? Exploring the Impact of Rater Identity on Toxicity Annotation
Tesh Goyal, Ian Kivlichan, Rachel Rosen, Lucy Vasserman - CSCW 2022
Toxicity detection sensitive to conversational context
- First Monday
On natural language user profiles for transparent and scrutable recommendation
Filip Radlinski, Krisztian Balog, Fernando Diaz, Lucas Dixon, Ben Wedin - ACM SIGIR 2022
Towards Tracing Knowledge in Language Models Back to the Training Data
Ekin Akyurek, Tolga Bolukbasi, Frederick Liu, Binbin Xiong, Ian Tenney, Jacob Andreas, Kelvin Guu - Findings of EMNLP 2022
A Systematic Review and Thematic Analysis of Community-Collaborative Approaches to Computing Research
Ned Cooper Tiffanie Horne Gillian Hayes Courtney Heldreth Michal Lahav Jess Scon Holbrook Lauren Wilcox - CHI 2022
"You have to prove the threat is real": Understanding the needs of Female Journalists and Activists to Document and Report Online Harassment.
Tesh Goyal, Leslie Park, Lucy Vasserman - CHI 2022
Whose AI Dream? In search of the aspiration in data annotation
Ding Wang, Shantanu Prabhat, Nithya Sambasivan - CHI 2022
“Because AI is 100% right and safe”: User Vulnerabilities and Sources of AI Authority in India
Shivani Kapania, Oliver Siy, Gabe Clapper, Azhagu SP, Nithya Sambasivan - CHI 2022
Deskilling of Domain Expertise in AI Development
Nithya Sambasivan, Rajesh Veeraraghavan - CHI 2022
When is ML Data Good? Datafication in Public Health in India
Divy Thakkar*, Azra Ismail*, Alex Hanna, Pratyush Kumar, Nithya Sambasivan, Neha Kumar - CHI 2022
PromptChainer: Chaining Large Language Model Prompts through Visual Programming
Tongshuang Wu, Ellen Jiang, Aaron Donsbach, Jeff Gray, Alejandra Molina, Michael Terry, Carrie J Cai - CHI 2022
AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts
Tongshuang Wu, Michael Terry, Carrie J Cai - CHI 2022
Discovering the Syntax and Strategies of Natural Language Programming with Generative Language Models
Ellen Jiang, Edwin Toh, Alejandra Molina, Kristen Olson, Claire Kayacik, Aaron Donsbach, Carrie J Cai, Michael Terry - CHI 2022
Prompt-based Prototyping with Large Language Models
Ellen Jiang, Kristen Olson, Edwin Toh, Alejandra Molina, Aaron Donsbach, Michael Terry, Carrie J Cai - CHI 2022
DISSECT: Disentangled Simultaneous Explanations via Concept Traversals
Asma Ghandeharioun, Been Kim, Chun-Liang Li, Brendan Jou, Brian Eoff, Rosalind W. Picard - ICLR 2022
Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AI
Mahima Pushkarna, Andrew Zaldivar, Oddur Kjartansson - FAccT 2022
Wordcraft: Story Writing With Large Language Models
Ann Yuan, Andy Coenen, Emily Reif, Daphne Ippolito - IUI 2022
IMACS: Image Model Attribution Comparison Summaries
Eldon Schoop, Ben Wedin, Andrei Kapishnikov, Tolga Bolukbasi, Michael Terry - arXiv 2022
SynthBio: A Case Study in Faster Curation of Text Datasets
Ann Yuan, Daphne Ippolito, Vitaly Nikolaev, Chris Callison-Burch, Andy Coenen, Sebastian Gehrmann - NeurIPS Datasets and Benchmarks 2021
2021
Designerly Tele-Experiences: a New Approach to Remote Yet Still Situated Co-Design
Ferran Altarriba Bertran, Alexandra Pometko, Muskan Gupta, Lauren Wilcox, Reeta Banerjee, Katherine Isbister - TOCHI
Specialized Healthsheet for Healthcare Datasets
Negar Rostamzadeh, Subhrajit Roy, Diana Mincu, Andrew Smart, Lauren Wilcox, Mahima Pushkarna, Razvan Amironesei, Jessica Schrouff, Madeleine Elish, Nyalleng Moorosi, Berk Ustun, Noah Broesti, Katherine Heller: - ML4Health 2021
Toxicity Detection can be Sensitive to the Conversational Context
Alexandros Xenos, John Pavlopoulos, Ion Androutsopoulos, Lucas Dixon, Jeffrey Sorensen, Leo Laugier - arxiv
