Shi Feng

51 papers A* 12A 1Journal 28Unranked 10
YearRankTypeTitle / Venue / Authors
2025 A* conf
A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users.
EMNLP
Nishant Balepur, Matthew Shu, Yoo Yeon Sung, Seraphina Goldfarb-Tarrant, Shi Feng, Fumeng Yang, Rachel Rudinger, Jordan Lee Boyd-Graber
2025 J jnl
A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users.
CoRR
Nishant Balepur, Matthew Shu, Yoo Yeon Sung, Seraphina Goldfarb-Tarrant, Shi Feng, Fumeng Yang, Rachel Rudinger, Jordan Lee Boyd-Graber
2025 A* conf
Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats.
ICLR
Jiaxin Wen, Vivek Hebbar, Caleb Larson, Aryan Bhatt, Ansh Radhakrishnan, Mrinank Sharma, Henry Sleight, Shi Feng, He He, Ethan Perez, Buck Shlegeris, Akbir Khan
2025 A* conf
Language Models Learn to Mislead Humans via RLHF.
ICLR
Jiaxin Wen, Ruiqi Zhong, Akbir Khan, Ethan Perez, Jacob Steinhardt, Minlie Huang, Samuel R. Bowman, He He, Shi Feng
2025 — conf
Reverse Question Answering: Can an LLM Write a Question so Hard (or Bad) that it Can't Answer?
NAACL (Short Papers)
Nishant Balepur, Feng Gu, Abhilasha Ravichander, Shi Feng, Jordan Lee Boyd-Graber, Rachel Rudinger
2025 J jnl
Unsupervised Elicitation of Language Models.
CoRR
Jiaxin Wen, Zachary Ankner, Arushi Somani, Peter Hase, Samuel Marks, Jacob Goldman-Wetzler, Linda Petrini, Henry Sleight, Collin Burns, He He, Shi Feng, Ethan Perez, Jan Leike
2025 — conf
Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personas.
ACL (1)
Nishant Balepur, Vishakh Padmakumar, Fumeng Yang, Shi Feng, Rachel Rudinger, Jordan Lee Boyd-Graber
2025 J jnl
Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personas.
CoRR
Nishant Balepur, Vishakh Padmakumar, Fumeng Yang, Shi Feng, Rachel Rudinger, Jordan Lee Boyd-Graber
2024 A* conf
A SMART Mnemonic Sounds like "Glue Tonic": Mixing LLMs with Student Feedback to Make Mnemonic Learning Stick.
EMNLP
Nishant Balepur, Matthew Shu, Alexander Miserlis Hoyle, Alison Robey, Shi Feng, Seraphina Goldfarb-Tarrant, Jordan L. Boyd-Graber
2024 J jnl
A SMART Mnemonic Sounds like "Glue Tonic": Mixing LLMs with Student Feedback to Make Mnemonic Learning Stick.
CoRR
Nishant Balepur, Matthew Shu, Alexander Miserlis Hoyle, Alison Robey, Shi Feng, Seraphina Goldfarb-Tarrant, Jordan L. Boyd-Graber
2024 J jnl
Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats.
CoRR
Jiaxin Wen, Vivek Hebbar, Caleb Larson, Aryan Bhatt, Ansh Radhakrishnan, Mrinank Sharma, Henry Sleight, Shi Feng, He He, Ethan Perez, Buck Shlegeris, Akbir Khan
2024 A* conf
KARL: Knowledge-Aware Retrieval and Representations aid Retention and Learning in Students.
EMNLP
Matthew Shu, Nishant Balepur, Shi Feng, Jordan L. Boyd-Graber
2024 J jnl
KARL: Knowledge-Aware Retrieval and Representations aid Retention and Learning in Students.
CoRR
Matthew Shu, Nishant Balepur, Shi Feng, Jordan L. Boyd-Graber
2024 A* conf
LLM Evaluators Recognize and Favor Their Own Generations.
NeurIPS
Arjun Panickssery, Samuel R. Bowman, Shi Feng
2024 J jnl
LLM Evaluators Recognize and Favor Their Own Generations.
CoRR
Arjun Panickssery, Samuel R. Bowman, Shi Feng
2024 J jnl
Language Models Learn to Mislead Humans via RLHF.
CoRR
Jiaxin Wen, Ruiqi Zhong, Akbir Khan, Ethan Perez, Jacob Steinhardt, Minlie Huang, Samuel R. Bowman, He He, Shi Feng
2024 — conf
Large Language Models Help Humans Verify Truthfulness - Except When They Are Convincingly Wrong.
NAACL-HLT
Chenglei Si, Navita Goyal, Tongshuang Wu, Chen Zhao, Shi Feng, Hal Daumé III, Jordan L. Boyd-Graber
2024 J jnl
Reverse Question Answering: Can an LLM Write a Question so Hard (or Bad) that it Can't Answer?
CoRR
Nishant Balepur, Feng Gu, Abhilasha Ravichander, Shi Feng, Jordan L. Boyd-Graber, Rachel Rudinger
2024 J jnl
Spontaneous Reward Hacking in Iterative Self-Refinement.
CoRR
Jane Pan, He He, Samuel R. Bowman, Shi Feng
2023 J jnl
Large Language Models Help Humans Verify Truthfulness - Except When They Are Convincingly Wrong.
CoRR
Chenglei Si, Navita Goyal, Sherry Tongshuang Wu, Chen Zhao, Shi Feng, Hal Daumé III, Jordan L. Boyd-Graber
2023 A* conf
Learning Human-Compatible Representations for Case-Based Decision Support.
