paper-with-me

홈 › Papers

NEFTune: Noisy Embeddings Improve Instruction Finetuning

2023-10-09 · Neel Jain, Ping-Yeh Chiang, Yuxin Wen, John Kirchenbauer, Hong-Min Chu, Gowthami Somepalli, Brian R. Bartoldson, Bhavya Kailkhura, Avi Schwarzschild, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein

We show that language model finetuning can be improved, sometimes dramatically, with a simple augmentation. NEFTune adds noise to the embedding vectors during training. Standard finetuning of LLaMA-2-7B using Alpaca achieves 29.79% on AlpacaEval, which rises to 64.69% using noisy embeddings. NEFTune also improves over strong baselines on modern instruction datasets. Models trained with Evol-Instruct see a 10% improvement, with ShareGPT an 8% improvement, and with OpenPlatypus an 8% improvement. Even powerful models further refined with RLHF such as LLaMA-2-Chat benefit from additional training with NEFTune.

📄 PDF Abstract BibTeX arXiv:2310.05914

Code (4)

neelsjain/neftune 공식 구현 pytorch
akjindal53244/arithmo pytorch
openaccess-ai-collective/axolotl pytorch
rijgersberg/geitje pytorch

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Understanding and Improving Noisy Embedding Techniques in Instruction Finetuning

2026-05-22 · Abhay Yadav arxiv

Recent advancements in instructional fine-tuning have injected noise into embeddings, with NEFTune (Jain et al., 2024) setting benchmarks using uniform noise. Despite NEFTune's empirical findings that uniform noise outpe…

Instruction Finetuning DeepSeek-R1-8B Model Using LoRA and NEFTune

2026-06-09 · Wu Yuerong, Mingni Luo arxiv

Financial named-entity recognition (NER) is essential for translating unstructured financial reports and news into structured knowledge graphs. However, general-purpose large language models (LLMs) often misclassify fina…

Knowledge Graphs

SymNoise: Advancing Language Model Fine-tuning with Symmetric Noise

2023-12-03 · Abhay Kumar Yadav, Arjun Singh

In this paper, we introduce a novel fine-tuning technique for language models, which involves incorporating symmetric noise into the embedding process. This method aims to enhance the model's function by more stringently…

Language ModelingLanguage Modelling

Finetuning Generative Large Language Models with Discrimination Instructions for Knowledge Graph Completion

2024-07-23 · Yang Liu, Xiaobin Tian, Zequn Sun, Wei Hu

Traditional knowledge graph (KG) completion models learn embeddings to predict missing facts. Recent works attempt to complete KGs in a text-generation manner with large language models (LLMs). However, they need to grou…

Knowledge Graph CompletionText Generation

Baichuan2-Sum: Instruction Finetune Baichuan2-7B Model for Dialogue Summarization

2024-01-27 · Jianfei Xiao, Yancan Chen, Yimin Ou, Hanyi Yu 외

Large language models (LLMs) like Llama, Baichuan and Bloom models show remarkable ability with instruction fine-tuning in many natural language tasks. Nevertheless, for the dialogue summarization task, which aims to gen…