Tatsunori Hashimoto

Assistant Professor, Stanford

thashim [AT] stanford.edu

Bio

I am currently an assistant professor at the computer science department in Stanford university.

My research uses tools from statistics to make machine learning systems more robust and trustworthy — especially in complex systems such as large language models. The goal of my research is to use robustness and worst-case performance as a lens to understand and make progress on several fundamental challenges in machine learning and natural language processing. A few topics of recent interest are,

Long-tail behavior
How can we ensure that a machine learning system won't fail catastrophically in the wild under changing conditions?
Understanding
A system which understands how to answer questions or generate text should also do so robustly out-of-domain.
Fairness
Machine learning systems which rely on unreliable correlations can result in spurious and harmful predictions.

Previously, I was a post-doc at Stanford working for John C. Duchi and Percy Liang on tradeoffs between the average and worst-case performance of machine learning models. Before my post-doc, I was a graduate student at MIT co-advised by Tommi Jaakkola and David Gifford and a undergraduate student at Harvard in statistics and math advised by Edoardo Airoldi.

Advisees

Niladri Chatterji (2021-) SAIL Postdoc (w/ Percy Liang)

Yu Sun (2023-) Postdoc (w/ Sanmi Koyejo and Carlos Guestrin)

Lisa Li (2021-) Graduate Student (w/ Percy Liang)

Xuechen Li (2021-) Graduate Student (w/ Carlos Guestrin)

Rohan Taori (2021-) Graduate Student

Tianyi Zhang (2021-) Graduate Student

Yann Dubois (2022-) Graduate Student (w/ Percy Liang)

Neil Band (2023-) Graduate Student (w/ Tengyu Ma)

Nicole Meister (2023-) Graduate Student

Publications

Most recent publications on Google Scholar.

Robust Distortion-free Watermarks for Language Models PDF

Rohith Kuditipudi, John Thickstun, Tatsunori Hashimoto, Percy Liang

ArXiv preprint

Likelihood-Based Diffusion Language Models PDF

Ishaan Gulrajani, Tatsunori B. Hashimoto

ArXiv preprint

AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback PDF

Yann Dubois, Xuechen Li, Rohan Taori, Tianyi Zhang, Ishaan Gulrajani, Jimmy Ba, Carlos Guestrin, Percy Liang, Tatsunori B Hashimoto

ArXiv preprint

Whose Opinions Do Language Models Reflect? PDF

Shibani Santurkar, Esin Durmus, Faisal Ladhak, Cinoo Lee, Percy Liang, Tatsunori Hashimoto

International Conference on Machine Learning (ICML 2023, oral)

Data Feedback Loops: Model-driven Amplification of Dataset Biases PDF

Rohan Taori, Tatsunori B Hashimoto

International Conference on Machine Learning (ICML 2023, oral)"

Foundation Models and Fair Use PDF

Peter Henderson, Xuechen Li, Dan Jurafsky, Tatsunori Hashimoto, Mark A Lemley, Percy Liang

ArXiv preprint

Navigating the Grey Area: Expressions of Overconfidence and Uncertainty in Language Models PDF

Kaitlyn Zhou, Dan Jurafsky, Tatsunori Hashimoto

ArXiv preprint

Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks PDF

Daniel Kang, Xuechen Li, Ion Stoica, Carlos Guestrin, Matei Zaharia, Tatsunori Hashimoto

ArXiv preprint

Evaluating Self-Supervised Learning via Risk Decomposition PDF

Yann Dubois, Tatsunori Hashimoto, Percy Liang

International Conference on Machine Learning (ICML 2023, oral)

Benchmarking Large Language Models for News Summarization PDF

Tianyi Zhang, Faisal Ladhak, Esin Durmus, Percy Liang, Kathleen McKeown, Tatsunori B Hashimoto

ArXiv preprint

Tracing and Removing Data Errors in Natural Language Generation Datasets PDF

Faisal Ladhak, Esin Durmus, Tatsunori Hashimoto

ArXiv preprint

Is a caption worth a thousand images? a controlled study for representation learning PDF

Shibani Santurkar, Yann Dubois, Rohan Taori, Percy Liang, Tatsunori Hashimoto

International Conference on Learning Representations (ICLR 2023)

Diffusion-LM Improves Controllable Text Generation PDF

Lisa Li, John Thickstun, Ishaan Gulrajani, Percy Liang, Tatsunori B Hashimoto

Advances in Neural Information Processing Systems 31 (NeurIPS 2022)

Identifiability Conditions for Domain Adaptation PDF

Ishaan Gulrajani, Tatsunori B Hashimoto

International Conference on Machine Learning (ICML 2022)

Undersampling is a Minimax Optimal Robustness Intervention in Nonparametric Classification PDF

Niladri Chatterji, Saminul Haque, Tatsunori B Hashimoto

ArXiv preprint

TempLM: Distilling Language Models into Template-Based Generators PDF

Tianyi Zhang, Mina Lee, Lisa Li, Ende Shen, Tatsunori B Hashimoto

ArXiv preprint

Jury learning: Integrating dissenting voices into machine learning models PDF

Mitchell Gordon, Michelle Lam, Joon Park, Kayur Patel, Jeff Hancock, Tatsunori B Hashimoto, Michael Bernstein

Conference on Human Factors in Computing Systems (CHI 2022, Best paper)

Spurious Correlations in Reference-Free Evaluation of Text Generation PDF

Esin Durmus, Faisal Ladhak, Tatsunori B Hashimoto

Annual Meeting of the Association of Computational Linguistics (ACL 2022)

