Ethan Perez
24 papers · 2018–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+12 more ↓ Show less ↑
🏃 Academic Marathon (7) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (7) 🐝 Cross-Pollinator (6)
🌍
Conference Polyglot
(7)
🏃
Academic Marathon
(7)
🌈
Renaissance Researcher
(8)
👥
Mega-Team
(63)
👑
Triple Crown
🌱
Topic Pioneer
🧬
Topic Evolution
📈
Trend Setter
🚀
Conference Pioneer
💎
Century Club
(24)
🗃️
Keyword Collector
(85)
🔥
Unstoppable
(8)
Conferences
ICLR (6)
EMNLP (5)
ACL (4)
NIPS (4)
ICML (3)
ECCV (1)
IJCNLP (1)
Top co-authors
Keywords
language model
(6)
question answering
(5)
few-shot learning
(3)
semantic parsing
(2)
prompt engineering
(2)
red teaming
(2)
evidence selection
(2)
reinforcement learning from human feedback
(2)
large language model
(2)
machine reading comprehension
(2)
reinforcement learning
(2)
imitation learning
(1)
question decomposition
(1)
kl divergence
(1)
model selection
(1)
natural language processing
(1)
language model evaluation
(1)
bayesian inference
(1)
text representation
(1)
passage retrieval
(1)
Papers
Language Models Learn to Mislead Humans via RLHF
ICLR 2025
Failures to Find Transferable Image Jailbreaks Between Vision-Language Models
ICLR 2025
Looking Inward: Language Models Can Learn About Themselves by Introspection
ICLR 2025
Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
ICLR 2025
Debating with More Persuasive LLMs Leads to More Truthful Answers
ICML 2024
Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning
ICLR 2024
Towards Understanding Sycophancy in Language Models
ICLR 2024
Many-shot Jailbreaking
NIPS 2024
Pretraining Language Models with Human Preferences
ICML 2023
Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting
NIPS 2023
Few-shot Adaptation Works with UnpredicTable Data
ACL 2023
Discovering Language Model Behaviors with Model-Written Evaluations
ACL 2023
Red Teaming Language Models with Language Models
EMNLP 2022
RL with KL penalties is better viewed as Bayesian inference
EMNLP 2022
Single-Turn Debate Does Not Help Humans Answer Hard Reading-Comprehension Questions
ACL 2022
Rissanen Data Analysis: Examining Dataset Characteristics via Description Length
ICML 2021
True Few-Shot Learning with Language Models
NIPS 2021
Case-based Reasoning for Natural Language Queries over Knowledge Bases
EMNLP 2021
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
NIPS 2020
Unsupervised Question Decomposition for Question Answering
EMNLP 2020
Finding Generalizable Evidence by Learning to Convince Q&A Models
EMNLP 2019
ELI5: Long Form Question Answering
ACL 2019
Finding Generalizable Evidence by Learning to Convince Q&A Models
IJCNLP 2019
Visual Reasoning with Multi-hop Feature Modulation
ECCV 2018