Exploring Activation Patterns of Parameters in Language Models

• URL: http://arxiv.org/abs/2405.17799v1
• Date: Tue, 28 May 2024 03:49:54 GMT
• Title: Exploring Activation Patterns of Parameters in Language Models
• Abstract summary: We propose a gradient-based metric to assess the activation level of model parameters. We find that parameters in the shallow layers will be activated densely, which means a larger portion of parameters will have great impacts on the outputs. In deep layers, the similarity of the distributions of activated parameters is positively correlated to the empirical data relevance.
• Score: 27.454051736471374
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Most work treats large language models as black boxes without in-depth understanding of their internal working mechanism. In order to explain the internal representations of LLMs, we propose a gradient-based metric to assess the activation level of model parameters. Based on this metric, we obtain three preliminary findings. (1) When the inputs are in the same domain, parameters in the shallow layers will be activated densely, which means a larger portion of parameters will have great impacts on the outputs. In contrast, parameters in the deep layers are activated sparsely. (2) When the inputs are across different domains, parameters in shallow layers exhibit higher similarity in the activation behavior than deep layers. (3) In deep layers, the similarity of the distributions of activated parameters is positively correlated to the empirical data relevance. Further, we develop three validation experiments to solidify these findings. (1) Firstly, starting from the first finding, we attempt to configure different prune ratios for different layers, and find this method can benefit model pruning. (2) Secondly, we find that a pruned model based on one calibration set can better handle tasks related to the calibration task than those not related, which validate the second finding. (3) Thirdly, Based on the STS-B and SICK benchmark, we find that two sentences with consistent semantics tend to share similar parameter activation patterns in deep layers, which aligns with our third finding. Our work sheds light on the behavior of parameter activation in LLMs, and we hope these findings will have the potential to inspire more practical applications.