Large Language Models Can Be Strong Differentially Private Learners PDF

Xuechen Li, Florian Tramer, Percy Liang, Tatsunori B Hashimoto

International Conference on Learning Representations (ICLR 2022 Oral)

Is Importance Weighting Incompatible with Interpolating Classifiers? PDF

Ke A Wang, Niladri S Chatterji, Saminul Haque, Tatsunori B Hashimoto

International Conference on Learning Representations (ICLR 2022)

Distributionally Robust Models with Parametric Likelihood Ratios PDF

Paul Michel, Tatsunori B Hashimoto, Graham Neubig

International Conference on Learning Representations (ICLR 2022)

Extending the WILDS Benchmark for Unsupervised Adaptation PDF

Shiori Sagawa, Pang Wei Koh [...] Tatsunori Hashimoto, Sergey Levine, Chelsea Finn, Percy Liang

International Conference on Learning Representations (ICLR 2022 Oral)

Model Performance Scaling with Multiple Data Sources PDF

Tatsunori B Hashimoto

International Conference on Machine Learning (ICML 2021)

On the Inductive Bias of Masked Language Modeling: From Statistical to Syntactic Dependencies PDF

Tianyi Zhang, Tatsunori B Hashimoto

Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2021)

Improved Natural Language Generation via Loss Truncation PDF

Daniel Kang, Tatsunori B Hashimoto

Annual Meeting of the Association of Computational Linguistics (ACL 2020)

Robustness to Spurious Correlations via Human Annotations PDF

Megha Srivastava, Tatsunori B Hashimoto, Percy Liang

International Conference on Machine Learning (ICML 2020)

Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-case Generalization PDF

Shiori Sagawa*, Pang Wei Koh*, Tatsunori B Hashimoto, Percy Liang

International Conference on Learning Representations (ICLR 2020)

Distributionally Robust Losses For Latent Covariate Mixtures PDF

John C Duchi, Tatsunori B Hashimoto, Hongseok Namkoong

Operations Research (2022)

Unifying Human and Statistical Evaluation for Natural Language Generation PDF

Tatsunori B Hashimoto*, Hugh Zhang*, Percy Liang

Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2019)

Generating Sentences by Editing Prototypes PDF

Kelvin Guu*, Tatsunori B Hashimoto*, Yonatan Oren, Percy Liang

Transactions of the Association of Computational Linguistics (TACL, presented at ACL 2018)

Fairness Without Demographics in Repeated Loss Minimization PDF

Tatsunori B Hashimoto, Megha Srivastava, Hongseok Namkoong, Percy Liang

Proceedings of the 35th International Conference on Machine Learning (ICML 2018, Best paper runner up)

Word embeddings as metric recovery in semantic spaces PDF

Tatsunori B Hashimoto, David Alvarez-Melis, Tommi S Jaakkola

Transactions of the Association for Computational Linguistics 4 (TACL, presented at ACL 2016)

Metric recovery from directed unweighted graphs PDF

Tatsunori B Hashimoto, Yi Sun, Tommi S Jaakkola

Artificial Intelligence and Statistics (AISTATS 2015), (best poster at NeurIPS 2014 workshop on networks)

Robust Distortion-free Watermarks for Language Models PDF

Rohith Kuditipudi, John Thickstun, Tatsunori Hashimoto, Percy Liang

ArXiv preprint

One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention PDF

Arvind Mahankali, Tatsunori B. Hashimoto, Tengyu Ma

ArXiv preprint

Likelihood-Based Diffusion Language Models PDF

Ishaan Gulrajani, Tatsunori B. Hashimoto

ArXiv preprint

AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback PDF

Yann Dubois, Xuechen Li, Rohan Taori, Tianyi Zhang, Ishaan Gulrajani, Jimmy Ba, Carlos Guestrin, Percy Liang, Tatsunori B Hashimoto

ArXiv preprint

When Do Pre-Training Biases Propagate to Downstream Tasks? A Case Study in Text Summarization PDF

Faisal Ladhak, Esin Durmus, Mirac Suzgun, Tianyi Zhang, Dan Jurafsky, Kathleen Mckeown, Tatsunori B Hashimoto

Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023)

Whose Opinions Do Language Models Reflect? PDF

Shibani Santurkar, Esin Durmus, Faisal Ladhak, Cinoo Lee, Percy Liang, Tatsunori Hashimoto

International Conference on Machine Learning (ICML 2023, oral)

Data Feedback Loops: Model-driven Amplification of Dataset Biases PDF

Rohan Taori, Tatsunori B Hashimoto

International Conference on Machine Learning (ICML 2023, oral)"

Foundation Models and Fair Use PDF

Peter Henderson, Xuechen Li, Dan Jurafsky, Tatsunori Hashimoto, Mark A Lemley, Percy Liang

ArXiv preprint

Navigating the Grey Area: Expressions of Overconfidence and Uncertainty in Language Models PDF

Kaitlyn Zhou, Dan Jurafsky, Tatsunori Hashimoto

ArXiv preprint

Out-of-Domain Robustness via Targeted Augmentations PDF

Irena Gao, Shiori Sagawa, Pang Wei Koh, Tatsunori Hashimoto, Percy Liang

International Conference on Machine Learning (ICML 2023)

Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks PDF

Daniel Kang, Xuechen Li, Ion Stoica, Carlos Guestrin, Matei Zaharia, Tatsunori Hashimoto

