Multi-task Code LLMs: Data Mix or Model Merge?
Open Access
- 12 April 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 29-36
Abstract
No abstract availableAll Related Versions
Funding Information
- National Artificial Intelligence Research Resource (NAIRR250429)
This publication has 13 references indexed in Scilit:
- Large Language Model for Vulnerability Detection and Repair: Literature Review and the Road AheadACM Transactions on Software Engineering and Methodology, 2025
- Evolutionary optimization of model merging recipesNature Machine Intelligence, 2025
- Code-Switching Curriculum Learning for Multilingual Transfer in LLMs2025
- Using AI-based coding assistants in practice: State of affairs, perceptions, and ways forwardInformation and Software Technology, 2024
- MFTCoder: Boosting Code LLMs with Multitask Fine-Tuning2024
- Learning-based Widget Matching for Migrating GUI Test Cases2024
- CMR Scaling Law: Predicting Critical Mixture Ratios for Continual Pre-training of Language Models2024
- MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmetic2024
- LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models2024
- Pearson Correlation Coefficient2009