A Recipe For Arbitrary Text Style Transfer with Large Language Models
Emily Reif, Daphne Ippolito, Ann Yuan, Andy Coenen, Chris Callison-Burch, Jason Wei - ICLR 2022
GenLine and GenForm: Two Tools for Interacting with Generative Language Models in a Code Editor
Ellen Jiang, Edwin Toh, Alejandra Molina, Aaron Donsbach, Carrie Cai, Michael Terry - UIST 2021
Augmenting the User-Item Graph with Textual Similarity Models
Federico López, Martin Scholz, Jessica Yung, Marie Pellat, Michael Strube, Lucas Dixon - arXiv
A Gentle Introduction to Graph Neural Networks
Benjamin Sanchez-Lengeling, Emily Reif, Adam Pearce, Alexander B. Wiltschko - Distll
Program Synthesis with Large Language Models
Jacob Austin, Augustus Odena, Maxwell Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie Cai, Michael Terry, Quoc Le, Charles Sutton - arXiv
Guided Integrated Gradients: An Adaptive Path Method for Removing Noise
Andrei Kapishnikov, Subhashini Venugopalan, Besim Avci, Ben Wedin, Michael Terry, Tolga Bolukbasi - CVPR 2021
Isolation in Coordination: Challenges of Caregivers in the USA.
Mark Schurgin, Mark Schlager, Laura Vardoulakis, Laura Pina, Lauren Wilcox - CHI 2021
Breakdowns and Breakthroughs: Observing Musicians' Responses to the COVID-19 Pandemic
Carrie Cai, Michelle Carney, Nida Zada, Michael Terry - CHI 2021
AI as Social Glue: Uncovering the Roles of Deep Generative AI during Social Music Composition
Mia Suh, Emily Youngbloom, Michael Terry, Carrie Cai - CHI 2021
Onboarding Materials as Cross-functional Boundary Objects for Developing AI Assistants
Cai, Winter, Steiner, Wilcox, Terry - CHI 2021
"Everyone wants to do the model work, not the data work": Data Cascades in High-Stakes AI
Nithya Sambasivan, Shivani Kapania, Hannah Highfill, Diana Akrong, Praveen Paritosh, Lora Aroyo - CHI 2021
“Brilliant AI Doctor” in Rural Clinics: Challenges in AI-Powered Clinical Decision Support System Deployment
Dakuo Wang, Liuping Wang, Zhan Zhang, Ding Wang, Haiyi Zhu, Yvonne Gao, Xiangmin Fan, Feng Tian - CHI 2021
An Interpretability Illusion for BERT
Tolga Bolukbasi, Adam Pearce, Ann Yuan, Andy Coenen, Emily Reif, Fernanda Viégas, Martin Wattenberg - arXiv
Civil rephrases of toxic texts with self-supervised transformers
L Laugier, I Pavlopoulos, J Sorensen, L Dixon - EACL 2021
Re-imagining Algorithmic Fairness in India and Beyond
Nithya Sambasivan, Erin Arnesen, Ben Hutchinson, Tulsee Doshi, Vinodkumar Prabhakaran - FAacT 2021
2020
Evaluating Attribution for Graph Neural Networks
Sanchez-Lengeling, Wei, Lee, Reif, Wang, Qian, McCloskey, Colwell, Wiltschko - NeurIPS 2020
The Language Interpretability Tool: Interactive Exploration, Explanation, and Counterfactual Analysis of NLP models
Tenney, Wexler, Bastings, Bolukbasi, Coenen, Gehrmann, Jiang, Pushkarna, Radebaugh, Reif, Yuan - EMNLP 2020
Non-portability of Algorithmic Fairness in India
Sambasivan, Arnesen, Hutchinson, Prabhakaran - NeurIPS 2020 workshop
Six Attributes of Unhealthy Conversation
I Price, J Gifford-Moore, J Flemming, S Musker, M Roichman, G Sylvain, L Dixon - WOAH 2020 workshop paper
Artificial intelligence assistance improves Gleason grading of prostate needle core biopsies
David F. Steiner, Kunal Nagpal, Rory Sayres, Davis J. Foote, Benjamin D. Wedin, Adam Pearce, Carrie J. Cai, Samantha R. Winter, Matthew Symonds, Liron Yatziv, Andrei Kapishnikov, Trissia Brown, Isabelle Flament-Auvigne, Fraser Tan, Martin C. Stumpe, Pan-Pan Jiang, Yun Liu, Po-Hsuan Cameron Chen, Greg S. Corrado, Michael Terry, Craig H. Mermel - JAMA Open Network 2020
Evaluation of the Use of Combined Artificial Intelligence and Pathologist Assessment to Review and Grade Prostate Biopsies.