ArXiv preprint

Evaluating Self-Supervised Learning via Risk Decomposition PDF

Yann Dubois, Tatsunori Hashimoto, Percy Liang

International Conference on Machine Learning (ICML 2023, oral)

Benchmarking Large Language Models for News Summarization PDF

Tianyi Zhang, Faisal Ladhak, Esin Durmus, Percy Liang, Kathleen McKeown, Tatsunori B Hashimoto

ArXiv preprint

Tracing and Removing Data Errors in Natural Language Generation Datasets PDF

Faisal Ladhak, Esin Durmus, Tatsunori Hashimoto

ArXiv preprint

Privacy-Preserving Domain Adaptation of Semantic Parsers PDF

Fatemehsadat Mireshghallah, Richard Shin, Yu Su, Tatsunori Hashimoto, Jason Eisner

ArXiv preprint

Coder Reviewer Reranking for Code Generation PDF

Tianyi Zhang, Tao Yu, Tatsunori B Hashimoto, Mike Lewis, Wen-tau Yih, Daniel Fried, Sida I Wang

International Conference on Machine Learning (ICML 2023)

ZK-IMG: Attested Images via Zero-Knowledge Proofs to Fight Disinformation PDF

Daniel Kang, Tatsunori Hashimoto, Ion Stoica, Yi Sun

ArXiv preprint

Easily accessible text-to-image generation amplifies demographic stereotypes at large scale PDF

Federico Bianchi, Pratyusha Kalluri, Esin Durmus, Faisal Ladhak, Myra Cheng, Debora Nozza, Tatsunori Hashimoto, Dan Jurafsky, James Zou, Aylin Caliskan

FAccT 2023

Contrastive decoding: Open-ended text generation as optimization PDF

Xiang Lisa Li, Ari Holtzman, Daniel Fried, Percy Liang, Jason Eisner, Tatsunori Hashimoto, Luke Zettlemoyer, Mike Lewis

ArXiv preprint

Scaling up Trustless DNN Inference with Zero-Knowledge Proofs PDF

Daniel Kang, Tatsunori Hashimoto, Ion Stoica, Yi Sun

ArXiv preprint

Is a caption worth a thousand images? a controlled study for representation learning PDF

Shibani Santurkar, Yann Dubois, Rohan Taori, Percy Liang, Tatsunori Hashimoto

International Conference on Learning Representations (ICLR 2023)

A Closer Look at the Calibration of Differentially Private Learners PDF

Hanlin Zhang, Xuechen Li, Prithviraj Sen, Salim Roukos, Tatsunori Hashimoto

ArXiv preprint

Improving self-supervised learning by characterizing idealized representations PDF

Yann Dubois, Tatsunori Hashimoto, Stefano Ermon, Percy Liang

Advances in Neural Information Processing Systems 31 (NeurIPS 2022)

When Does Differentially Private Learning Not Suffer in High Dimensions? PDF

Xuechen Li, Daogao Liu, Tatsunori Hashimoto, Huseyin A. Inan, Janardhan Kulkarni, Yin Tat Lee, Abhradeep Guha Thakurta

Advances in Neural Information Processing Systems 31 (NeurIPS 2022)

Diffusion-LM Improves Controllable Text Generation PDF

Lisa Li, John Thickstun, Ishaan Gulrajani, Percy Liang, Tatsunori B Hashimoto

Advances in Neural Information Processing Systems 31 (NeurIPS 2022)

Identifiability Conditions for Domain Adaptation PDF

Ishaan Gulrajani, Tatsunori B Hashimoto

International Conference on Machine Learning (ICML 2022)

Undersampling is a Minimax Optimal Robustness Intervention in Nonparametric Classification PDF

Niladri Chatterji, Saminul Haque, Tatsunori B Hashimoto

ArXiv preprint

TempLM: Distilling Language Models into Template-Based Generators PDF

Tianyi Zhang, Mina Lee, Lisa Li, Ende Shen, Tatsunori B Hashimoto

ArXiv preprint

Emergent abilities of large language models PDF

Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, Ed H Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, William Fedus

Transactions on Machine Learning Research (2022)

Jury learning: Integrating dissenting voices into machine learning models PDF

Mitchell Gordon, Michelle Lam, Joon Park, Kayur Patel, Jeff Hancock, Tatsunori B Hashimoto, Michael Bernstein

Conference on Human Factors in Computing Systems (CHI 2022, Best paper)

Spurious Correlations in Reference-Free Evaluation of Text Generation PDF

Esin Durmus, Faisal Ladhak, Tatsunori B Hashimoto

Annual Meeting of the Association of Computational Linguistics (ACL 2022)

Large Language Models Can Be Strong Differentially Private Learners PDF

Xuechen Li, Florian Tramer, Percy Liang, Tatsunori B Hashimoto

International Conference on Learning Representations (ICLR 2022 Oral)

Language Modeling via Stochastic Processes PDF

Rose E Wang, Esin Durmus, Noah Goodman, Tatsunori B Hashimoto

International Conference on Learning Representations (ICLR 2022 Oral)

Is Importance Weighting Incompatible with Interpolating Classifiers? PDF

Ke A Wang, Niladri S Chatterji, Saminul Haque, Tatsunori B Hashimoto

International Conference on Learning Representations (ICLR 2022)

Distributionally Robust Models with Parametric Likelihood Ratios PDF

Paul Michel, Tatsunori B Hashimoto, Graham Neubig

International Conference on Learning Representations (ICLR 2022)

Extending the WILDS Benchmark for Unsupervised Adaptation PDF

Shiori Sagawa, Pang Wei Koh [...] Tatsunori Hashimoto, Sergey Levine, Chelsea Finn, Percy Liang

International Conference on Learning Representations (ICLR 2022 Oral)

On the opportunities and risks of foundation models PDF

Rishi Bommasani [.. alphabetical authors ..] Tatsunori Hashimoto [...]

