-
Moral Foundations of Large Language Models
Paper • 2310.15337 • Published • 1 -
Specific versus General Principles for Constitutional AI
Paper • 2310.13798 • Published • 2 -
Contrastive Prefence Learning: Learning from Human Feedback without RL
Paper • 2310.13639 • Published • 21 -
RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
Paper • 2309.00267 • Published • 45
Collections
Discover the best community collections!
Collections including paper arxiv:2309.06657
-
Efficient RLHF: Reducing the Memory Usage of PPO
Paper • 2309.00754 • Published • 13 -
Statistical Rejection Sampling Improves Preference Optimization
Paper • 2309.06657 • Published • 13 -
Aligning Large Multimodal Models with Factually Augmented RLHF
Paper • 2309.14525 • Published • 29 -
Stabilizing RLHF through Advantage Model and Selective Rehearsal
Paper • 2309.10202 • Published • 9
-
Language Modeling Is Compression
Paper • 2309.10668 • Published • 80 -
Baichuan 2: Open Large-scale Language Models
Paper • 2309.10305 • Published • 16 -
Chain-of-Verification Reduces Hallucination in Large Language Models
Paper • 2309.11495 • Published • 37 -
LMDX: Language Model-based Document Information Extraction and Localization
Paper • 2309.10952 • Published • 61
-
Statistical Rejection Sampling Improves Preference Optimization
Paper • 2309.06657 • Published • 13 -
In-Context Learning Creates Task Vectors
Paper • 2310.15916 • Published • 39 -
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
Paper • 2404.08801 • Published • 62 -
Make Your LLM Fully Utilize the Context
Paper • 2404.16811 • Published • 52
-
Efficient RLHF: Reducing the Memory Usage of PPO
Paper • 2309.00754 • Published • 13 -
Statistical Rejection Sampling Improves Preference Optimization
Paper • 2309.06657 • Published • 13 -
Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?
Paper • 2309.07462 • Published • 3 -
Stabilizing RLHF through Advantage Model and Selective Rehearsal
Paper • 2309.10202 • Published • 9