Related papers

• Divergent large language model predictions from convergent representations in ambiguous word pairs [2.4087148947930634]
  We investigate how decoder-only transformers resolve lexical ambiguity through layer-by-layer analysis.<n>For both homonyms and polysemes, we find that representations become maximally distinct in middle layers, then partially reconverge in late layers.
  arXiv  Detail & Related papers  (2026-08-03T07:26:45Z)
• When Does Sparsity Mitigate the Curse of Depth in LLMs [53.137717161619484]
  We show that sparsity acts as a regulator of variance propagation and thereby improves depth utilization.<n>Our results reveal sparsity as a key yet previously overlooked mechanism for effective depth scaling in large language models.
  arXiv  Detail & Related papers  (2026-03-16T15:04:16Z)
• Multidimensional Bayesian Active Machine Learning of Working Memory Task Performance [4.8878998002743606]
  We show a validation of a Bayesian, two-axis, active-classification approach for a working-memory reconstruction task.<n>In a young adult population, we compare GP-driven Adaptive Mode (AM) with a traditional adaptive staircase Classic Mode (CM)<n>AM estimates converge more quickly than other sampling strategies, demonstrating that only about 30 samples are required for accurate fitting of the full model.
  arXiv  Detail & Related papers  (2025-10-01T00:48:14Z)
• R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference [77.47238561728459]
  R-Sparse is a training-free activation sparsity approach capable of achieving high sparsity levels in advanced LLMs. Experiments on Llama-2/3 and Mistral models across ten diverse tasks demonstrate that R-Sparse achieves comparable performance at 50% model-level sparsity.
  arXiv  Detail & Related papers  (2025-04-28T03:30:32Z)
• A Sliding Layer Merging Method for Efficient Depth-Wise Pruning in LLMs [14.514670828712669]
  This paper reveals the "Patch-like" feature relationship between layers in large language models by analyzing the correlation of the outputs of different layers in the reproducing kernel Hilbert space. We propose a sliding layer merging method that dynamically selects and fuses consecutive layers from top to bottom according to a pre-defined similarity threshold. Our method outperforms existing pruning techniques in both zero-shot inference performance and retraining recovery quality after pruning.
  arXiv  Detail & Related papers  (2025-02-26T14:15:24Z)
• LESA: Learnable LLM Layer Scaling-Up [57.0510934286449]
  Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive.<n>Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones.<n>We propose textbfLESA, a novel learnable method for depth scaling-up.
  arXiv  Detail & Related papers  (2025-02-19T14:58:48Z)
• Joint Localization and Activation Editing for Low-Resource Fine-Tuning [73.64004083269424]
  We propose a joint localization and activation editing (JoLA) method. JoLA learns (1) which heads in the Transformer to edit (2) whether the intervention should be additive, multiplicative, or both and (3) the intervention parameters themselves. Through evaluations on three benchmarks spanning commonsense reasoning, natural language understanding, and natural language generation, we demonstrate that JoLA consistently outperforms existing methods.
  arXiv  Detail & Related papers  (2025-02-03T09:13:09Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts. Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• On Layer-wise Representation Similarity: Application for Multi-Exit Models with a Single Classifier [20.17288970927518]
  We study the similarity of representations between the hidden layers of individual transformers. We propose an aligned training approach to enhance the similarity between internal representations.
  arXiv  Detail & Related papers  (2024-06-20T16:41:09Z)
• Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient [57.9629676017527]
  We propose an optimization-based structural pruning on Large-Language Models. We learn the pruning masks in a probabilistic space directly by optimizing the loss of the pruned model. Our method operates for 2.7 hours with around 35GB memory for the 13B models on a single A100 GPU.
  arXiv  Detail & Related papers  (2024-06-15T09:31:03Z)
• Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective [106.92016199403042]
  We empirically investigate knowledge transfer from larger to smaller models through a parametric perspective. We employ sensitivity-based techniques to extract and align knowledge-specific parameters between different large language models. Our findings highlight the critical factors contributing to the process of parametric knowledge transfer.
  arXiv  Detail & Related papers  (2023-10-17T17:58:34Z)
• The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute [66.84421705029624]
  We introduce an experimental protocol that enables model comparisons based on equivalent compute, measured in accelerator hours. We pre-process an existing large, diverse, and high-quality dataset of books that surpasses existing academic benchmarks in quality, diversity, and document length. This work also provides two baseline models: a feed-forward model derived from the GPT-2 architecture and a recurrent model in the form of a novel LSTM with ten-fold throughput.
  arXiv  Detail & Related papers  (2023-09-20T10:31:17Z)
• Ladder-of-Thought: Using Knowledge as Steps to Elevate Stance Detection [73.31406286956535]
  We introduce the Ladder-of-Thought (LoT) for the stance detection task. LoT directs the small LMs to assimilate high-quality external knowledge, refining the intermediate rationales produced. Our empirical evaluations underscore LoT's efficacy, marking a 16% improvement over GPT-3.5 and a 10% enhancement compared to GPT-3.5 with CoT on stance detection task.
  arXiv  Detail & Related papers  (2023-08-31T14:31:48Z)
• Part-guided Relational Transformers for Fine-grained Visual Recognition [59.20531172172135]
  We propose a framework to learn the discriminative part features and explore correlations with a feature transformation module. Our proposed approach does not rely on additional part branches and reaches state-the-of-art performance on 3-of-the-level object recognition.
  arXiv  Detail & Related papers  (2022-12-28T03:45:56Z)
• Adapted Multimodal BERT with Layer-wise Fusion for Sentiment Analysis [84.12658971655253]
  We propose Adapted Multimodal BERT, a BERT-based architecture for multimodal tasks. adapter adjusts the pretrained language model for the task at hand, while the fusion layers perform task-specific, layer-wise fusion of audio-visual information with textual BERT representations. In our ablations we see that this approach leads to efficient models, that can outperform their fine-tuned counterparts and are robust to input noise.
  arXiv  Detail & Related papers  (2022-12-01T17:31:42Z)
• BERMo: What can BERT learn from ELMo? [6.417011237981518]
  We use linear combination scheme proposed in Embeddings from Language Models (ELMo) to combine the scaled internal representations from different network depths. Our approach has two-fold benefits: (1) improved gradient flow for the downstream task and (2) increased representative power.
  arXiv  Detail & Related papers  (2021-10-18T17:35:41Z)
• Layer Reduction: Accelerating Conformer-Based Self-Supervised Model via Layer Consistency [31.572652956170252]
  Transformer-based self-supervised models are trained as feature extractors and have empowered many downstream speech tasks to achieve state-of-the-art performance. We experimentally achieve 7.8X parameter reduction, 41.9% training speedup and 37.7% inference speedup while maintaining comparable performance with conventional BERT-like self-supervised methods.
  arXiv  Detail & Related papers  (2021-04-08T08:21:59Z)
• Associating Multi-Scale Receptive Fields for Fine-grained Recognition [5.079292308180334]
  We propose a novel cross-layer non-local (CNL) module to associate multi-scale receptive fields by two operations. CNL computes correlations between features of a query layer and all response layers. Our model builds spatial dependencies among multi-level layers and learns more discriminative features.
  arXiv  Detail & Related papers  (2020-05-19T01:16:31Z)

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.