ALPINE: An adaptive language-agnostic pruning method for language models for code

• URL: http://arxiv.org/abs/2407.04147v2
• Date: Mon, 10 Feb 2025 21:18:04 GMT
• Title: ALPINE: An adaptive language-agnostic pruning method for language models for code
• Abstract summary: Language models of code have demonstrated state-of-the-art performance across various software engineering and source code analysis tasks.<n>This work introduces ALPINE, an adaptive programming language-agnostic pruning technique designed to substantially reduce these models' computational overhead.<n>Experiments on two software engineering tasks, defect prediction and code clone detection across three language models CodeBERT, GraphCodeBERT and UniXCoder show that ALPINE achieves up to a 50% reduction in FLOPs, a 58.1% decrease in memory footprint, and a 28.1% improvement in throughput on average.
• Score: 4.148857672591562
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Language models of code have demonstrated state-of-the-art performance across various software engineering and source code analysis tasks. However, their demanding computational resource requirements and consequential environmental footprint remain as significant challenges. This work introduces ALPINE, an adaptive programming language-agnostic pruning technique designed to substantially reduce these models' computational overhead. The proposed method offers a pluggable layer that can be integrated with all Transformer-based models. With ALPINE, input sequences undergo adaptive compression throughout the pipeline, reaching a size up to $\times 3$ less their initial size, resulting in significantly reduced computational load. Our experiments on two software engineering tasks, defect prediction and code clone detection across three language models CodeBERT, GraphCodeBERT and UniXCoder show that ALPINE achieves up to a 50% reduction in FLOPs, a 58.1% decrease in memory footprint, and a 28.1% improvement in throughput on average. This led to a reduction in CO2 by up to $44.85$%. Importantly, it achieves the reduction in computation resources while maintaining up to 98.1% of the original predictive performance. These findings highlight the potential of ALPINE in making language models of code more resource-efficient and accessible while preserving their performance, contributing to the overall sustainability of adopting language models in software development. Also, it sheds light on redundant and noisy information in source code analysis corpora, as shown by the substantial sequence compression achieved by ALPINE.

