The Curse of Depth in Large Language Models

• URL: http://arxiv.org/abs/2502.05795v2
• Date: Tue, 01 Jul 2025 08:18:41 GMT
• Title: The Curse of Depth in Large Language Models
• Authors: Wenfang Sun, Xinyuan Song, Pengxiang Li, Lu Yin, Yefeng Zheng, Shiwei Liu,
• Abstract summary: In large language models, nearly half of the layers are less effective than expected.<n>LayerNorm Scaling (LNS) scales the variance of output of the layer normalization inversely by the square root of its depth.<n>LNS consistently outperforms previous normalization and scaling techniques in enhancing LLM pre-training performance.
• Score: 28.37870372690079
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In this paper, we introduce the Curse of Depth, a concept that highlights, explains, and addresses the recent observation in modern Large Language Models (LLMs) where nearly half of the layers are less effective than expected. We first confirm the wide existence of this phenomenon across the most popular families of LLMs such as Llama, Mistral, DeepSeek, and Qwen. Our analysis, theoretically and empirically, identifies that the underlying reason for the ineffectiveness of deep layers in LLMs is the widespread usage of Pre-Layer Normalization (Pre-LN). While Pre-LN stabilizes the training of Transformer LLMs, its output variance exponentially grows with the model depth, which undesirably causes the derivative of the deep Transformer blocks to be an identity matrix, and therefore barely contributes to the training. To resolve this training pitfall, we propose LayerNorm Scaling (LNS), which scales the variance of output of the layer normalization inversely by the square root of its depth. This simple modification mitigates the output variance explosion of deeper Transformer layers, improving their contribution. Across a wide range of model sizes (130M to 7B), our experiments show that LNS consistently outperforms previous normalization and scaling techniques in enhancing LLM pre-training performance. Moreover, this improvement seamlessly carries over to supervised fine-tuning. All these gains can be attributed to the fact that LayerNorm Scaling enables deeper layers to contribute more effectively during training. Our code is available at \href{https://github.com/lmsdss/LayerNorm-Scaling}{LayerNorm-Scaling}.

