PublishedCurated

LoRA: Low-Rank Adaptation of Large Language Models

Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen

International Conference on Learning Representations (ICLR) 202217 June 2021

Abstract

Freezes the pretrained weights and injects trainable low-rank matrices into each layer instead. The number of trainable parameters drops by several orders of magnitude, adapters are small enough to swap at runtime, and training cost falls with them.

arXiv Code

BibTeX

@inproceedings{hu2021lora,
  author    = {Edward J. Hu and Yelong Shen and Phillip Wallis and Zeyuan Allen-Zhu and Yuanzhi Li and Shean Wang and Lu Wang and Weizhu Chen},
  title     = {LoRA: Low-Rank Adaptation of Large Language Models},
  booktitle = {International Conference on Learning Representations (ICLR) 2022},
  year      = {2021},
  eprint    = {2106.09685},
  archivePrefix = {arXiv},
  url       = {https://arxiv.org/abs/2106.09685}
}

Ejentic did not author this paper. Credit belongs to the authors named above; the note is ours.

2026

Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning

The interesting part is the failure it fixes: a good step inside a bad run gets no credit. Anyone who has debugged an agent by reading successful traces only has already lost the most informative data, which lives in the runs that failed at step nine of twelve.

2023

Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Cut the RLHF pipeline down to one training run. For teams without the infrastructure to run a reward model and PPO, this is usually the practical route into preference tuning.