Skip to content
conftrace_

Ethan Perez

23 papers · 2018–2025 · 6 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
+11 more ↓ πŸ—ΊοΈ Taxonomy Completionist (48) πŸƒ Academic Marathon Β· Sprint 🌍 Conference Polyglot Β· Silver πŸŒ‰ Interdisciplinary Bridge Β· Silver 🐣 Hot Topic Early Bird
🌟 Keyword Trendsetter Combo (3) πŸ‘₯ Mega-Team Β· Legion πŸ‘‘ Triple Crown 🧬 Topic Evolution 🧭 Keyword Pioneer πŸ“ˆ Trend Setter πŸ—ƒοΈ Keyword Collector (106) πŸš€ Conference Pioneer πŸ”₯ Unstoppable Β· Bronze πŸ’Ž Century Club Β· Bronze 🌈 Renaissance Researcher (6)

Venues

ICLR (6) EMNLP (5) ACL (4) NeurIPS (4) ICML (3) ECCV (1)

Top co-authors

Samuel R. Bowman (6) Douwe Kiela (5) Mrinank Sharma (4) Tomasz Korbak (4) Kyunghyun Cho (4) Nicholas Schiefer (3) Akbir Khan (3) John Hughes (3) Henry Sleight (3) Ansh Radhakrishnan (3)

Research topics

Artificial Intelligence (18) Core AI (15) Machine Learning (12) Natural Language Processing (12) Learning Types Β· Machine Learning (9) Applications (7) Deep Learning (5) Resources & Methods (5) Learning Types Β· Deep Learning (4) Optimization & Theory (4) Learning Paradigms (3) Generation (2) Models (2) Computer Science (1) Interdisciplinary (1)

Keywords

language model (5) question answering (4) reinforcement learning from human feedback (4) large language model (4) few-shot learning (3) reinforcement learning (3) human evaluation (3) prompt engineering (2) red teaming (2) vision-language model (2) safety evaluation (2) semantic parsing (2) kl divergence (1) model robustness (1) natural language processing (1) bayesian inference (1) model selection (1) transfer learning (1) language modeling (1) variational inference (1)

Papers

Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats ICLR 2025 Failures to Find Transferable Image Jailbreaks Between Vision-Language Models ICLR 2025 Language Models Learn to Mislead Humans via RLHF ICLR 2025 Looking Inward: Language Models Can Learn About Themselves by Introspection ICLR 2025 Debating with More Persuasive LLMs Leads to More Truthful Answers ICML 2024 Many-shot Jailbreaking NeurIPS 2024 Towards Understanding Sycophancy in Language Models ICLR 2024 Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning ICLR 2024 Discovering Language Model Behaviors with Model-Written Evaluations ACL 2023 Few-shot Adaptation Works with UnpredicTable Data ACL 2023 Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting NeurIPS 2023 Pretraining Language Models with Human Preferences ICML 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 Case-based Reasoning for Natural Language Queries over Knowledge Bases EMNLP 2021 Rissanen Data Analysis: Examining Dataset Characteristics via Description Length ICML 2021 True Few-Shot Learning with Language Models NeurIPS 2021 Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks NeurIPS 2020 Unsupervised Question Decomposition for Question Answering EMNLP 2020 ELI5: Long Form Question Answering ACL 2019 Finding Generalizable Evidence by Learning to Convince Q&A Models EMNLP 2019 Visual Reasoning with Multi-hop Feature Modulation ECCV 2018