ArXiv preprint

Accelerating approximate aggregation queries with expensive predicates PDF

Daniel Kang, John Guibas, Peter Bailis, Tatsunori B Hashimoto, Yi Sun, Matei Zaharia

ACM Conference on Management of Data (SIGMOD 2022)

Model Performance Scaling with Multiple Data Sources PDF

Tatsunori B Hashimoto

International Conference on Machine Learning (ICML 2021)

Measuring Conversational Uptake: A Case Study on Student-Teacher Interactions PDF

Dorottya Demszky, Jing Liu, Zid Mancenido, Julie Cohen, Heather Hill, Dan Jurafsky, Tatsunori B Hashimoto

Annual Meeting of the Association of Computational Linguistics (ACL 2020)

DReCa: A general task augmentation strategy for few-shot natural language inference PDF

Shikhar Murty, Tatsunori B Hashimoto, Christopher D Manning

Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2021)

On the Inductive Bias of Masked Language Modeling: From Statistical to Syntactic Dependencies PDF

Tianyi Zhang, Tatsunori B Hashimoto

Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2021)

Modeling the Second Player in Distributionally Robust Optimization PDF

Paul Michel, Tatsunori B. Hashimoto, Graham Neubig

International Conference on Learning Representations (ICLR 2021)

Task-agnostic Indexes for Deep Learning-based Queries over Unstructured Data PDF

Daniel Kang, John Guibas, Peter Bailis, Tatsunori Hashimoto, Matei Zaharia

Preprint

The Disagreement Deconvolution: Bringing Machine Learning Performance Metrics In Line With Reality PDF

Mitchell L Gordon, Kaitlyn Zhou, Kayur Patel, Tatsunori B Hashimoto, Michael S Bernstein

Conference on Human Factors in Computing Systems (CHI 2021)

Approximate Selection with Guarantees using Proxies PDF

Daniel Kang*, Edward Gan*, Peter Bailis, Tatsunori B Hashimoto, Matei Zaharia

International Conference on Very Large Data Bases (VLDB 2020)

Improved Natural Language Generation via Loss Truncation PDF

Daniel Kang, Tatsunori B Hashimoto

Annual Meeting of the Association of Computational Linguistics (ACL 2020)

Robustness to Spurious Correlations via Human Annotations PDF

Megha Srivastava, Tatsunori B Hashimoto, Percy Liang

International Conference on Machine Learning (ICML 2020)

Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-case Generalization PDF

Shiori Sagawa*, Pang Wei Koh*, Tatsunori B Hashimoto, Percy Liang

International Conference on Learning Representations (ICLR 2020)

Learning Autocomplete Systems as a Communication Game PDF

Mina Lee, Tatsunori B Hashimoto, Percy Liang

Emergent Communication Workshop at Neural Information Processing Systems (NeurIPS 2019)

Distributionally Robust Language Modeling PDF

Yonatan Oren*, Shiori Sagawa *, Tatsunori B Hashimoto *, Percy Liang

Empirical Methods in Natural Language Processing (EMNLP 2019)

Distributionally Robust Losses For Latent Covariate Mixtures PDF

John C Duchi, Tatsunori B Hashimoto, Hongseok Namkoong

Operations Research (2022)

Inferring Multidimensional Rates of Aging from Cross-Sectional Data PDF

Emma Pierson*, Pang Wei Koh *, Tatsunori B Hashimoto *, Daphne Koller, Jure Lesokevic, Nicholas Eriksson, Percy Liang

22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019)

Unifying Human and Statistical Evaluation for Natural Language Generation PDF

Tatsunori B Hashimoto*, Hugh Zhang*, Percy Liang

Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2019)

A Retrieve-and-Edit Framework for Predicting Structured Outputs PDF

Tatsunori B Hashimoto, Kelvin Guu, Yonatan Oren, Percy Liang

Advances in Neural Information Processing Systems 31 (NeurIPS 2018, Oral)

Generating Sentences by Editing Prototypes PDF

Kelvin Guu*, Tatsunori B Hashimoto*, Yonatan Oren, Percy Liang

Transactions of the Association of Computational Linguistics (TACL, presented at ACL 2018)

Fairness Without Demographics in Repeated Loss Minimization PDF

Tatsunori B Hashimoto, Megha Srivastava, Hongseok Namkoong, Percy Liang

Proceedings of the 35th International Conference on Machine Learning (ICML 2018, Best paper runner up)

Derivative free optimization via repeated classification PDF

Tatsunori B Hashimoto, Steve Yadlowsky, John C Duchi

21st International Conference on Artificial Intelligence and Statistics (AISTATS 2018)

Unsupervised Transformation Learning via Convex Relaxations PDF

Tatsunori B Hashimoto, Percy S Liang, John C Duchi

Advances in Neural Information Processing Systems 30 (NeurIPS 2017)

Continuous representations and models from random walk diffusion limits PDF

Tatsunori B Hashimoto

PhD Thesis, MIT CSAIL, 2016

Word embeddings as metric recovery in semantic spaces PDF

Tatsunori B Hashimoto, David Alvarez-Melis, Tommi S Jaakkola

Transactions of the Association for Computational Linguistics 4 (TACL, presented at ACL 2016)