Related papers

• GPAS: Accelerating Convergence of LLM Pretraining via Gradient-Preserving Activation Scaling [39.3376897081385]
  We propose Gradient-Preserving Activation Scaling (GPAS), a technique that can be used in combination with existing approaches.<n>GPAS works by scaling down the intermediate activations while keeping their gradients unchanged.<n>Experiments across various model sizes from 71M to 1B show that GPAS achieves consistent performance gains.
  arXiv  Detail & Related papers  (2025-06-27T09:45:15Z)
• Training-Free Reasoning and Reflection in MLLMs [45.134271969594614]
  This paper introduces FRANK Model, a training-FRee ANd r1-liKe MLLM that imbues off-the-shelf MLLMs with reasoning and reflection abilities.<n>Our key insight is to decouple perception and reasoning across MLLM decoder layers.<n>To this end, we propose a layer-wise, Taylor-derived closed-form fusion mechanism that integrates reasoning capacity into deep decoder layers.
  arXiv  Detail & Related papers  (2025-05-22T02:51:12Z)
• Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective [55.90119819642064]
  We address the challenge of determining the layer-wise sparsity rates of large language models (LLMs) through a theoretical perspective. This refers to the cumulative effect of reconstruction errors throughout the sparsification process. We derive a simple yet effective approach to layer-wise sparsity allocation that mitigates this issue.
  arXiv  Detail & Related papers  (2025-02-20T17:51:10Z)
• LESA: Learnable LLM Layer Scaling-Up [57.0510934286449]
  Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive. Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones. We propose textbfLESA, a novel learnable method for depth scaling-up.
  arXiv  Detail & Related papers  (2025-02-19T14:58:48Z)
• AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models [94.82766517752418]
  We propose AlphaPruning, which uses shape metrics to allocate layerwise sparsity ratios in a more theoretically principled manner. Our results show that AlphaPruning prunes LLaMA-7B to 80% sparsity while maintaining reasonable perplexity, marking a first in the literature on LLMs.
  arXiv  Detail & Related papers  (2024-10-14T03:35:11Z)
• Zeroth-Order Fine-Tuning of LLMs in Random Subspaces [66.27334633749734]
  As language models grow in size, memory demands for backpropagation increase. Zeroth-order (ZOZO) optimization methods offer a memory-efficient alternative. We show that SubZero enhances fine-tuning and achieves faster results compared to standard ZOZO approaches.
  arXiv  Detail & Related papers  (2024-10-11T17:01:43Z)
• Investigating Layer Importance in Large Language Models [28.156622049937216]
  Large language models (LLMs) have gained increasing attention due to their prominent ability to understand and process texts. The lack of understanding of LLMs has obstructed the deployment in safety-critical scenarios and hindered the development of better models. This study identifies cornerstone layers in LLMs and underscores their critical role for future research.
  arXiv  Detail & Related papers  (2024-09-22T09:53:13Z)
• DLO: Dynamic Layer Operation for Efficient Vertical Scaling of LLMs [46.443316184807145]
  We introduce Dynamic Layer Operations (DLO), a novel approach for vertically scaling transformer-based Large Language Models (LLMs) Unlike traditional Mixture-of-Experts (MoE) methods that focus on extending the model width, our approach targets model depth, addressing the redundancy observed across layer representations for various input samples. Experimental results demonstrate that DLO not only outperforms the original unscaled models but also achieves comparable results to densely expanded models with significantly improved efficiency.
  arXiv  Detail & Related papers  (2024-07-03T18:34:08Z)
• Temporal Scaling Law for Large Language Models [57.83580734589091]
  We propose the novel concept of Temporal Scaling Law, studying how the test loss of an LLM evolves as the training steps scale up.<n>In contrast to modeling the test loss as a whole in a coarse-grained manner, we break it down and dive into the fine-grained test loss of each token position.<n>We derive the much more precise temporal scaling law by studying the temporal patterns of the parameters in the dynamic hyperbolic-law.
  arXiv  Detail & Related papers  (2024-04-27T05:49:11Z)
• Streamlining Redundant Layers to Compress Large Language Models [21.27944103424621]
  This paper introduces LLM-Streamline, a pioneer work on layer pruning for large language models (LLMs)<n>It is based on the observation that different layers have varying impacts on hidden states, enabling the identification of less important layers to be pruned.<n>Experiments show that LLM-Streamline outperforms both previous and concurrent state-of-the-art pruning methods in terms of both performance and training efficiency.
  arXiv  Detail & Related papers  (2024-03-28T04:12:13Z)
• ShortGPT: Layers in Large Language Models are More Redundant Than You Expect [38.148626520751385]
  We show that many layers of Large Language Models (LLMs) exhibit high similarity, and some layers play a negligible role in network functionality. We propose a straightforward pruning approach: layer removal, in which we directly delete the redundant layers. Experiments demonstrate that our method, which we call ShortGPT, significantly outperforms previous state-of-the-art (SOTA) methods in model pruning.
  arXiv  Detail & Related papers  (2024-03-06T17:04:18Z)
• Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs [67.38165028487242]
  We introduce Dynamic Sparse No Training (DSnoT), a training-free fine-tuning approach to fine-tune large language models (LLMs) Inspired by the Dynamic Sparse Training, DSnoT minimizes the reconstruction error between the dense and sparse LLMs. Our paper offers fresh insights into how to fine-tune sparse LLMs in an efficient training-free manner and open new venues to scale the great potential of sparsity to LLMs.
  arXiv  Detail & Related papers  (2023-10-13T07:38:52Z)
• Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity [88.62935593360162]
  Large Language Models (LLMs) are renowned for their remarkable performance across diverse domains. We introduce a novel LLM pruning methodology that incorporates a tailored set of non-uniform layerwise sparsity ratios, termed as Outlier Weighed Layerwise sparsity (OWL) OWL exhibits a remarkable performance gain, surpassing the state-of-the-art Wanda and SparseGPT by 61.22 and 6.80 perplexity at a high sparsity level of 70%, respectively.
  arXiv  Detail & Related papers  (2023-10-08T14:22:58Z)
• DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models [79.01926242857613]
  Large language models (LLMs) are prone to hallucinations, generating content that deviates from facts seen during pretraining. We propose a simple decoding strategy for reducing hallucinations with pretrained LLMs. We find that this Decoding by Contrasting Layers (DoLa) approach is able to better surface factual knowledge and reduce the generation of incorrect facts.
  arXiv  Detail & Related papers  (2023-09-07T17:45:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.