软件生成数据中的偏差与误差缓解:一种利用生成式代码模型的先进搜索与优化框架
Bias and Error Mitigation in Software-Generated Data: An Advanced Search and Optimization Framework Leveraging Generative Code Models
AI总结:
本文提出一种基于 Solomonoff Induction 和 Kolmogorov Conditional Complexity 的先进搜索与优化框架,利用 LLMs 生成并选择最优代码,以迭代缓解软件生成数据中的偏差与误差。
摘要:
数据生成与分析是许多行业和学科的基础,从商业战略决策到物理与社会科学研究。然而,使用软件和算法生成的数据可能存在偏差和错误。这些问题可能源于原始软件的问题、不符合具体情况特定需求的默认设置,甚至是基础理论和模型存在的更深层问题。本文提出了一种先进的搜索与优化框架,旨在生成并选择最优源代码,以纠正先前版本中的错误和偏差,从而解决专门从事数据分析和生成的软件系统中的典型问题,尤其是企业和数据科学领域的系统。在同一软件系统上多次应用此框架将逐步提高输出结果的质量。它以 Solomonoff Induction 作为可靠的理论基础,并用 Kolmogorov Conditional Complexity(一种新颖的改进)对其进行扩展,以评估一组候选程序。我们提议使用生成式模型来创建这组程序,特别强调 Large Language Models (LLMs) 生成高质量代码的能力。
英文摘要:
Data generation and analysis is a fundamental aspect of many industries and disciplines, from strategic decision making in business to research in the physical and social sciences. However, data generated using software and algorithms can be subject to biases and errors. These can be due to problems with the original software, default settings that do not align with the specific needs of the situation, or even deeper problems with the underlying theories and models. This paper proposes an advanced search and optimization framework aimed at generating and choosing optimal source code capable of correcting errors and biases from previous versions to address typical problems in software systems specializing in data analysis and generation, especially those in the corporate and data science world. Applying this framework multiple times on the same software system would incrementally improve the quality of the output results. It uses Solomonoff Induction as a sound theoretical basis, extending it with Kolmogorov Conditional Complexity, a novel adaptation, to evaluate a set of candidate programs. We propose the use of generative models for the creation of this set of programs, with special emphasis on the capabilities of Large Language Models (LLMs) to generate high quality code.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。