Learning Population-Level Diffusions with Generative RNNs PDF

Tatsunori B Hashimoto, David Gifford, Tommi S Jaakkola

Proceedings of the 33rd International Conference on Machine Learning (ICML 2016)

From random walks to distances on unweighted graphs PDF

Tatsunori B Hashimoto, Yi Sun, Tommi S Jaakkola

Advances in Neural Information Processing Systems (NeurIPS 2015)

Metric recovery from directed unweighted graphs PDF

Tatsunori B Hashimoto, Yi Sun, Tommi S Jaakkola

Artificial Intelligence and Statistics (AISTATS 2015), (best poster at NeurIPS 2014 workshop on networks)

A synergistic DNA logic predicts genome-wide chromatin accessibility PDF

Tatsunori B Hashimoto*, Richard I Sherwood*, Daniel D Kang*, Nisha Rajagopal, Amira A Barkal, Haoyang Zeng, Bart JM Emons, Sharanya Srinivasan, Tommi S Jaakkola, David K Gifford

Genome research (2016)

Cas9 Functionally Opens Chromatin PDF

Amira A Barkal, Sharanya Srinivasan, Tatsunori B Hashimoto, David K Gifford, Richard I Sherwood

PloS One (2016)

Cloning-free CRISPR PDF

Mandana Arbab, Sharanya Srinivasan, Tatsunori B Hashimoto, Niels Geijsen, Richard I Sherwood

Stem cell reports (2015)

GERV: a statistical method for generative evaluation of regulatory variants for transcription factor binding PDF

Haoyang Zeng, Tatsunori B Hashimoto, Daniel D Kang, David K Gifford

Bioinformatics (2015)

Long-term persistence and development of induced pancreatic beta cells generated by lineage conversion of acinar cells PDF

Weida Li, Claudia Cavelti-Weder, Yinying Zhang, Kendell Clement, Scott Donovan, Gabriel Gonzalez, Jiang Zhu, Marianne Stemann, Ke Xu, Tatsunori B Hashimoto, Takatsugu Yamada, Mio Nakanishi, Yuemei Zhang, Samuel Zeng, David Gifford, Alexander Meissner, Gordon Weir, Qiao Zhou

Nature Biotechnology (2014)

Universal count correction for high-throughput sequencing PDF

Tatsunori B Hashimoto, Matthew D Edwards, David K Gifford

PLoS computational biology (2014)

Discovery of directional and nondirectional pioneer transcription factors by modeling DNase profile magnitude and shape PDF

Richard I Sherwood *, Tatsunori B Hashimoto *, Charles W O'donnell *, Sophia Lewis, Amira A Barkal, John Peter Van Hoff, Vivek Karun, Tommi S Jaakkola, David K Gifford

Nature Biotechnology (2014)

Quantifying condition-dependent intracellular protein levels enables high-precision fitness estimates PDF

Kerry A Geiler-Samerotte, Tatsunori B Hashimoto, Michael F Dion, Bogdan A Budnik, Edoardo M Airoldi, D Allan Drummond

PloS one (2013)

Lineage-based identification of cellular states and expression programs PDF

Tatsunori B Hashimoto, Tommi S Jaakkola, Richard Sherwood, Esteban O. Mazzoni, Hynek Wichterle, David Gifford

Bioinformatics (2012)

Finding drug discovery rules of thumb with bump hunting PDF

Tatsunori B Hashimoto, Matthew Segall

Proceedings of the ACS (2010)

BFL: a node and edge betweenness based fast layout algorithm for large scale networks. PDF

Tatsunori B Hashimoto, Masao Nagasaki, Kaname Kojima, Satoru Miyano

BMC bioinformatics (2009)

Robust Distortion-free Watermarks for Language Models PDF

Rohith Kuditipudi, John Thickstun, Tatsunori Hashimoto, Percy Liang

ArXiv preprint

One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention PDF

Arvind Mahankali, Tatsunori B. Hashimoto, Tengyu Ma

ArXiv preprint

Likelihood-Based Diffusion Language Models PDF

Ishaan Gulrajani, Tatsunori B. Hashimoto

ArXiv preprint

Data Feedback Loops: Model-driven Amplification of Dataset Biases PDF

Rohan Taori, Tatsunori B Hashimoto

International Conference on Machine Learning (ICML 2023, oral)"

Out-of-Domain Robustness via Targeted Augmentations PDF

Irena Gao, Shiori Sagawa, Pang Wei Koh, Tatsunori Hashimoto, Percy Liang

International Conference on Machine Learning (ICML 2023)

Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks PDF

Daniel Kang, Xuechen Li, Ion Stoica, Carlos Guestrin, Matei Zaharia, Tatsunori Hashimoto

ArXiv preprint

Evaluating Self-Supervised Learning via Risk Decomposition PDF

Yann Dubois, Tatsunori Hashimoto, Percy Liang

International Conference on Machine Learning (ICML 2023, oral)

Scaling up Trustless DNN Inference with Zero-Knowledge Proofs PDF

Daniel Kang, Tatsunori Hashimoto, Ion Stoica, Yi Sun

ArXiv preprint

Is a caption worth a thousand images? a controlled study for representation learning PDF

Shibani Santurkar, Yann Dubois, Rohan Taori, Percy Liang, Tatsunori Hashimoto

International Conference on Learning Representations (ICLR 2023)

