paper-with-me

Papers

Enhancing LLM Code Generation Capabilities through Test-Driven Development and Code Interpreter

2025-11-16 · Sajed Jalil, Shuvo Saha, Hossain Mohammad Seym arxiv

Over the past few years, improving LLM code generation capabilities has been a key focus in NLP research. Despite Bengali having 242 million native speakers worldwide, it receives little attention when it comes to training LLMs. More recently, various fine-tuning and augmented generation techniques have been employed to significantly enhance code generation performance. However, they require considerable expertise and resources to utilize effectively as an end user. The goal of our work is to democratize access to powerful code generation tools in resource-constrained emerging markets, enabling users to leverage them in their native language. We introduce a novel approach that combines Test-Driven Development (TDD) and Code Interpreter (CI), utilizing open-weight models, which improves the baseline accuracy for code generation with Bengali prompts and achieves an overall accuracy of 85%. Our approach requires no finetuning and proves that even the smallest models in the same family can attain up to 98% accuracy compared to the largest models. All of our results are publicly shared in GitHub for validation and reproducibility.

📄 PDF Abstract BibTeX arXiv:2511.12823

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Similar Papers 제목 키워드 기반

UniTSyn: A Large-Scale Dataset Capable of Enhancing the Prowess of Large Language Models for Program Testing

2024-02-04 · Yifeng He, Jiabo Huang, Yuyang Rong, Yiwen Guo 외

The remarkable capability of large language models (LLMs) in generating high-quality code has drawn increasing attention in the software testing community. However, existing code LLMs often demonstrate unsatisfactory cap…

software testing

CodeIF: Benchmarking the Instruction-Following Capabilities of Large Language Models for Code Generation

2025-02-26 · Kaiwen Yan, Hongcheng Guo, Xuanqing Shi, Jingyi Xu 외

With the rapid advancement of Large Language Models (LLMs), the demand for robust instruction-following capabilities in code generation tasks has grown significantly. Code generation not only facilitates faster prototypi…

BenchmarkingCode GenerationInstruction Following

Predict the Retrieval! Test time adaptation for Retrieval Augmented Generation

2026-01-16 · Xin Sun, Zhongqi Chen, Qiang Liu, Shu Wu 외 arxiv

Retrieval-Augmented Generation (RAG) has emerged as a powerful approach for enhancing large language models' question-answering capabilities through the integration of external knowledge. However, when adapting RAG syste…

Test-time Adaptation

Alignment with Fill-In-the-Middle for Enhancing Code Generation

2025-08-27 · Houxing Ren, Zimu Lu, Weikang Shi, Haotian Hou 외 arxiv

The code generation capabilities of Large Language Models (LLMs) have advanced applications like tool invocation and problem-solving. However, improving performance in code-related tasks remains challenging due to limite…

Code Generation

Revisit Self-Debugging with Self-Generated Tests for Code Generation

2025-01-22 · Xiancai Chen, Zhengwei Tao, Kechi Zhang, Changzhi Zhou 외

Large language models (LLMs) have shown significant advancements in code generation, but still face challenges on tasks beyond their basic capabilities. Recently, the notion of self-debugging has been proposed to boost t…

Code Generation