Geoffrey Irving
7 papers · 2016–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (4) 🏃 Academic Marathon (8) 🐝 Cross-Pollinator (12)
🐣
Hot Topic Early Bird
🐝
Cross-Pollinator
(12)
🌈
Renaissance Researcher
(6)
🌟
Keyword Trendsetter Combo
(3)
👥
Mega-Team
(28)
📈
Trend Setter
Conferences
NIPS (3)
ICML (2)
EMNLP (1)
OSDI (1)
Top co-authors
Research topics
Keywords
harmful content
(2)
representation learning
(1)
reinforcement learning
(1)
imitation learning
(1)
preference learning
(1)
question answering
(1)
prompt engineering
(1)
toxicity detection
(1)
language model evaluation
(1)
document retrieval
(1)
responsible ai
(1)
distributed computing
(1)
distributed training
(1)
demonstration learning
(1)
reward learning
(1)
deep neural network
(1)
language model
(1)
safety evaluation
(1)
automated theorem proving
(1)
red teaming
(1)
Papers
Scalable AI Safety via Doubly-Efficient Debate
ICML 2024
Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models
NIPS 2022
Red Teaming Language Models with Language Models
EMNLP 2022
Improving Language Models by Retrieving from Trillions of Tokens
ICML 2022
Reward learning from human preferences and demonstrations in Atari
NIPS 2018
TensorFlow: A System for Large-Scale Machine Learning
OSDI 2016
DeepMath - Deep Sequence Models for Premise Selection
NIPS 2016