A Closer Look at the Calibration of Differentially Private Learners PDF

Hanlin Zhang, Xuechen Li, Prithviraj Sen, Salim Roukos, Tatsunori Hashimoto

ArXiv preprint

Improving self-supervised learning by characterizing idealized representations PDF

Yann Dubois, Tatsunori Hashimoto, Stefano Ermon, Percy Liang

Advances in Neural Information Processing Systems 31 (NeurIPS 2022)

When Does Differentially Private Learning Not Suffer in High Dimensions? PDF

Xuechen Li, Daogao Liu, Tatsunori Hashimoto, Huseyin A. Inan, Janardhan Kulkarni, Yin Tat Lee, Abhradeep Guha Thakurta

Advances in Neural Information Processing Systems 31 (NeurIPS 2022)

Identifiability Conditions for Domain Adaptation PDF

Ishaan Gulrajani, Tatsunori B Hashimoto

International Conference on Machine Learning (ICML 2022)

Undersampling is a Minimax Optimal Robustness Intervention in Nonparametric Classification PDF

Niladri Chatterji, Saminul Haque, Tatsunori B Hashimoto

ArXiv preprint

Emergent abilities of large language models PDF

Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, Ed H Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, William Fedus

Transactions on Machine Learning Research (2022)

Large Language Models Can Be Strong Differentially Private Learners PDF

Xuechen Li, Florian Tramer, Percy Liang, Tatsunori B Hashimoto

International Conference on Learning Representations (ICLR 2022 Oral)

Is Importance Weighting Incompatible with Interpolating Classifiers? PDF

Ke A Wang, Niladri S Chatterji, Saminul Haque, Tatsunori B Hashimoto

International Conference on Learning Representations (ICLR 2022)

Distributionally Robust Models with Parametric Likelihood Ratios PDF

Paul Michel, Tatsunori B Hashimoto, Graham Neubig

International Conference on Learning Representations (ICLR 2022)

Extending the WILDS Benchmark for Unsupervised Adaptation PDF

Shiori Sagawa, Pang Wei Koh [...] Tatsunori Hashimoto, Sergey Levine, Chelsea Finn, Percy Liang

International Conference on Learning Representations (ICLR 2022 Oral)

Model Performance Scaling with Multiple Data Sources PDF

Tatsunori B Hashimoto

International Conference on Machine Learning (ICML 2021)

Modeling the Second Player in Distributionally Robust Optimization PDF

Paul Michel, Tatsunori B. Hashimoto, Graham Neubig

International Conference on Learning Representations (ICLR 2021)

Task-agnostic Indexes for Deep Learning-based Queries over Unstructured Data PDF

Daniel Kang, John Guibas, Peter Bailis, Tatsunori Hashimoto, Matei Zaharia

Preprint

Approximate Selection with Guarantees using Proxies PDF

Daniel Kang*, Edward Gan*, Peter Bailis, Tatsunori B Hashimoto, Matei Zaharia

International Conference on Very Large Data Bases (VLDB 2020)

Robustness to Spurious Correlations via Human Annotations PDF

Megha Srivastava, Tatsunori B Hashimoto, Percy Liang

International Conference on Machine Learning (ICML 2020)

Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-case Generalization PDF

Shiori Sagawa*, Pang Wei Koh*, Tatsunori B Hashimoto, Percy Liang

International Conference on Learning Representations (ICLR 2020)

Distributionally Robust Losses For Latent Covariate Mixtures PDF

John C Duchi, Tatsunori B Hashimoto, Hongseok Namkoong

Operations Research (2022)

A Retrieve-and-Edit Framework for Predicting Structured Outputs PDF

Tatsunori B Hashimoto, Kelvin Guu, Yonatan Oren, Percy Liang

Advances in Neural Information Processing Systems 31 (NeurIPS 2018, Oral)

Fairness Without Demographics in Repeated Loss Minimization PDF

Tatsunori B Hashimoto, Megha Srivastava, Hongseok Namkoong, Percy Liang

Proceedings of the 35th International Conference on Machine Learning (ICML 2018, Best paper runner up)

Derivative free optimization via repeated classification PDF

Tatsunori B Hashimoto, Steve Yadlowsky, John C Duchi

21st International Conference on Artificial Intelligence and Statistics (AISTATS 2018)

Unsupervised Transformation Learning via Convex Relaxations PDF

Tatsunori B Hashimoto, Percy S Liang, John C Duchi

Advances in Neural Information Processing Systems 30 (NeurIPS 2017)

Continuous representations and models from random walk diffusion limits PDF

Tatsunori B Hashimoto

PhD Thesis, MIT CSAIL, 2016

Word embeddings as metric recovery in semantic spaces PDF

Tatsunori B Hashimoto, David Alvarez-Melis, Tommi S Jaakkola

Transactions of the Association for Computational Linguistics 4 (TACL, presented at ACL 2016)

Learning Population-Level Diffusions with Generative RNNs PDF

Tatsunori B Hashimoto, David Gifford, Tommi S Jaakkola

Proceedings of the 33rd International Conference on Machine Learning (ICML 2016)

From random walks to distances on unweighted graphs PDF

Tatsunori B Hashimoto, Yi Sun, Tommi S Jaakkola

Advances in Neural Information Processing Systems (NeurIPS 2015)

Metric recovery from directed unweighted graphs PDF

Tatsunori B Hashimoto, Yi Sun, Tommi S Jaakkola

Artificial Intelligence and Statistics (AISTATS 2015), (best poster at NeurIPS 2014 workshop on networks)

