Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Understanding and Improving Noisy Embedding Techniques in Instruction Finetuning

About

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 outperforms Gaussian noise, the reasons for this remain unclear. This paper aims to clarify this by offering a thorough analysis, both theoretical and empirical, indicating comparable performance among these noise types. Additionally, we introduce a new fine-tuning method for language models, utilizing symmetric noise in embeddings. This method aims to enhance the model's function by more stringently regulating its local curvature, demonstrating superior performance over the current method, NEFTune. When fine-tuning the LLaMA-2-7B model using Alpaca, standard techniques yield a 29.79% score on AlpacaEval. However, our approach, SymNoise, increases this score significantly to 69.04%, using symmetric noisy embeddings. This is a 6.7% improvement over the state-of-the-art method, NEFTune (64.69%). Furthermore, when tested on various models and stronger baseline instruction datasets, such as Evol-Instruct, ShareGPT, OpenPlatypus, SymNoise consistently outperforms NEFTune. The current literature, including NEFTune, has underscored the importance of more in-depth research into the application of noise-based strategies in the fine-tuning of language models. Our approach, SymNoise, is another significant step towards this direction, showing notable improvement over the existing state-of-the-art method.

Abhay Yadav• 2026

Related benchmarks

TaskDatasetResultRank
Commonsense ReasoningHellaSwag
HellaSwag Accuracy80.8
711
Instruction FollowingAlpacaEval
Win Rate69.8
420
ReasoningARC
Accuracy56
245
Language UnderstandingMMLU
MMLU Accuracy47.9
147
Showing 4 of 4 rows

Other info

Follow for update