ICLR
Han Liu, Yizhou Tian, Chacha Chen, Shi Feng, Yuxin Chen, Chenhao Tan
2023 J jnl
Learning Human-Compatible Representations for Case-Based Decision Support.
CoRR
Han Liu, Yizhou Tian, Chacha Chen, Shi Feng, Yuxin Chen, Chenhao Tan
2023 — conf
Machine Explanations and Human Understanding.
FAccT
Chacha Chen, Shi Feng, Amit Sharma, Chenhao Tan
2023 J jnl
Machine Explanations and Human Understanding.
Trans. Mach. Learn. Res.
Chacha Chen, Shi Feng, Amit Sharma, Chenhao Tan
2023 — conf
Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations.
ACL (1)
Chenglei Si, Dan Friedman, Nitish Joshi, Shi Feng, Danqi Chen, He He
2023 J jnl
Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations.
CoRR
Chenglei Si, Dan Friedman, Nitish Joshi, Shi Feng, Danqi Chen, He He
2022 A* conf
Active Example Selection for In-Context Learning.
EMNLP
Yiming Zhang, Shi Feng, Chenhao Tan
2022 J jnl
Active Example Selection for In-Context Learning.
CoRR
Yiming Zhang, Shi Feng, Chenhao Tan
2022 A* conf
Learning to Explain Selectively: A Case Study on Question Answering.
EMNLP
Shi Feng, Jordan L. Boyd-Graber
2022 J jnl
Machine Explanations and Human Understanding.
CoRR
Chacha Chen, Shi Feng, Amit Sharma, Chenhao Tan
2021 J jnl
Calibrate Before Use: Improving Few-Shot Performance of Language Models.
CoRR
Tony Z. Zhao, Eric Wallace, Shi Feng, Dan Klein, Sameer Singh
2021 A* conf
Calibrate Before Use: Improving Few-shot Performance of Language Models.
ICML
Zihao Zhao, Eric Wallace, Shi Feng, Dan Klein, Sameer Singh
2021 — conf
Concealed Data Poisoning Attacks on NLP Models.
NAACL-HLT
Eric Wallace, Tony Z. Zhao, Shi Feng, Sameer Singh
2020 J jnl
Customizing Triggers with Concealed Data Poisoning.
CoRR
Eric Wallace, Tony Z. Zhao, Shi Feng, Sameer Singh
2019 — conf
Misleading Failures of Partial-input Baselines.
ACL (1)
Shi Feng, Eric Wallace, Jordan L. Boyd-Graber
2019 J jnl
Misleading Failures of Partial-input Baselines.
CoRR
Shi Feng, Eric Wallace, Jordan L. Boyd-Graber
2019 J jnl
Quizbowl: The Case for Incremental Question Answering.
CoRR
Pedro Rodriguez, Shi Feng, Mohit Iyyer, He He, Jordan L. Boyd-Graber
2019 J jnl
Trick Me If You Can: Human-in-the-loop Generation of Adversarial Question Answering Examples.
Trans. Assoc. Comput. Linguistics
Eric Wallace, Pedro Rodriguez, Shi Feng, Ikuya Yamada, Jordan L. Boyd-Graber
2019 A* conf
Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation.
ICML
Sahil Singla, Eric Wallace, Shi Feng, Soheil Feizi
2019 J jnl
Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation.
CoRR
Sahil Singla, Eric Wallace, Shi Feng, Soheil Feizi
2019 — conf
Universal Adversarial Triggers for Attacking and Analyzing NLP.
EMNLP/IJCNLP (1)
Eric Wallace, Shi Feng, Nikhil Kandpal, Matt Gardner, Sameer Singh
2019 J jnl
Universal Adversarial Triggers for NLP.
CoRR
Eric Wallace, Shi Feng, Nikhil Kandpal, Matt Gardner, Sameer Singh
2019 A conf
What can AI do for me?: evaluating machine learning interpretations in cooperative play.
IUI
Shi Feng, Jordan L. Boyd-Graber
2018 J jnl
Interpreting Neural Networks With Nearest Neighbors.
CoRR
Eric Wallace, Shi Feng, Jordan L. Boyd-Graber
2018 — conf
Interpreting Neural Networks with Nearest Neighbors.
BlackboxNLP@EMNLP
Eric Wallace, Shi Feng, Jordan L. Boyd-Graber
2018 A* conf
Pathologies of Neural Models Make Interpretation Difficult.
EMNLP
Shi Feng, Eric Wallace, Alvin Grissom II, Mohit Iyyer, Pedro Rodriguez, Jordan L. Boyd-Graber
2018 J jnl
Right Answer for the Wrong Reason: Discovery and Mitigation.
CoRR
Shi Feng, Eric Wallace, Mohit Iyyer, Pedro Rodriguez, Alvin Grissom II, Jordan L. Boyd-Graber
2018 J jnl
Trick Me If You Can: Adversarial Writing of Trivia Challenge Questions.
CoRR
Eric Wallace, Pedro Rodriguez, Shi Feng, Jordan L. Boyd-Graber
2018 J jnl
What can AI do for me: Evaluating Machine Learning Interpretations in Cooperative Play.
CoRR
Shi Feng, Jordan L. Boyd-Graber
2017 — conf
The UMD Neural Machine Translation Systems at WMT17 Bandit Learning Task.
WMT
Amr Sharaf, Shi Feng, Khanh Nguyen, Kianté Brantley, Hal Daumé III
2017 J jnl
The UMD Neural Machine Translation Systems at WMT17 Bandit Learning Task.
CoRR
Amr Sharaf, Shi Feng, Khanh Nguyen, Kianté Brantley, Hal Daumé III