Peter West

he/him | CV | github | LinkedIn | Google Scholar | pawest at cs dot washington dot edu

I am currently on the academic job market (2023/2024)

I am a PhD candidate working in Natural Language Processing and AI at the University of Washington. My broad research goal is reducing the capability gap between compact language models (LMs) and extreme scale frontier models. I have worked with Yejin Choi to design learning and inference algorithms to unlock capabilities in smaller models, for example:

In parallel, I study LM capabilities and their limits, particularly how frontier models diverge from human expectations. For example, I proposed the Generative AI Paradox to question the relative abilities to understand and generate in these models

My work has been recognized with multiple awards, including best method paper at NAACL 2022, outstanding paper at ACL 2023, and outstanding paper at EMNLP 2023. I was also awarded the NSERC PGS-D fellowship which supported my PhD in part, and was recognized with an honorable mention for the NSF GRFP.

I received my BSc (Honours Computer Science) from the University of British Columbia in 2017. I have been an intern at the Allen Institute for AI on the Mosaic team and Microsoft Research in the Natural Language Processing Group. Outside of research, I love cooking, making bread, pasta, ice cream, and cocktails. I love movies of all kinds, and music.


Recent Preprints

The Generative AI Paradox: "What It Can Create, It May Not Understand"
=Peter West, =Ximing Lu, =Nouha Dziri, =Faeze Brahman, =Linjie Li, Jena D. Hwang, Liwei Jiang, Jillian Fisher, Abhilasha Ravichander, Khyathi Chandu, Benjamin Newman, Pang Wei Koh, Allyson Ettinger, Yejin Choi
= Equal Contribution

Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties
Taylor Sorensen, Liwei Jiang, Jena Hwang, Sydney Levine, Valentina Pyatkin, Peter West, Nouha Dziri, Ximing Lu, Kavel Rao, Chandra Bhagavatula, Maarten Sap, John Tasioulas, Yejin Choi

Generative Models as a Complex Systems Science: How can we make sense of large language model behavior?
Ari Holtzman, Peter West, Luke Zettlemoyer

Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing
Jaehun Jung, Peter West, Liwei Jiang, Faeze Brahman, Ximing Lu, Jillian Fisher, Taylor Sorensen, Yejin Choi

Recent Publications

SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization
EMNLP 2023 Outstanding Paper Award for Dialogue and Interactive Systems!
Hyunwoo Kim, Jack Hessel, Liwei Jiang, Peter West, Ximing Lu, Youngjae Yu, Pei Zhou, Ronan Le Bras, Malihe Alikhani, Gunhee Kim, Maarten Sap, Yejin Choi

Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning
EMNLP 2023
Ximing Lu, Faeze Brahman, Peter West, Jaehun Jung, Khyathi Chandu, Abhilasha Ravichander, Lianhui Qin, Prithviraj Ammanabrolu, Liwei Jiang, Sahana Ramnath, Nouha Dziri, Jillian Fisher, Bill Yuchen Lin, Skyler Hallinan, Xiang Ren, Sean Welleck, Yejin Choi

We're Afraid Language Models Aren't Modeling Ambiguity
EMNLP 2023
Alisa Liu, Zhaofeng Wu, Julian Michael, Alane Suhr, Peter West, Alexander Koller, Swabha Swayamdipta, Noah A Smith, Yejin Choi

NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation
Findings of EMNLP 2023
Peter West, Ronan Le Bras, Taylor Sorensen, Bill Yuchen Lin, Liwei Jiang, Ximing Lu, Khyathi Chandu, Jack Hessel, Ashutosh Baheti, Chandra Bhagavatula, Yejin Choi

Faith and Fate: Limits of Transformers on Compositionality
Neurips 2023 (Spotlight)
Nouha Dziri, Ximing Lu, Melanie Sclar, Xiang Lorraine Li, Liwei Jiang, Bill Yuchen Lin, Peter West, Chandra Bhagavatula, Ronan Le Bras, Jena D. Hwang, Soumya Sanyal, Sean Welleck, Xiang Ren, Allyson Ettinger, Zaid Harchaoui, Yejin Choi

Localized Symbolic Knowledge Distillation for Visual Commonsense Models
Neurips 2023
Jae Sung Park, Jack Hessel, Khyathi Raghavi Chandu, Paul Pu Liang, Ximing Lu, Peter West, Youngjae Yu, Qiuyuan Huang, Jianfeng Gao, Ali Farhadi, Yejin Choi

Minding Language Models'(Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker
ACL 2023 Outstanding Paper Award!
Melanie Sclar, Sachin Kumar, Peter West, Alane Suhr, Yejin Choi, Yulia Tsvetkov