Steiner, Nagpal, Sayres, Foote, Wedin, Pearce, Cai, Winter, Symonds, Yatziv, Kapishnikov, Brown, Flament, Tan, Stumpe, Jiang, Liu, Chen, Corrado, Terry, Mermel - JAMA Open Network 2020
Debugging Tests for Model Explanations
Julius Adebayo, Michael Muelly, Ilaria Liccardi, Been Kim - NeurIPS / WHI 2020
Beyond the Portal: Re-imagining the Post-pandemic Future of Work
Thakkar, Kumar, Sambasivan - ACM interactions 27(6) 2020
AI Song Contest: Human-AI Co-Creation in Songwriting
Cheng-Zhi Anna Huang, Hendrik Vincent Koops, Ed Newton-Rex, Monica Dinculescu, Carrie J. Cai - ISMIR 2020
On the Making and Breaking of Social Music Improvisation during the COVID-19 Pandemic
Carrie J. Cai, Michael Terry - New Future of Work Symposium 2020
Concept Bottleneck Models
Pang Wei Koh, Thao Nguyen, Yew Siang Tang, Stephen Mussmann, Emma Pierson, Been Kim, Percy Liang - ICML 2020
Neural Networks Trained on Natural Scenes Exhibit Gestalt Closure
Kim, Reif, Wattenberg, Bengio, Mozer - Computational Brain & Behavior
Toxicity Detection: Does Context Really Matter?
Pavlopoulos, Sorensen, Dixon, Thain, Androutsopoulos - ACL 2020
Towards an AI-powered Future that Works for Vocational Workers
Thakkar, Kumar, Sambasivan - CHI 2020
Classifying Constructive Comments
Kolhatkar, Thain, Sorensen, Dixon, Taboada - Special Issue Journal, WWW, ALW, 2020
On Completeness-aware Concept-Based Explanations in Deep Neural Networks
Chih-Kuan Yeh, Been Kim, Sercan O. Arik, Chun-Liang Li, Tomas Pfister, Pradeep Ravikumar - NeurIPS 2020
Expert Discussions Improve Comprehension of Difficult Cases in Medical Image Assessment
Mike Shaekerman, Carrie Cai, Abigail Huang, Rory Sayres - CHI 2020
Novice-AI Music Co-Creation via AI-Steering Tools for Deep Generative Nets
Ryan Louie, Andy Coenen, Anna Huang, Michael Terry, Carrie Cai - CHI 2020
2019
AI in Nigeria
Courtney Heldreth, Fernanda Viégas, Titi Akinsanmi, Diana Akrong
A Benchmark for Interpretability Methods in Deep Neural Networks
Sara Hooker, Dumitru Erhan, Pieter-Jan Kindermans, Been Kim - NeurIPS 2019
"Hello AI": Uncovering the Onboarding Needs of Medical Practitioners for Human-AI Collaborative Decision-Making
Carrie J. Cai, Samantha Winter, David Steiner, Lauren Wilcox, Michael Terry - CSCW
Human Evaluation of Models Built for Interpretability
Isaac Lage, Emily Chen, Jeffrey He, Menaka Narayanan, Been Kim, Samuel Gershman and Finale Doshi-Velez - HCOMP 2019
Software Developers Learning Machine Learning: Motivations, Hurdles, and Desires
Carrie J. Cai, Philip J. Guo - VLHCC 2019
XRAI: Better Attributions Through Regions
Andrei Kapishnikov, Tolga Bolukbasi, Fernanda Viégas, Michael Terry - ICCV 2019
Debiasing Embeddings for Reduced Gender Bias in Text Classification
Flavien Prost, Nithum Thain, Tolga Bolukbasi - ACL
BIM: Towards Quantitative Evaluation of Interpretability Methods with Ground Truth
Mengjiao Yang, Been Kim - arXiv
The Bach Doodle: Approachable music composition with machine learning at scale
Cheng-Zhi Anna Huang, Curtis Hawthorne, Adam Roberts, Monica Dinculescu, James Wexler, Leon Hong, Jacob Howcroft - arXiv
