A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity
Paper
•
2401.01967
•
Published
Training Paper
Paper for LLM training
-
-
Secrets of RLHF in Large Language Models Part I: PPO
Paper • 2307.04964 • Published • 28 -
Zephyr: Direct Distillation of LM Alignment
Paper • 2310.16944 • Published • 121 -
LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
Paper • 2404.05961 • Published • 64 -
QLoRA: Efficient Finetuning of Quantized LLMs
Paper • 2305.14314 • Published • 45 -
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Paper • 2305.18290 • Published • 48 -
PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models
Paper • 2404.02948 • Published • 2 -
BookSum: A Collection of Datasets for Long-form Narrative Summarization
Paper • 2105.08209 • Published • 2