Related papers

• Compiling Code LLMs into Lightweight Executables [18.677096682203697]
  Ditto is a novel method for optimizing both the model size of Code LLMs and their inference programs.<n>We evaluate Ditto on three popular Code LLMs, achieving up to 10.5$times$ lower memory usage compared with their original inference pipeline.
  arXiv  Detail & Related papers  (2026-03-31T14:40:19Z)
• AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent [80.83250816918861]
  Large Reasoning Models (LRMs) like o3 and DeepSeek-R1 have achieved remarkable progress in natural language reasoning with long chain-of-thought.<n>However, they remain computationally inefficient and struggle with accuracy when solving problems requiring complex mathematical operations.<n>We present AgentMath, an agent framework that seamlessly integrates language models' reasoning capabilities with code interpreters' computational precision.
  arXiv  Detail & Related papers  (2025-12-23T19:57:49Z)
• Zero-Shot Performance Prediction for Probabilistic Scaling Laws [20.863873378387865]
  The prediction of learning curves for Natural Language Processing (NLP) models enables informed decision-making.<n>We formulate the prediction task as a multitask learning problem, where each task's data is modelled as being organized within a two-layer hierarchy.<n>We validate our framework on three small-scale NLP datasets with up to $30$ LCs.
  arXiv  Detail & Related papers  (2025-10-19T07:56:25Z)
• Accelerated Test-Time Scaling with Model-Free Speculative Sampling [58.69141724095398]
  We introduce STAND (STochastic Adaptive N-gram Drafting), a novel model-free speculative decoding approach.<n>We show that STAND reduces inference latency by 60-65% compared to standard autoregressive decoding.<n>As a model-free approach, STAND can be applied to any existing language model without additional training.
  arXiv  Detail & Related papers  (2025-06-05T07:31:18Z)
• QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation [51.393569044134445]
  Large language models (LLMs) trained via reinforcement learning with verifiable reward (RLVR) have achieved breakthroughs on tasks with explicit, automatable verification.<n> Extending RLVR to automatically generating hardware description languages (HDLs) like Verilog from natural-language (NL) specifications, however, poses three key challenges.<n>We introduce CodeV-R1, an RLVR framework for training Verilog generation LLMs.
  arXiv  Detail & Related papers  (2025-05-30T03:51:06Z)
• NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding [54.88765757043535]
  This work rethinks data structures for statistical n-gram language models to enable fast and parallel operations for GPU-optimized inference.<n>Our approach, named NGPU-LM, introduces customizable greedy decoding for all major ASR model types with less than 7% computational overhead.<n>The proposed approach can eliminate more than 50% of the accuracy gap between greedy and beam search for out-of-domain scenarios while avoiding significant slowdown caused by beam search.
  arXiv  Detail & Related papers  (2025-05-28T20:43:10Z)
• EquiBench: Benchmarking Code Reasoning Capabilities of Large Language Models via Equivalence Checking [54.354203142828084]
  We present the task of equivalence checking as a new way to evaluate the code reasoning abilities of large language models. We introduce EquiBench, a dataset of 2400 program pairs spanning four programming languages and six equivalence categories. Our evaluation of 17 state-of-the-art LLMs shows that OpenAI o3-mini achieves the highest overall accuracy of 78.0%.
  arXiv  Detail & Related papers  (2025-02-18T02:54:25Z)
• Transformer^-1: Input-Adaptive Computation for Resource-Constrained Deployment [3.6219999155937113]
  This paper proposes a Transformer$-1$ architecture to address the resource waste caused by fixed computation paradigms in deep learning models under dynamic scenarios. In a benchmark test, our method reduces FLOPs by 42.7% and peak memory usage by 3% compared to the standard Transformer. We also conducted experiments on several natural language processing tasks and achieved significant improvements in resource efficiency.
  arXiv  Detail & Related papers  (2025-01-26T15:31:45Z)
• Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning [73.73967342609603]
  We introduce a predictor-corrector learning framework to minimize truncation errors. We also propose an exponential moving average-based coefficient learning method to strengthen our higher-order predictor. Our model surpasses a robust 3.8B DeepNet by an average of 2.9 SacreBLEU, using only 1/3 parameters.
  arXiv  Detail & Related papers  (2024-11-05T12:26:25Z)
• ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models [14.310720048047136]
  ALPS is an optimization-based framework that tackles the pruning problem using the operator splitting technique and a preconditioned gradient conjugate-based post-processing step. Our approach incorporates novel techniques to accelerate and theoretically guarantee convergence while leveraging vectorization and GPU parallelism for efficiency. On the OPT-30B model with 70% sparsity, ALPS achieves a 13% reduction in test perplexity on the WikiText dataset and a 19% improvement in zero-shot benchmark performance compared to existing methods.
  arXiv  Detail & Related papers  (2024-06-12T02:57:41Z)
• Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs [57.27982780697922]
  Large language models have demonstrated exceptional capability in natural language understanding and generation. However, their generation speed is limited by the inherently sequential nature of their decoding process. This paper introduces Lexical Unit Decoding, a novel decoding methodology implemented in a data-driven manner.
  arXiv  Detail & Related papers  (2024-05-24T04:35:13Z)
• Exploring the Impact of the Output Format on the Evaluation of Large Language Models for Code Translation [8.81447711370817]
  We empirically analyze the generated outputs of eleven popular instruct-tuned large language models (LLMs) Our results demonstrate that a strategic combination of prompt engineering and regular expression can effectively extract the source code from the model generation output.
  arXiv  Detail & Related papers  (2024-03-25T21:41:31Z)
• Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generation [32.178931149612644]
  ulModel ulImprovement via ulNeuron ulTargeting (textscMINT) is a novel approach for repairing code Language Models (LMs) textscMINT is effective, efficient, and reliable, capable of correcting a neural model by patching a minimum number of neurons.
  arXiv  Detail & Related papers  (2023-12-08T20:28:08Z)
• CodeGen2: Lessons for Training LLMs on Programming and Natural Languages [116.74407069443895]
  We unify encoder and decoder-based models into a single prefix-LM. For learning methods, we explore the claim of a "free lunch" hypothesis. For data distributions, the effect of a mixture distribution and multi-epoch training of programming and natural languages on model performance is explored.
  arXiv  Detail & Related papers  (2023-05-03T17:55:25Z)
• Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods [91.54785981649228]
  This paper focuses on non-linear two-layer autoencoders trained in the challenging proportional regime. Our results characterize the minimizers of the population risk, and show that such minimizers are achieved by gradient methods. For the special case of a sign activation function, our analysis establishes the fundamental limits for the lossy compression of Gaussian sources via (shallow) autoencoders.
  arXiv  Detail & Related papers  (2022-12-27T12:37:34Z)
• You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model [37.24203191658052]
  Large-scale Transformer models bring significant improvements for various downstream vision language tasks with a unified architecture. Performance improvements come with increasing model size, resulting in slow inference speed and increased cost for severing. We propose a novel early exiting strategy for unified visual language models, which allows dynamically skip the layers in encoder and decoder simultaneously.
  arXiv  Detail & Related papers  (2022-11-21T02:32:25Z)
• Confident Adaptive Language Modeling [95.45272377648773]
  CALM is a framework for dynamically allocating different amounts of compute per input and generation timestep. We demonstrate the efficacy of our framework in reducing compute -- potential speedup of up to $times 3$ -- while provably maintaining high performance.
  arXiv  Detail & Related papers  (2022-07-14T17:00:19Z)
• ALF: Autoencoder-based Low-rank Filter-sharing for Efficient Convolutional Neural Networks [63.91384986073851]
  We propose the autoencoder-based low-rank filter-sharing technique technique (ALF) ALF shows a reduction of 70% in network parameters, 61% in operations and 41% in execution time, with minimal loss in accuracy.
  arXiv  Detail & Related papers  (2020-07-27T09:01:22Z)

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.