Work

CodeRise: Bootstrapping LLMs for Ultra Low-Resource Programming Languages via Progressive Self-Refinement Curriculum

Year: 2026

Type: conference-paper

Abstract: Large Language Models (LLMs) struggle with code generation for Ultra Low-Resource Programming Languages (ULRPLs) due to the scarcity of training data.Existing synthetic data generation methods fail in this context, suffering from a severe cold-start problem and resulting in samples that lack diversity.To overcome these challenges, we propose CodeRise, a novel two-stage framework that autonomously generates a high-quality, diverse, and progressively complex curriculum for ULRPLs.The framework first tackles the cold-start and distribution issues by leveraging the full formal syntax of the target language as structural guidance and applying a biased sampling strategy over library modules.Building on this foundation, we fine-tune the model to generate increasingly complex code without explicit syntax input, using an adaptive curriculum and multi-turn self-debugging to progressively improve code quality.We evaluate on two ULRPLs, Tengo and Janet, using migrated HumanEval-Tengo and MBPP-Tengo, as well as our new benchmarks, TengoEval and JanetEval.Experiments show that CodeRise significantly outperforms both training-free and training-based baselines in ultra low-resource environments. Module Frequency Proportion(%)

Source: Findings of the Association for Computational Linguistics: ACL (Findings of ACL)

DOI: 10.18653/v1/2026.findings-acl.1840

Authors: Tengfei Wen, Xuanang Chen, Ben He, Xiaoliang Cong, Le Sun

Institutions: Chinese Academy of Sciences, Institute of Software, University of Chinese Academy of Sciences, ByteDance (China)

Language: English

Topic: Software Engineering Research

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

SDG: Quality education

Open Access status: hybrid

Funder: National Natural Science Foundation of China