Likelihood-Based Diffusion Language Models PDF

Ishaan Gulrajani, Tatsunori B. Hashimoto

ArXiv preprint

AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback PDF

Yann Dubois, Xuechen Li, Rohan Taori, Tianyi Zhang, Ishaan Gulrajani, Jimmy Ba, Carlos Guestrin, Percy Liang, Tatsunori B Hashimoto

ArXiv preprint

When Do Pre-Training Biases Propagate to Downstream Tasks? A Case Study in Text Summarization PDF

Faisal Ladhak, Esin Durmus, Mirac Suzgun, Tianyi Zhang, Dan Jurafsky, Kathleen Mckeown, Tatsunori B Hashimoto

Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023)

Whose Opinions Do Language Models Reflect? PDF

Shibani Santurkar, Esin Durmus, Faisal Ladhak, Cinoo Lee, Percy Liang, Tatsunori Hashimoto

International Conference on Machine Learning (ICML 2023, oral)

Foundation Models and Fair Use PDF

Peter Henderson, Xuechen Li, Dan Jurafsky, Tatsunori Hashimoto, Mark A Lemley, Percy Liang

ArXiv preprint

Navigating the Grey Area: Expressions of Overconfidence and Uncertainty in Language Models PDF

Kaitlyn Zhou, Dan Jurafsky, Tatsunori Hashimoto

ArXiv preprint

Benchmarking Large Language Models for News Summarization PDF

Tianyi Zhang, Faisal Ladhak, Esin Durmus, Percy Liang, Kathleen McKeown, Tatsunori B Hashimoto

ArXiv preprint

Tracing and Removing Data Errors in Natural Language Generation Datasets PDF

Faisal Ladhak, Esin Durmus, Tatsunori Hashimoto

ArXiv preprint

Privacy-Preserving Domain Adaptation of Semantic Parsers PDF

Fatemehsadat Mireshghallah, Richard Shin, Yu Su, Tatsunori Hashimoto, Jason Eisner

ArXiv preprint

Contrastive decoding: Open-ended text generation as optimization PDF

Xiang Lisa Li, Ari Holtzman, Daniel Fried, Percy Liang, Jason Eisner, Tatsunori Hashimoto, Luke Zettlemoyer, Mike Lewis

ArXiv preprint

Diffusion-LM Improves Controllable Text Generation PDF

Lisa Li, John Thickstun, Ishaan Gulrajani, Percy Liang, Tatsunori B Hashimoto

Advances in Neural Information Processing Systems 31 (NeurIPS 2022)

TempLM: Distilling Language Models into Template-Based Generators PDF

Tianyi Zhang, Mina Lee, Lisa Li, Ende Shen, Tatsunori B Hashimoto

ArXiv preprint

Emergent abilities of large language models PDF

Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, Ed H Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, William Fedus

Transactions on Machine Learning Research (2022)

Jury learning: Integrating dissenting voices into machine learning models PDF

Mitchell Gordon, Michelle Lam, Joon Park, Kayur Patel, Jeff Hancock, Tatsunori B Hashimoto, Michael Bernstein

Conference on Human Factors in Computing Systems (CHI 2022, Best paper)

Spurious Correlations in Reference-Free Evaluation of Text Generation PDF

Esin Durmus, Faisal Ladhak, Tatsunori B Hashimoto

Annual Meeting of the Association of Computational Linguistics (ACL 2022)

Large Language Models Can Be Strong Differentially Private Learners PDF

Xuechen Li, Florian Tramer, Percy Liang, Tatsunori B Hashimoto

International Conference on Learning Representations (ICLR 2022 Oral)

Language Modeling via Stochastic Processes PDF

Rose E Wang, Esin Durmus, Noah Goodman, Tatsunori B Hashimoto

International Conference on Learning Representations (ICLR 2022 Oral)

On the opportunities and risks of foundation models PDF

Rishi Bommasani [.. alphabetical authors ..] Tatsunori Hashimoto [...]

ArXiv preprint

Measuring Conversational Uptake: A Case Study on Student-Teacher Interactions PDF

Dorottya Demszky, Jing Liu, Zid Mancenido, Julie Cohen, Heather Hill, Dan Jurafsky, Tatsunori B Hashimoto

Annual Meeting of the Association of Computational Linguistics (ACL 2020)

DReCa: A general task augmentation strategy for few-shot natural language inference PDF

Shikhar Murty, Tatsunori B Hashimoto, Christopher D Manning

Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2021)

On the Inductive Bias of Masked Language Modeling: From Statistical to Syntactic Dependencies PDF

Tianyi Zhang, Tatsunori B Hashimoto

Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2021)

The Disagreement Deconvolution: Bringing Machine Learning Performance Metrics In Line With Reality PDF

Mitchell L Gordon, Kaitlyn Zhou, Kayur Patel, Tatsunori B Hashimoto, Michael S Bernstein

Conference on Human Factors in Computing Systems (CHI 2021)

Improved Natural Language Generation via Loss Truncation PDF

Daniel Kang, Tatsunori B Hashimoto

Annual Meeting of the Association of Computational Linguistics (ACL 2020)

Learning Autocomplete Systems as a Communication Game PDF

Mina Lee, Tatsunori B Hashimoto, Percy Liang

Emergent Communication Workshop at Neural Information Processing Systems (NeurIPS 2019)

Distributionally Robust Language Modeling PDF

Yonatan Oren*, Shiori Sagawa *, Tatsunori B Hashimoto *, Percy Liang

Empirical Methods in Natural Language Processing (EMNLP 2019)

