Model Alignment Process
Das, Sayantan. 2024. “Model Alignment Process.” blog.premai.io/model-alignment-process/
Abstract
The alignment of generative models with human feedback has significantly improved the performance of natural language generation tasks. For large language models (LLMs), alignment methods like reinforcement learning from human feedback (RLHF) and direct preference optimization (DPO) have consistently worked better than just supervised fine-tuning (SFT) alone based on current
BibTeX
@misc{dasModelAlignmentProcess2024,
title = {Model {{Alignment Process}}},
author = {Das, Sayantan},
year = 2024,
month = mar,
journal = {Prem},
url = {https://blog.premai.io/model-alignment-process/},
urldate = {2024-03-31},
abstract = {The alignment of generative models with human feedback has significantly improved the performance of natural language generation tasks. For large language models (LLMs), alignment methods like reinforcement learning from human feedback (RLHF) and direct preference optimization (DPO) have consistently worked better than just supervised fine-tuning (SFT) alone based on current},
langid = {english}
}