Why Personalizing Deep Learning-Based Code Completion Tools Matters

• URL: http://arxiv.org/abs/2503.14201v1
• Date: Tue, 18 Mar 2025 12:26:06 GMT
• Title: Why Personalizing Deep Learning-Based Code Completion Tools Matters
• Authors: Alessandro Giagnorio, Alberto Martin-Lopez, Gabriele Bavota,
• Abstract summary: We consider 136 developers from two organizations (Apache and Spring), two model architectures (T5 and Code Llama), and three model sizes (60M, 750M, and 7B trainable parameters)<n>For the Code Llama model (7B), we compared the performance of the already pre-trained model publicly available online with the same model fine-tuned on organization- and developer-specific datasets.<n>Our results show that there is a boost in prediction capabilities provided by both an organization-specific and a developer-specific additional fine-tuning.
• Score: 55.39571645315926
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning (DL)-based code completion tools have transformed software development by enabling advanced code generation. These tools leverage models trained on vast amounts of code from numerous repositories, capturing general coding patterns. However, the impact of fine-tuning these models for specific organizations or developers to boost their performance on such subjects remains unexplored. In this work, we fill this gap by presenting solid empirical evidence answering this question. More specifically, we consider 136 developers from two organizations (Apache and Spring), two model architectures (T5 and Code Llama), and three model sizes (60M, 750M, and 7B trainable parameters). T5 models (60M, 750M) were pre-trained and fine-tuned on over 2,000 open-source projects, excluding the subject organizations' data, and compared against versions fine-tuned on organization- and developer-specific datasets. For the Code Llama model (7B), we compared the performance of the already pre-trained model publicly available online with the same model fine-tuned via parameter-efficient fine-tuning on organization- and developer-specific datasets. Our results show that there is a boost in prediction capabilities provided by both an organization-specific and a developer-specific additional fine-tuning, with the former being particularly performant. Such a finding generalizes across (i) the two subject organizations (i.e., Apache and Spring) and (ii) models of completely different magnitude (from 60M to 7B trainable parameters). Finally, we show that DL models fine-tuned on an organization-specific dataset achieve the same completion performance of pre-trained code models used out of the box and being $\sim$10$\times$ larger, with consequent savings in terms of deployment and inference cost (e.g., smaller GPUs needed).

Related papers

• How to Select Pre-Trained Code Models for Reuse? A Learning Perspective [29.83900262273832]
  Off-the-shelf Pre-trained Code Models (PCMs) have been released publicly. We conduct experiments on 100 widely-used opensource PCMs for code intelligence tasks, with sizes ranging from 42.5 million to 3 billion parameters. The results demonstrate that learning-based selection methods reduce selection time to 100 seconds, compared to 2,700 hours with brute-force fine-tuning.
  arXiv  Detail & Related papers  (2025-01-07T13:45:24Z)
• Language Models as Continuous Self-Evolving Data Engineers [32.67875951851165]
  Large Language Models (LLMs) have demonstrated remarkable capabilities on various tasks. Traditional training approaches rely too much on expert-labeled data. We propose a novel paradigm named LANCE that enables LLMs to train themselves by autonomously generating, cleaning, reviewing, and annotating data.
  arXiv  Detail & Related papers  (2024-12-19T18:28:41Z)
• What matters when building vision-language models? [52.8539131958858]
  We develop Idefics2, an efficient foundational vision-language model with 8 billion parameters. Idefics2 achieves state-of-the-art performance within its size category across various multimodal benchmarks. We release the model (base, instructed, and chat) along with the datasets created for its training.
  arXiv  Detail & Related papers  (2024-05-03T17:00:00Z)
• An Exploratory Study on Automatic Identification of Assumptions in the Development of Deep Learning Frameworks [3.457512613793633]
  Existing approaches and tools for assumption management usually depend on manual identification of assumptions. This study intends to evaluate different classification models for the purpose of identification with respect to assumptions from the point of view of developers and users.
  arXiv  Detail & Related papers  (2024-01-08T03:50:03Z)
• How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources [117.6496550359768]
  This work explores recent advances in instruction-tuning language models on a range of open instruction-following datasets. We provide a large set of instruction-tuned models from 6.7B to 65B parameters in size, trained on 12 instruction datasets. We evaluate them on their factual knowledge, reasoning, multilinguality, coding, and open-ended instruction following abilities.
  arXiv  Detail & Related papers  (2023-06-07T19:59:23Z)
• Skill over Scale: The Case for Medium, Domain-Specific Models for SE [4.2630881518611226]
  We show that modestly sized domain-specific models can outperform much larger ones on code labeling tasks.<n>We train two models: SOBertBase (125M parameters) and SOBertLarge (762M parameters) at a budget of just $374 and $1600 each.<n>Results demonstrate that pre-training both extensively and properly on in-domain data can yield a powerful and affordable alternative to leveraging closed-source general-purpose models.
  arXiv  Detail & Related papers  (2023-06-05T21:38:30Z)
• CCT5: A Code-Change-Oriented Pre-Trained Model [14.225942520238936]
  We propose to pre-train a model specially designed for code changes to better support developers in software maintenance. We first collect a large-scale dataset containing 1.5M+ pairwise data of code changes and commit messages. We fine-tune the pre-trained model, CCT5, on three widely-labelled tasks incurred by code changes and two tasks specific to the code review process.
  arXiv  Detail & Related papers  (2023-05-18T07:55:37Z)
• Scaling Instruction-Finetuned Language Models [126.4789306516927]
  Finetuning language models on a collection of datasets phrased as instructions has been shown to improve model performance. We find that instruction finetuning dramatically improves performance on a variety of model classes.
  arXiv  Detail & Related papers  (2022-10-20T16:58:32Z)
• Unifying Language Learning Paradigms [96.35981503087567]
  We present a unified framework for pre-training models that are universally effective across datasets and setups. We show how different pre-training objectives can be cast as one another and how interpolating between different objectives can be effective. Our model also achieve strong results at in-context learning, outperforming 175B GPT-3 on zero-shot SuperGLUE and tripling the performance of T5-XXL on one-shot summarization.
  arXiv  Detail & Related papers  (2022-05-10T19:32:20Z)
• DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models [152.29364079385635]
  As pre-trained models grow bigger, the fine-tuning process can be time-consuming and computationally expensive. We propose a framework for resource- and parameter-efficient fine-tuning by leveraging the sparsity prior in both weight updates and the final model weights. Our proposed framework, dubbed Dually Sparsity-Embedded Efficient Tuning (DSEE), aims to achieve two key objectives: (i) parameter efficient fine-tuning and (ii) resource-efficient inference.
  arXiv  Detail & Related papers  (2021-10-30T03:29:47Z)

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.