LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions

• URL: http://arxiv.org/abs/2505.23811v2
• Date: Tue, 03 Jun 2025 21:18:10 GMT
• Title: LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions
• Authors: Hadi Askari, Shivanshu Gupta, Fei Wang, Anshuman Chhabra, Muhao Chen,
• Abstract summary: Pretrained Large Language Models (LLMs) achieve strong performance across a wide range of tasks.<n>LLMs exhibit substantial variability in the various layers' training quality with respect to specific downstream applications.<n>We propose LayerIF to quantify the training quality of individual layers in a principled and task-sensitive manner.
• Score: 33.23446361483562
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pretrained Large Language Models (LLMs) achieve strong performance across a wide range of tasks, yet exhibit substantial variability in the various layers' training quality with respect to specific downstream applications, limiting their downstream performance. It is therefore critical to estimate layer-wise training quality in a manner that accounts for both model architecture and training data. However, existing approaches predominantly rely on model-centric heuristics (such as spectral statistics, outlier detection, or uniform allocation) while overlooking the influence of data. To address these limitations, we propose LayerIF, a data-driven framework that leverages Influence Functions to quantify the training quality of individual layers in a principled and task-sensitive manner. By isolating each layer's gradients and measuring the sensitivity of the validation loss to training examples by computing layer-wise influences, we derive data-driven estimates of layer importance. Notably, our method produces task-specific layer importance estimates for the same LLM, revealing how layers specialize for different test-time evaluation tasks. We demonstrate the utility of our scores by leveraging them for two downstream applications: (a) expert allocation in LoRA-MoE architectures and (b) layer-wise sparsity distribution for LLM pruning. Experiments across multiple LLM architectures demonstrate that our model-agnostic, influence-guided allocation leads to consistent gains in task performance.

Related papers

• Layer-Aware Embedding Fusion for LLMs in Text Classifications [1.4250487522292254]
  We propose a layer-aware embedding selection method and investigate how to quantitatively evaluate different layers to identify the most important ones for downstream NLP tasks.<n>Experiments on four English text classification datasets demonstrate that different layers in LLMs exhibit varying degrees of representational strength for classification.<n>We also explore how combining embeddings from multiple LLMs, without requiring model fine-tuning, can improve performance.
  arXiv  Detail & Related papers  (2025-04-08T07:45:50Z)
• Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning [61.99353167168545]
  We show that fine-tuning with LLM-generated data improves target task performance and reduces non-target task degradation.<n>This is the first work to provide an empirical explanation based on token perplexity reduction to mitigate catastrophic forgetting in LLMs after fine-tuning.
  arXiv  Detail & Related papers  (2025-01-24T08:18:56Z)
• Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning [104.27224674122313]
  Fine-tuning MLLM has become a common practice to improve performance on specific downstream tasks. To balance the trade-off between generalization and specialization, we propose measuring the parameter importance for both pre-trained and fine-tuning distributions.
  arXiv  Detail & Related papers  (2024-11-17T01:16:37Z)
• Layer Importance and Hallucination Analysis in Large Language Models via Enhanced Activation Variance-Sparsity [5.854247492297834]
  This paper first explores layer importance using the Activation Variance-Sparsity Score (AVSS) Building on AVSS, we propose an enhanced version tailored to assess hallucination propensity across layers (EAVSS) This improved approach introduces Hallucination-Specific Activation Variance (HSAV) and Hallucination-Specific Sparsity (HSS) metrics, allowing precise identification of hallucination-prone layers.
  arXiv  Detail & Related papers  (2024-11-15T09:33:47Z)
• AVSS: Layer Importance Evaluation in Large Language Models via Activation Variance-Sparsity Analysis [5.854247492297834]
  We propose a novel metric combining normalized activation variance and sparsity to assess each layer's contribution to model performance. By identifying and removing approximately the lowest 25% of layers based on AVSS, we achieve over 90% of original model performance.
  arXiv  Detail & Related papers  (2024-11-04T14:29:49Z)
• Understanding Layer Significance in LLM Alignment [23.582520695083588]
  We propose identifying which layers within large language models are most critical to the alignment process.<n> Experimental results reveal that, despite substantial differences in alignment datasets, the important layers of a model exhibit nearly 90% overlap.<n>The results also indicate that freezing non-essential layers improves overall model performance, while selectively tuning the most critical layers significantly enhances fine-tuning efficiency with minimal performance loss.
  arXiv  Detail & Related papers  (2024-10-23T13:47:05Z)
• 60 Data Points are Sufficient to Fine-Tune LLMs for Question-Answering [50.12622877002846]
  Large language models (LLMs) encode extensive world knowledge through pre-training on massive datasets, which can be fine-tuned for the question-answering (QA) task.<n>We categorize supervised fine-tuning (SFT) data based on the extent of knowledge memorized by the pretrained LLMs.<n>Our experiments show that as few as 60 data points during the SFT stage can activate the knowledge encoded during pre-training, enabling LLMs to perform the QA task.
  arXiv  Detail & Related papers  (2024-09-24T07:38:38Z)
• Performance Law of Large Language Models [58.32539851241063]
  Performance law can be used to guide the choice of LLM architecture and the effective allocation of computational resources. Performance law can be used to guide the choice of LLM architecture and the effective allocation of computational resources without extensive experiments.
  arXiv  Detail & Related papers  (2024-08-19T11:09:12Z)
• Comprehensive Reassessment of Large-Scale Evaluation Outcomes in LLMs: A Multifaceted Statistical Approach [64.42462708687921]
  Evaluations have revealed that factors such as scaling, training types, architectures and other factors profoundly impact the performance of LLMs. Our study embarks on a thorough re-examination of these LLMs, targeting the inadequacies in current evaluation methods. This includes the application of ANOVA, Tukey HSD tests, GAMM, and clustering technique.
  arXiv  Detail & Related papers  (2024-03-22T14:47:35Z)
• From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning [52.257422715393574]
  We introduce a self-guided methodology for Large Language Models (LLMs) to autonomously discern and select cherry samples from open-source datasets. Our key innovation, the Instruction-Following Difficulty (IFD) metric, emerges as a pivotal metric to identify discrepancies between a model's expected responses and its intrinsic generation capability.
  arXiv  Detail & Related papers  (2023-08-23T09:45:29Z)
• Comparative layer-wise analysis of self-supervised speech models [29.258085176788097]
  We measure acoustic, phonetic, and word-level properties encoded in individual layers, using a lightweight analysis tool based on canonical correlation analysis (CCA) We find that these properties evolve across layers differently depending on the model, and the variations relate to the choice of pre-training objective. We discover that CCA trends provide reliable guidance to choose layers of interest for downstream tasks and that single-layer performance often matches or improves upon using all layers, suggesting implications for more efficient use of pre-trained models.
  arXiv  Detail & Related papers  (2022-11-08T00:59:05Z)
• Influence Functions in Deep Learning Are Fragile [52.31375893260445]
  influence functions approximate the effect of samples in test-time predictions. influence estimates are fairly accurate for shallow networks. Hessian regularization is important to get highquality influence estimates.
  arXiv  Detail & Related papers  (2020-06-25T18:25:59Z)

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.