mlsanityData to 14 Oct 2026

BanglaForge: LLM Collaboration with Self-Refinement for Bangla Code Generation

arXiv 2512.19122 ↗First posted 22 Dec 2025cs.SE cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Bangla is a low-resource language for code generation, lacking large-scale annotated datasets and tools to transform natural language specifications into executable programs. This makes Bangla-to-code generation a challenging task requiring innovative solutions. To address this, we introduce BanglaForge, a novel framework for generating code from Bangla function descriptions. BanglaForge leverages a retrieval-augmented dual-model collaboration paradigm with self-refinement, combining in-context learning, llm-based translation, systematic prompt engineering, and iterative self-refinement based on execution feedback, where a coder generates initial solutions and a reviewer enhances them for robustness. On the BLP-2025 Bangla Code Generation benchmark, BanglaForge achieves a competitive Pass@1 accuracy of 84.00%, demonstrating the effectiveness of retrieval, model collaboration, and self-refinement for low-resource Bangla code generation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 7 of its 24 references that are in the map. First posted on arXiv 22 Dec 2025.

Builds on

7 of 24 references.

References · 7

  1. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  2. 2021BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Banglacited by 125
  3. 2024mHumanEval -- A Multilingual Benchmark to Evaluate Large Language Models for Code Generationcited by 32
  4. 2023BenLLMEval: A Comprehensive Evaluation into the Potentials and Pitfalls of Large Language Models on Bengali NLPcited by 23
  5. 2021Predicting Efficiency/Effectiveness Trade-offs for Dense vs. Sparse Retrieval Strategy Selectioncited by 15
  6. 2023Vacaspati: A Diverse Corpus of Bangla Literaturecited by 10
  7. 2025TigerCoder: A Novel Suite of LLMs for Code Generation in Banglacited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025PyBangla at BLP-2025 Task 2: Enhancing Bangla-to-Python Code Generation with Iterative Self-Correction and Multilingual Agents
  2. 2023SelfEvolve: A Code Evolution Framework via Large Language Models
  3. 2024DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories
  4. 2026CangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language
  5. 2024CodeLutra: Boosting LLM Code Generation via Preference-Guided Refinement
  6. 2024Comments as Natural Logic Pivots: Improve Code Generation via Comment Perspective
  7. 2025Towards Advancing Code Generation with Large Language Models: A Research Roadmap
  8. 2025Holistic Evaluation of State-of-the-Art LLMs for Code Generation