What is Wrong with Perplexity for Long-context Language Modeling?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fang, Lizhe, Wang, Yifei, Liu, Zhaoyang, Zhang, Chenheng, Jegelka, Stefanie, Gao, Jinyang, Ding, Bolin, Wang, Yisen
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911078815891456
author Fang, Lizhe
Wang, Yifei
Liu, Zhaoyang
Zhang, Chenheng
Jegelka, Stefanie
Gao, Jinyang
Ding, Bolin
Wang, Yisen
author_facet Fang, Lizhe
Wang, Yifei
Liu, Zhaoyang
Zhang, Chenheng
Jegelka, Stefanie
Gao, Jinyang
Ding, Bolin
Wang, Yisen
contents Handling long-context inputs is crucial for large language models (LLMs) in tasks such as extended conversations, document summarization, and many-shot in-context learning. While recent approaches have extended the context windows of LLMs and employed perplexity (PPL) as a standard evaluation metric, PPL has proven unreliable for assessing long-context capabilities. The underlying cause of this limitation has remained unclear. In this work, we provide a comprehensive explanation for this issue. We find that PPL overlooks key tokens, which are essential for long-context understanding, by averaging across all tokens and thereby obscuring the true performance of models in long-context scenarios. To address this, we propose \textbf{LongPPL}, a novel metric that focuses on key tokens by employing a long-short context contrastive method to identify them. Our experiments demonstrate that LongPPL strongly correlates with performance on various long-context benchmarks (e.g., Pearson correlation of -0.96), significantly outperforming traditional PPL in predictive accuracy. Additionally, we introduce \textbf{LongCE} (Long-context Cross-Entropy) loss, a re-weighting strategy for fine-tuning that prioritizes key tokens, leading to consistent improvements across diverse benchmarks. In summary, these contributions offer deeper insights into the limitations of PPL and present effective solutions for accurately evaluating and enhancing the long-context capabilities of LLMs. Code is available at https://github.com/PKU-ML/LongPPL.
format Preprint
id arxiv_https___arxiv_org_abs_2410_23771
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle What is Wrong with Perplexity for Long-context Language Modeling?
Fang, Lizhe
Wang, Yifei
Liu, Zhaoyang
Zhang, Chenheng
Jegelka, Stefanie
Gao, Jinyang
Ding, Bolin
Wang, Yisen
Computation and Language
Machine Learning
Handling long-context inputs is crucial for large language models (LLMs) in tasks such as extended conversations, document summarization, and many-shot in-context learning. While recent approaches have extended the context windows of LLMs and employed perplexity (PPL) as a standard evaluation metric, PPL has proven unreliable for assessing long-context capabilities. The underlying cause of this limitation has remained unclear. In this work, we provide a comprehensive explanation for this issue. We find that PPL overlooks key tokens, which are essential for long-context understanding, by averaging across all tokens and thereby obscuring the true performance of models in long-context scenarios. To address this, we propose \textbf{LongPPL}, a novel metric that focuses on key tokens by employing a long-short context contrastive method to identify them. Our experiments demonstrate that LongPPL strongly correlates with performance on various long-context benchmarks (e.g., Pearson correlation of -0.96), significantly outperforming traditional PPL in predictive accuracy. Additionally, we introduce \textbf{LongCE} (Long-context Cross-Entropy) loss, a re-weighting strategy for fine-tuning that prioritizes key tokens, leading to consistent improvements across diverse benchmarks. In summary, these contributions offer deeper insights into the limitations of PPL and present effective solutions for accurately evaluating and enhancing the long-context capabilities of LLMs. Code is available at https://github.com/PKU-ML/LongPPL.
title What is Wrong with Perplexity for Long-context Language Modeling?
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2410.23771