I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation
ACL 2023
Chandra Bhagavatula, Jena D. Hwang, Doug Downey, Ronan Le Bras, Ximing Lu, Lianhui Qin, Keisuke Sakaguchi, Swabha Swayamdipta, Peter West, Yejin Choi

Generating Sequences by Learning to Self-Correct
ICLR 2023
=Sean Welleck, =Ximing Lu, ♡Peter West, ♡Faeze Brahman, Tianxiao Shen, Daniel Khashabi, Yejin Choi
= co-first author
♡ co-second author

Quark: Controllable Text Generation with Reinforced Unlearning
Neurips 2022
Ximing Lu, Sean Welleck, Jack Hessel, Liwei Jiang, Lianhui Qin, Peter West, Prithviraj Ammanabrolu, Yejin Choi

Referee: Reference-Free Sentence Summarization with Sharper Controllability through Symbolic Knowledge Distillation
EMNLP 2022
Melanie Sclar, Peter West, Sachin Kumar, Yulia Tsvetkov, Yejin Choi

Symbolic knowledge distillation: from general language models to commonsense models
NAACL 2022
Peter West, Chandra Bhagavatula, Jack Hessel, Jena D Hwang, Liwei Jiang, Ronan Le Bras, Ximing Lu, Sean Welleck, Yejin Choi
[paper] [code and data]

NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics
NAACL 2022 Best Paper Award!
Ximing Lu, ♡Sean Welleck, ♡Peter West, Liwei Jiang, Jungo Kasai, Daniel Khashabi, Ronan Le Bras, Lianhui Qin, Youngjae Yu, Rowan Zellers, Noah A Smith, Yejin Choi
♡ co-second author

Probing Factually Grounded Content Transfer with Factual Ablation
Findings of ACL 2022
Peter West, Chris Quirk, Michel Galley, Yejin choi
[paper] [code]

Generated Knowledge Prompting for Commonsense Reasoning
ACL 2022
Jiacheng Liu, Alisa Liu, Ximing Lu, Sean Welleck, Peter West, Ronan Le Bras, Yejin Choi, Hannaneh Hajishirzi

Symbolic Brittleness in Sequence Models: on Systematic Generalization in Symbolic Mathematics
AAAI 2021
Sean Welleck, Peter West, Jize Cao, Yejin Choi

Surface Form Competition: Why the Highest Probability Answer Isn’t Always Right
EMNLP 2021
=Ari Holtzman, =Peter West, Vered Shwartz, Yejin Choi, and Luke Zettlemoyer
= equal contribution

Reflective Decoding: Unsupervised Paraphrasing and Abductive Reasoning
ACL 2021
Peter West, Ximing Lu, Ari Holtzman, Chandra Bhagavatula, Jena Hwang, and Yejin Choi

Neurologic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints
NAACL 2021
Ximing Lu, Peter West, Rowan Zellers, Ronan Le Bras, Chandra Bhagavatula, and Yejin Choi

Unsupervised Commonsense Question Answering with Self-Talk
EMNLP 2020
Vered Shwartz, Peter West, Ronan Le Bras, Chandra Bhagavatula, Yejin Choi

Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning
EMNLP 2020
Lianhui Qin, Vered Shwartz, Peter West, Chandra Bhagavatula, Jena Hwang, Ronan Le Bras, Antoine Bosselut, Yejin Choi

BottleSum: Self-Supervised and Unsupervised Sentence Summarization using the Information Bottleneck Principle
EMNLP 2019
Peter West, Ari Holtzman, Jan Buys, Yejin Choi

Other Work

SRIFTY: Swift and Thrifty Distributed Neural Network Training on the Cloud
MLSYS 2022
Liang Luo, Peter West, Pratyush Patel, Arvind Krishnamurthy, Luis Ceze

Adjusting for Confounders with Text: Challenges and an Empirical Evaluation Framework for Causal Inference
CWSM 2022
Galen Weld, Peter West, Maria Glenski, David Arbour, Ryan Rossi, Tim Althoff

PLink: Discovering and Exploiting Datacenter Network Locality for Efficient Cloud-based Distributed Training
MLSYS 2020
Liang Luo, Peter West, Arvind Krishnamurthy, Luis Ceze, Jacob Nelson

Refractometric micro-sensor using a mirrored capillary resonator
Optics Express 2016
William Morrish, Peter West, Nathan Orlando, Elizaveta Klantsataya, Kirsty Gardner, Stephen Lane, Raymond Decorby, Alexandre François, Alkiviathes Meldrum

Protein biosensing with fluorescent microcapillaries
Optics Express 2015
Stephen Lane, Peter West, Alexandre François, Alkiviathes Meldrum