Unifying Human and Statistical Evaluation for Natural Language Generation PDF

Tatsunori B Hashimoto*, Hugh Zhang*, Percy Liang

Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2019)

A Retrieve-and-Edit Framework for Predicting Structured Outputs PDF

Tatsunori B Hashimoto, Kelvin Guu, Yonatan Oren, Percy Liang

Advances in Neural Information Processing Systems 31 (NeurIPS 2018, Oral)

Generating Sentences by Editing Prototypes PDF

Kelvin Guu*, Tatsunori B Hashimoto*, Yonatan Oren, Percy Liang

Transactions of the Association of Computational Linguistics (TACL, presented at ACL 2018)

Continuous representations and models from random walk diffusion limits PDF

Tatsunori B Hashimoto

PhD Thesis, MIT CSAIL, 2016

Word embeddings as metric recovery in semantic spaces PDF

Tatsunori B Hashimoto, David Alvarez-Melis, Tommi S Jaakkola

Transactions of the Association for Computational Linguistics 4 (TACL, presented at ACL 2016)

Inferring Multidimensional Rates of Aging from Cross-Sectional Data PDF

Emma Pierson*, Pang Wei Koh *, Tatsunori B Hashimoto *, Daphne Koller, Jure Lesokevic, Nicholas Eriksson, Percy Liang

22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019)

Continuous representations and models from random walk diffusion limits PDF

Tatsunori B Hashimoto

PhD Thesis, MIT CSAIL, 2016

Learning Population-Level Diffusions with Generative RNNs PDF

Tatsunori B Hashimoto, David Gifford, Tommi S Jaakkola

Proceedings of the 33rd International Conference on Machine Learning (ICML 2016)

A synergistic DNA logic predicts genome-wide chromatin accessibility PDF

Tatsunori B Hashimoto*, Richard I Sherwood*, Daniel D Kang*, Nisha Rajagopal, Amira A Barkal, Haoyang Zeng, Bart JM Emons, Sharanya Srinivasan, Tommi S Jaakkola, David K Gifford

Genome research (2016)

Cas9 Functionally Opens Chromatin PDF

Amira A Barkal, Sharanya Srinivasan, Tatsunori B Hashimoto, David K Gifford, Richard I Sherwood

PloS One (2016)

Cloning-free CRISPR PDF

Mandana Arbab, Sharanya Srinivasan, Tatsunori B Hashimoto, Niels Geijsen, Richard I Sherwood

Stem cell reports (2015)

GERV: a statistical method for generative evaluation of regulatory variants for transcription factor binding PDF

Haoyang Zeng, Tatsunori B Hashimoto, Daniel D Kang, David K Gifford

Bioinformatics (2015)

Long-term persistence and development of induced pancreatic beta cells generated by lineage conversion of acinar cells PDF

Weida Li, Claudia Cavelti-Weder, Yinying Zhang, Kendell Clement, Scott Donovan, Gabriel Gonzalez, Jiang Zhu, Marianne Stemann, Ke Xu, Tatsunori B Hashimoto, Takatsugu Yamada, Mio Nakanishi, Yuemei Zhang, Samuel Zeng, David Gifford, Alexander Meissner, Gordon Weir, Qiao Zhou

Nature Biotechnology (2014)

Universal count correction for high-throughput sequencing PDF

Tatsunori B Hashimoto, Matthew D Edwards, David K Gifford

PLoS computational biology (2014)

Discovery of directional and nondirectional pioneer transcription factors by modeling DNase profile magnitude and shape PDF

Richard I Sherwood *, Tatsunori B Hashimoto *, Charles W O'donnell *, Sophia Lewis, Amira A Barkal, John Peter Van Hoff, Vivek Karun, Tommi S Jaakkola, David K Gifford

Nature Biotechnology (2014)

Quantifying condition-dependent intracellular protein levels enables high-precision fitness estimates PDF

Kerry A Geiler-Samerotte, Tatsunori B Hashimoto, Michael F Dion, Bogdan A Budnik, Edoardo M Airoldi, D Allan Drummond

PloS one (2013)

Lineage-based identification of cellular states and expression programs PDF

Tatsunori B Hashimoto, Tommi S Jaakkola, Richard Sherwood, Esteban O. Mazzoni, Hynek Wichterle, David Gifford

Bioinformatics (2012)

Finding drug discovery rules of thumb with bump hunting PDF

Tatsunori B Hashimoto, Matthew Segall

Proceedings of the ACS (2010)

BFL: a node and edge betweenness based fast layout algorithm for large scale networks. PDF

Tatsunori B Hashimoto, Masao Nagasaki, Kaname Kojima, Satoru Miyano

BMC bioinformatics (2009)

Teaching

CS324 (Winter 2023): Advances in Foundation Models

CS324 (Winter 2022): Large Language Models

CS329D (Fall 2021, Spring 2021): Machine Learning Under Distribution Shifts

Former Advisees

Esin Durmus (2021-2023) SAIL Postdoc (w/ Dan Jurafsky), now at Anthropic.

Shibani Santurkar (2021-2023) Postdoc (w/ Percy Liang and Tengyu Ma), now at OpenAI.

Daniel Kang (2021-2022) Graduate Student (w/ Matei Zaharia and Peter Bailis), now assistant prof at UIUC.

Ishaan Gulrajani (2021-2022) Graduate Student (on leave), at OpenAI

Resume

Acknowledgement

This website uses the website design and template by Martin Saveski