Eric Mitchell
19 papers · 2020–2024 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
🌍 Conference Polyglot (6) 🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (14)
🌈
Renaissance Researcher
(5)
🌍
Conference Polyglot
(6)
🤝
Dynamic Duo
(15)
👑
Triple Crown
🔥
Unstoppable
(5)
💎
Century Club
(19)
⚡
Prolific Year
(7)
🗃️
Keyword Collector
(70)
Conferences
ICLR (5)
EMNLP (4)
ICML (4)
NIPS (4)
CORL (1)
IJCAI (1)
Top co-authors
Keywords
large language model
(5)
language model
(4)
reinforcement learning from human feedback
(3)
direct preference optimization
(2)
offline reinforcement learning
(2)
online adaptation
(2)
imitation learning
(1)
online learning
(1)
reinforcement learning
(1)
model calibration
(1)
model editing
(1)
knowledge editing
(1)
natural language inference
(1)
question answering
(1)
uncertainty quantification
(1)
language model alignment
(1)
instruction following
(1)
text classification
(1)
confidence calibration
(1)
preference optimization
(1)
Papers
RLVF: Learning from Verbal Feedback without Overgeneralization
ICML 2024
A Critical Evaluation of AI Feedback for Aligning Large Language Models
NIPS 2024
Online Adaptation of Language Models with a Memory of Amortized Contexts
NIPS 2024
Calibrating Language Models with Adaptive Temperature Scaling
EMNLP 2024
An Emulator for Fine-tuning Large Language Models using Small Language Models
ICLR 2024
Language Model Detectors Are Easily Optimized Against
ICLR 2024
Fine-Tuning Language Models for Factuality
ICLR 2024
Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback
EMNLP 2023
DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature
ICML 2023
RECKONING: Reasoning through Dynamic Knowledge Encoding
NIPS 2023
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
NIPS 2023
Meta-Learning Online Adaptation of Language Models
EMNLP 2023
Memory-Based Model Editing at Scale
ICML 2022
Fast Model Editing at Scale
ICLR 2022
Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference
EMNLP 2022
Offline Meta-Reinforcement Learning with Advantage Weighting
ICML 2021
Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation
CORL 2021
Reward Prediction Error as an Exploration Objective in Deep RL
IJCAI 2020
Higher-Order Function Networks for Learning Composable 3D Object Representations
ICLR 2020