The What-If Tool: Interactive Probing of Machine Learning Models
James Wexler, Mahima Pushkarna, Tolga Bolukbasi, Martin Wattenberg, Fernanda Viégas, Jimbo Wilson - VIS 2019
Similar Image Search for Histopathology: SMILY
Narayan Hegde, Jason D. Hipp, Yun Liu, Michael Emmert-Buck, Emily Reif, Daniel Smilkov, Michael Terry, Carrie J. Cai, Mahul B. Amin, Craig H. Mermel, Phil Q. Nelson, Lily H. Peng, Greg S. Corrado, Martin C. Stumpe - Nature
Visualizing and Measuring the Geometry of BERT
Andy Coenen, Emily Reif, Ann Yuan, Been Kim, Adam Pearce, Fernanda Viégas, Martin Wattenberg - NeurIPS
Do Neural Networks Show Gestalt Phenomena? An Exploration of the Law of Closure
Been Kim, Emily Reif, Martin Wattenberg, Samy Bengio - arXiv
The Effects of Example-based Explanations in a Machine Learning Interface
Carrie J Cai, Jonas Jongejan, Jess Holbrook - IUI 2019
Human-Centered Tools for Coping with Imperfect Algorithms during Medical Decision-Making
Carrie J. Cai, Emily Reif, Narayan Hegde, Jason Hipp, Been Kim, Daniel Smilkov, Martin Wattenberg, Fernanda Viégas, Greg S. Corrado, Martin C. Stumpe, Michael Terry - CHI 2019
Towards Automatic Concept-based Explanations
Amirata Ghorbani, James Wexler, James Zou, Been Kim - NeurIPS
Tensorflow.js: Machine learning for the web and beyond
Daniel Smilkov, Nikhil Thorat, Yannick Assogba, Ann Yuan, Nick Kreeger, Ping Yu, Kangyi Zhang, Shanqing Cai, Eric Nielsen, David Soergel, Stan Bileschi, Michael Terry, Charles Nicholson, Sandeep N. Gupta, Sarah Sirajuddin, D. Sculley, Rajat Monga, Greg Corrado, Fernanda B. Viégas, Martin Wattenberg - SysML
2018
Interpreting Black Box Predictions using Fisher Kernels
Rajiv Khanna, Been Kim, Joydeep Ghosh, Oluwasanmi Koyejo - AISTATS
ClinicalVis: Supporting Clinical Task-Focused Design Evaluation
Marzyeh Ghassemi, Mahima Pushkarna, James Wexler, Jesse Johnson, Paul Varghese - arXiv
Sanity Checks for Saliency Maps
Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow, Moritz Hardt, Been Kim - NeurIPS
GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation
Minsuk Kahng, Nikhil Thorat, Duen Horng Chau, Fernanda Viégas, Martin Wattenberg - VIS 2018
Deep learning of aftershock patterns following large earthquakes
Phoebe M. R. DeVries, Fernanda Viégas, Martin Wattenberg & Brendan J. Meade - Nature
To Trust Or Not To Trust A Classifier
Heinrich Jiang, Been Kim, Melody Y. Guan, Maya Gupta - NeurIPS
Human-in-the-Loop Interpretability Prior
Isaac Lage, Andrew Slavin Ross, Been Kim, Samuel J. Gershman, Finale Doshi-Velez - NeurIPS
Scalable and accurate deep learning with electronic health records
Alvin Rajkomar, Eyal Oren, Kai Chen, Andrew M. Dai, Nissan Hajaj, Michaela Hardt, Peter J. Liu, Xiaobing Liu, Jake Marcus, Mimi Sun, Patrik Sundberg, Hector Yee, Kun Zhang, Yi Zhang, Gerardo Flores, Gavin E. Duggan, Jamie Irvine, Quoc Le, Kurt Litsch, Alexander Mossin, Justin Tansuwan, De Wang, James Wexler, Jimbo Wilson, Dana Ludwig, Samuel L. Volchenboum, Katherine Chou, Michael Pearson, Srinivasan Madabushi, Nigam H. Shah, Atul J. Butte, Michael D. Howell, Claire Cui, Greg S. Corrado & Jeffrey Dean - Nature
