[about]
[talks]
[papers]
Shi Feng
[email]
[scholar]
[cv]
[twitter]
Incoming assistant professor at George Washington University
Current postdoc with Sam Bowman and He He at
NYU Alignment Research Group
Postdoc with
Chenhao Tan at University of Chicago
PhD with
Jordan Boyd-Graber at University of Maryland
I'm interested in developing tools for thinking.
Crowdsourcing truth at scale is the core of the current AI paradigm.
But as these AIs get better at producing correct-
looking outputs on tasks we don't fully understand, this paradigm is running into limitations.
I believe the solution is to design
truth-finding processes for and with AIs.
To build a mental picture of what that looks like, I find it useful to think about
AlphaGo's move 37.
Many Go players initially dismissed it as a bug, but its value became apparent as the game unfolded.
In other words, even domain experts initially misjudged the AI, but the interactive process of Lee Sedol playing out the rest of the game lead to a more precise evaluation.
My high-level goal is to improve
human supervision of non-human processes with new
theories,
algorithms,
data collection schemes, and
UIs.
I'm always thinking about the following questions:
Does the model know something that I don't?
How can I ask the right questions to elicit that knowledge?
Talks
- May 2023 Evaluating AI: From Crowdsourcing Truths to Truth-finding Processes [pdf]
- Jul 2022 NAACL Tutorial on Human Evaluations of Explanations [website]
- Apr 2019 NLP Highlights Podcast on pathologies of neural models [spotify]
Papers
-
Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations
Chenglei Si*, Dan Friedman*, Nitish Joshi, Shi Feng, Danqi Chen, He He
ACL 2023
-
Machine Explanations and Human Understanding
Chacha Chen*, Shi Feng*, Amit Sharma, Chenhao Tan
TMLR 2023, FAccT 2023, and best paper at HMCaT @ ICML 2022
[arxiv]
-
Learning Human-Compatible Representations for Case-Based Decision Support
Han Liu, Yizhou Tian, Chacha Chen, Shi Feng, Yuxin Chen, Chenhao Tan
ICLR 2023
[openreview]
-
Learning to Explain Selectively
Shi Feng, Jordan Boyd-Graber
EMNLP 2022
[acl]
[pdf]
-
Active Example Selection for In-Context Learning
Yiming Zhang, Shi Feng, Chenhao Tan
EMNLP 2022
[acl]
[pdf]
-
Human Learning Meets Representation Learning
Matthew Shu*, Shi Feng*, Jordan Boyd-Graber
preprint
-
Calibrate Before Use: Improving Few-shot Performance of Language Models
Tony Z. Zhao*, Eric Wallace*, Shi Feng, Dan Klein, Sameer Singh
ICML 2021
[pmlr]
[pdf]
-
Concealed Data Poisoning Attacks on NLP Models
Eric Wallace*, Tony Z. Zhao*, Shi Feng, Sameer Singh
NAACL 2021
[acl]
[pdf]
[blog]
-
Universal Adversarial Triggers for Attacking and Analyzing NLP
Eric Wallace, Shi Feng, Nikhil Kandpal, Matt Gardner, Sameer Singh
EMNLP 2019
[acl]
[pdf]
[blog]
-
Misleading Failures of Partial-input Baselines
Shi Feng, Eric Wallace, Jordan Boyd-Graber
ACL 2019, short paper
[acl]
[pdf]
-
Quizbowl: The Case for Incremental Question Answering
Pedro Rodriguez, Shi Feng, Mohit Iyyer, He He, Jordan Boyd-Graber
In submission [arxiv]
-
Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation
Sahil Singla, Eric Wallace, Shi Feng, Soheil Feizi
ICML 2019
[pmlr]
[pdf]
-
Trick Me If You Can: Human-in-the-loop Generation of Adversarial Examples for Question Answering
Eric Wallace, Pedro Rodriguez, Shi Feng, Jordan Boyd-Graber
TACL 2019
[acl]
[pdf]
-
What can AI do for me: Evaluating Machine Learning Interpretations in Cooperative Play
Shi Feng, Jordan Boyd-Graber
IUI 2019
[arxiv]
-
Pathologies of Neural Models Make Interpretation Difficult
Shi Feng, Eric Wallace, Alvin Grissom II, Mohit Iyyer, Pedro Rodriguez, Jordan Boyd-Graber
EMNLP 2018, oral
[acl]
[pdf]
[talk]
-
Interpreting Neural Networks with Nearest Neighbors
Eric Wallace*, Shi Feng*, Jordan Boyd-Graber
BlackboxNLP @ EMNLP 2018
[acl]
[pdf]
-
The UMD Neural Machine Translation Systems at WMT17 Bandit Learning Task
Amr Sharaf, Shi Feng, Khanh Nguyen, Kianté Brantley, Hal Daumé III
WMT @ EMNLP 2017
[acl]
[pdf]
-
Improving Attention Modeling with Implicit Distortion and Fertility for Machine Translation
Shi Feng, Shujie Liu, Nan Yang, Mu Li, Ming Zhou, Kenny Q. Zhu
COLING 2016
[acl]
[pdf]
Experience
- June 1 2020 Intern @ Salesforce Research
- Mar 2019 Invited talks at UPenn, UCSD, UCI
- Best reviewer award @ EMNLP 2018, 2020
- Summer 2018 Research Intern @ Microsoft Research