Rethinking the Outlier Distribution in Large Language Models: An In-depth Study

ACL ARR 2025 February Submission5752 Authors

16 Feb 2025 (modified: 09 May 2025)ACL ARR 2025 February SubmissionEveryoneRevisionsBibTeXCC BY 4.0
Abstract:

Investigating outliers in large language models (LLMs) is crucial due to their significant impact on various aspects of LLM performance, including quantization and compression. Outliers often cause considerable quantization errors, leading to degraded model performance. Identifying and addressing these outliers can enhance the accuracy and efficiency of the quantization process, enabling smoother deployment on edge devices or specialized hardware. Recent studies have identified two common types of outliers in LLMs: massive activations and channel-wise outliers. While numerous quantization algorithms have been proposed to mitigate their effects and maintain satisfactory accuracy, few have thoroughly explored the root causes of these outliers in depth.

In this paper, we conduct a comprehensive investigation into the formation mechanisms of these outliers and propose potential strategies to mitigate their occurrence. Ultimately, we introduce some efficient approaches to eliminate most massive activations and channel-wise outliers, facilitating efficient quantization.

Paper Type: Long
Research Area: Efficient/Low-Resource Methods for NLP
Research Area Keywords: Large Language Model, Outlier, Efficient AI
Languages Studied: English
Submission Number: 5752
Loading