A Critical Evaluation of AI Feedback for Aligning Large Language Models
Paper
•
2402.12366
•
Published
•
3
rlhf/finetune
-
-
PERL: Parameter Efficient Reinforcement Learning from Human Feedback
Paper • 2403.10704 • Published • 58 -
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Paper • 2403.03507 • Published • 184 -
Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation
Paper • 2401.08417 • Published • 34 -
Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks
Paper • 2404.14723 • Published • 10 -
Self-Play Preference Optimization for Language Model Alignment
Paper • 2405.00675 • Published • 27 -
Show, Don't Tell: Aligning Language Models with Demonstrated Feedback
Paper • 2406.00888 • Published • 31 -
Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level
Paper • 2406.11817 • Published • 13 -
Following Length Constraints in Instructions
Paper • 2406.17744 • Published • 1 -
Understanding the performance gap between online and offline alignment algorithms
Paper • 2405.08448 • Published • 17 -
Direct Language Model Alignment from Online AI Feedback
Paper • 2402.04792 • Published • 30 -
Contrastive Prefence Learning: Learning from Human Feedback without RL
Paper • 2310.13639 • Published • 24 -
Self-Taught Evaluators
Paper • 2408.02666 • Published • 28 -
Training Language Models to Self-Correct via Reinforcement Learning
Paper • 2409.12917 • Published • 136