2017
Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
Been Kim, Martin Wattenberg, Justin Gilmer, Carrie Cai, James Wexler, Fernanda Viégas, Rory Sayres - ICML 2018
Direct-Manipulation Visualization of Deep Networks
Daniel Smilkov, Shan Carter, D. Sculley, Fernanda B. Viégas, Martin Wattenberg - arXiv
SmoothGrad: removing noise by adding noise
Daniel Smilkov, Nikhil Thorat, Been Kim, Fernanda Viégas, Martin Wattenberg - arXiv
Visualizing Dataflow Graphs of Deep Learning Models in TensorFlow
Kanit Wongsuphasawat, Daniel Smilkov, James Wexler, Jimbo Wilson, Dandelion Mane, Doug Fritz, Dilip Krishnan, Fernanda B. Viégas, and Martin Wattenberg - VIS 2017
What Is Better Than Coulomb Failure Stress? A Ranking of Scalar Static Stress Triggering Mechanisms from 105 Mainshock-Aftershock Pairs
Brendan J. Meade, Phoebe M. R. DeVries, Jeremy Faller, Fernanda Viégas, Martin Wattenberg - Geophysical Research Letters
2016
Interactive Visualization of Spatially Amplified GNSS Time-Series Position Fields
Brendan J. Meade, William T. Freeman, James Wilson, Fernanda Viégas, and Martin Wattenberg
Embedding Projector: Interactive Visualization and Interpretation of Embeddings
Daniel Smilkov, Nikhil Thorat, Charles Nicholson, Emily Reif, Fernanda B. Viégas, Martin Wattenberg - NeurIPS
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Ian Goodfellow, Andrew Harp, Geoffrey Irving, Michael Isard, Yangqing Jia, Rafal Jozefowicz, Lukasz Kaiser, Manjunath Kudlur, Josh Levenberg, Dan Mane, Rajat Monga, Sherry Moore, Derek Murray, Chris Olah, Mike Schuster, Jonathon Shlens, Benoit Steiner, Ilya Sutskever, Kunal Talwar, Paul Tucker, Vincent Vanhoucke, Vijay Vasudevan, Fernanda Viégas, Oriol Vinyals, Pete Warden, Martin Wattenberg, Martin Wicke, Yuan Yu, Xiaoqiang Zheng - arXiv
Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation
Melvin Johnson, Mike Schuster, Quoc V. Le, Maxim Krikun, Yonghui Wu, Zhifeng Chen, Nikhil Thorat, Fernanda Viégas, Martin Wattenberg, Greg Corrado, Macduff Hughes, Jeffrey Dean - ACL
2014
Visualizing Statistical Mix Effects and Simpson's Paradox
Zan Armstrong, Martin Wattenberg - InfoVis 2014
2013
Google+Ripples: a native visualization of information flow
Fernanda Viégas, Martin Wattenberg, Jack Hebert, Geoffrey Borggaard, Alison Cichowlas, Jonathan Feinberg, Jon Orwant, Christopher Wren - WWW
Ad Click Prediction: a View from the Trenches
H. Brendan McMahan, Gary Holt, D. Sculley, Michael Young, Dietmar Ebner, Julian Grady, Lan Nie, Todd Phillips, Eugene Davydov, Daniel Golovin, Sharat Chikkerur, Dan Liu, Martin Wattenberg, Arnar Mar Hrafnkelsson, Tom Boulos, Jeremy Kubica - KDD 2013
2012
Through the looking glass: talking about the world with visualization
Fernanda Viégas & Martin Wattenberg - ACM
2010
Beautiful History: Visualizing Wikipedia (Chapter 11)
Fernanda Viégas & Martin Wattenberg - O'Reilly
Interactive blogposts and websites
Can Large Language Models Explain Their Internal Mechanisms?
