Josef Dai
8 papers · 2023–2025 · 4 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (20) 🐣 Hot Topic Early Bird 🧭 Keyword Pioneer
⚡
Prolific Year · Productive
Venues
Top co-authors
Research topics
Artificial Intelligence
(8)
Core AI
(8)
Machine Learning
(5)
Deep Learning
(4)
Optimization & Theory · Machine Learning
(4)
Natural Language Processing
(3)
Models
(3)
Resources & Methods
(3)
Reinforcement Learning
(2)
Learning Types · Deep Learning
(2)
Learning Types · Machine Learning
(2)
Methods
(2)
Optimization & Theory · Deep Learning
(1)
Keywords
reinforcement learning from human feedback
(4)
large language model
(3)
language model alignment
(2)
safe reinforcement learning
(2)
safety alignment
(2)
human preference
(2)
reward modeling
(2)
constrained optimization
(1)
model alignment
(1)
data compression
(1)
bayesian network
(1)
sequence-to-sequence learning
(1)
safety evaluation
(1)
safety benchmark
(1)
lagrangian method
(1)
preference data
(1)
alignment fine-tuning
(1)
model elasticity
(1)
pre-training distribution
(1)
harmful output mitigation
(1)
Papers
Language Models Resist Alignment: Evidence From Data Compression
ACL 2025
PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference
ACL 2025
Reward Generalization in RLHF: A Topological Perspective
ACL 2025
SafeLawBench: Towards Safe Alignment of Large Language Models
ACL 2025
Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback
AAAI 2025
Safe RLHF: Safe Reinforcement Learning from Human Feedback
ICLR 2024
BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset
NeurIPS 2023
Safety Gymnasium: A Unified Safe Reinforcement Learning Benchmark
NeurIPS 2023