# NEFTune: Noisy Embeddings Improve Instruction Finetuning

arXiv: https://arxiv.org/abs/2310.05914 · HTML: https://mlsanity.com/paper/2310.05914/

## Key facts

- Cited by 100 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 9 Oct 2023.

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [FreeLB: Enhanced Adversarial Training for Natural Language Understanding](https://mlsanity.com/paper/1909.11764/) (2019)
- [On the Reliability of Watermarks for Large Language Models](https://mlsanity.com/paper/2306.04634/) (2023)
- [Platypus: Quick, Cheap, and Powerful Refinement of LLMs](https://mlsanity.com/paper/2308.07317/) (2023)
- [Text-Only Training for Image Captioning using Noise-Injected CLIP](https://mlsanity.com/paper/2211.00575/) (2022)
- [Robust Optimization as Data Augmentation for Large-scale Graphs](https://mlsanity.com/paper/2010.09891/) (2020)
- [ZeroPrompt: Scaling Prompt-Based Pretraining to 1,000 Tasks Improves Zero-Shot Generalization](https://mlsanity.com/paper/2201.06910/) (2022)

## Built on by (most cited first, 30 of 100)

- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [What matters when building vision-language models?](https://mlsanity.com/paper/2405.02246/) (2024)
- [Building and better understanding vision-language models: insights and future directions](https://mlsanity.com/paper/2408.12637/) (2024)
- [WARM: On the Benefits of Weight Averaged Reward Models](https://mlsanity.com/paper/2401.12187/) (2024)
- [Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding](https://mlsanity.com/paper/2402.05109/) (2024)
- [From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future](https://mlsanity.com/paper/2408.02479/) (2024)
- [Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning](https://mlsanity.com/paper/2402.04833/) (2024)
- [A Closer Look at the Limitations of Instruction Tuning](https://mlsanity.com/paper/2402.05119/) (2024)
- [Preserving Diversity in Supervised Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2408.16673/) (2024)
- [Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs](https://mlsanity.com/paper/2406.10209/) (2024)
- [Instruction Tuning With Loss Over Instructions](https://mlsanity.com/paper/2405.14394/) (2024)
- [IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations](https://mlsanity.com/paper/2404.01266/) (2024)
- [Interpretable Steering of Large Language Models with Feature Guided Activation Additions](https://mlsanity.com/paper/2501.09929/) (2025)
- [Hermes 3 Technical Report](https://mlsanity.com/paper/2408.11857/) (2024)
- [Automating Research Synthesis with Domain-Specific Large Language Model Fine-Tuning](https://mlsanity.com/paper/2404.08680/) (2024)
- [Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models](https://mlsanity.com/paper/2404.01231/) (2024)
- [Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction](https://mlsanity.com/paper/2504.15266/) (2025)
- [Teuken-7B-Base & Teuken-7B-Instruct: Towards European LLMs](https://mlsanity.com/paper/2410.03730/) (2024)
- [LLM-Assisted Crisis Management: Building Advanced LLM Platforms for Effective Emergency Response and Public Collaboration](https://mlsanity.com/paper/2402.10908/) (2024)
- [Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models](https://mlsanity.com/paper/2403.02178/) (2024)
- [Aloe: A Family of Fine-tuned Open Healthcare LLMs](https://mlsanity.com/paper/2405.01886/) (2024)
- [SweRank: Software Issue Localization with Code Ranking](https://mlsanity.com/paper/2505.07849/) (2025)
- [LM4OPT: Unveiling the Potential of Large Language Models in Formulating Mathematical Optimization Problems](https://mlsanity.com/paper/2403.01342/) (2024)
- [A Survey on Trustworthiness in Foundation Models for Medical Image Analysis](https://mlsanity.com/paper/2407.15851/) (2024)
- [GRIN: GRadient-INformed MoE](https://mlsanity.com/paper/2409.12136/) (2024)
- [TeleChat Technical Report](https://mlsanity.com/paper/2401.03804/) (2024)
- [Differentially Private Steering for Large Language Model Alignment](https://mlsanity.com/paper/2501.18532/) (2025)
- [Disambiguate First, Parse Later: Generating Interpretations for Ambiguity Resolution in Semantic Parsing](https://mlsanity.com/paper/2502.18448/) (2025)
- [T-SHIRT: Token-Selective Hierarchical Data Selection for Instruction Tuning](https://mlsanity.com/paper/2506.01317/) (2025)

## Abstract (arXiv)

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.