Nada Hussein*, Asma Ghandeharioun*, Ryan Mullins, Emily Reif, Jimbo Wilson, Nithum Thain, Lucas Dixon - IEEE VIS 2024, VISxAI
Do Machine Learning Models Memorize or Generalize?
Adam Pearce, Asma Ghandeharioun, Nada Hussein, Nithum Thain, Martin Wattenberg, Lucas Dixon - IEEE VIS 2023, VISxAI
From Confidently Incorrect Models to Humble Ensembles
Nithum Thain, Adam Pearce, Jasper Snoek and Balaji Lakshminarayanan
Searching for Unintended Biases With Saliency
Astrid Bertrand, Adam Pearce and Nithum Thain
How Federated Learning Protects Privacy
Nicole Mitchell and Adam Pearce
Are Model Predictions Probabilities
Nithum Thain, Adam Pearce, Jasper Snoek & Mahima Pushkarna
Datasets Have Worldviews
Dylan Baker
Can a Model Be Differentially Private and Fair?
Adam Pearce
What Have Language Models Learned?
Adam Pearce - IEEE VIS 2021, VISxAI
Measuring Diversity
Adam Pearce, Dylan Baker, Ellen Jiang, Meg Mitchell* and Timnit Gebru*
Why Some Models Leak Data
Adam Pearce and Ellen Jiang
The Language Interpretability Tool (LIT): Interactive Exploration and Analysis of NLP Models
James Wexler, Ian Tenney
How randomized response can help collect sensitive information responsibly
Adam Pearce and Ellen Jiang
Ground Truth: Supporting Farmers with Machine Learning
Courtney Heldreth, Diana Akrong
Explore COVID-19 Symptoms Search Trends
Adam Pearce
Participatory Machine Learning
Fernanda Viegas, Jess Holbrook, Martin Wattenberg
Hidden Bias
Adam Pearce
Measuring Fairness
Adam Pearce
Communicating Model Uncertainty Over Space
Adam Pearce
What does BERT dream of? Deep Dreaming with BERT.
Alex Bäuerle, James Wexler
Depth Predictions in Art
Ellen Jiang, Emily Reif, Been Kim
Understanding UMAP
Andy Coenen, Adam Pearce
Language, Context, and Geometry in Neural Networks, Part II
Andy Coenen, Emily Reif, Ann Yuan, Been Kim, Adam Pearce, Fernanda Viégas, Martin Wattenberg
Language, Context, and Geometry in Neural Networks, Part I
Andy Coenen, Emily Reif, Ann Yuan, Been Kim, Adam Pearce, Fernanda Viégas, Martin Wattenberg
Building SMILY: a Human-centric, Similar-image Search Tool for Pathology
Narayan Hegde, Carrie J. Cai
The Bach Doodle: Celebrating Johann Sebastian Bach
Cheng-Zhi Anna Huang, Curtis Hawthorne, Adam Roberts, Monica Dinculescu, James Wexler, Leon Hong, Jacob Howcroft
See how the world draws
Reena Jana, Josh Lovejoy,
How to Use t-SNE Effectively
Martin Wattenberg, Fernanda Viégas, Ian Johnson - Distill
Attacking discrimination with smarter machine learning
Martin Wattenberg, Fernanda Viégas, Moritz Hardt
Design and Redesign in Data Visualization
Fernanda Viégas, Martin Wattenberg
Luscious
Fernanda Viégas & Martin Wattenberg
