In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) has been redirecting to new domain since Jan. 1st, 2025.
See More
App. Res. of Comp. Accepted Paper
Vol. 42, 2025 No. 10

Coordination of fine-tuned code generation models and large language models via uncertainty estimation

Hong Shaodong1a,1b
Shen Guowei1a,1b
Luo Sufen2
Liu Tao2
1. a. National Key Laboratory of Public Big Data, b. Ministry of Education Engineering Research Center of Text Computing & Cognitive Intelligence, Guizhou University, Guiyang 550025, China
2. Guizhou Provincial Judicial Police Academy, Guiyang 550025, China
DOI: 10.19734/j.issn.1001-3695.2025.04.0082

Abstract

The complementary mechanism between fine-tuned code generation models and large language model (LLM) remains underexplored, leading to ambiguous decision boundaries in their collaboration. A method named Coral was proposed to coordinate fine-tuned models and LLMs based on uncertainty estimation. This method analyzed the complementarity between the two models and quantified their decision boundaries. Coral adopted the concept of expected calibration error to compare uncertainty estimation methods and selected a stable method for the fine-tuned model. This enabled the fine-tuned model to output uncertainty scores reflecting prediction confidence. Coral calculated an uncertainty threshold by maximizing BLEU scores on a validation dataset, which quantified the decision boundary between the models. Based on the threshold and the uncertainty scores, the method identified in-distribution (ID) and out-of-distribution (OOD) data. The LLM handled OOD data to improve the generalization of the fine-tuned model. Evaluation on two benchmark datasets showed that Coral outperformed the use of either model alone in both BLEU and Exact Match metrics. The results indicate that Coral effectively coordinates the fine-tuned model and LLM.

Foundation Support

国家自然科学基金[62062022]
贵州省省级科技计划[黔科合基础-ZK[2023]重点011]
基于大数据的行政执法智能监督模型研究与应用[黔科合支撑[2023]一般447]

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.04.0082
Publish at: Application Research of Computers Accepted Paper, Vol. 42, 2025 No. 10

Publish History

[2025-06-04] Accepted Paper

Cite This Article

洪少东, 申国伟, 罗素芬, 等. 基于不确定性估计的微调代码生成模型与大语言模型的协同方法 [J]. 计算机应用研究, 2025, 42 (10). (2025-06-04). https://doi.org/10.19734/j.issn.1001-3695.2025.04.0082. (Hong Shaodong, Shen Guowei, Luo Sufen, et al. Coordination of fine-tuned code generation models and large language models via uncertainty estimation [J]. Application Research of Computers, 2025, 42 (10). (2025-06-04). https://doi.org/10.19734/j.issn.1001-3695.2025.04.0082. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)