←Back to feed
🧠 AI🟢 Bullish
LIA: Supervised Fine-Tuning of Large Language Models for Automatic Issue Assignment
arXiv – CS AI|Arsham Khosravani, Alireza Hoseinpour, Arshia Akhavan, Mehdi Keshani, Abbas Heydarnoori||6 views
🤖AI Summary
Researchers developed LIA, a supervised fine-tuning approach using DeepSeek-R1-Distill-Llama-8B to automatically assign software issues to developers. The system achieved up to 187.8% improvement over the base model and 211.2% better performance than existing methods in developer recommendation accuracy.
Key Takeaways
- →LIA uses supervised fine-tuning of LLMs to automatically assign software issues to appropriate developers based on issue descriptions.
- →The system achieved 187.8% improvement in Hit@1 accuracy compared to the base DeepSeek-R1-Distill-Llama-8B model.
- →LIA outperformed four leading issue assignment methods by up to 211.2% in Hit@1 score.
- →The approach addresses limitations of existing methods that require large volumes of project-specific training data.
- →Results demonstrate the effectiveness of domain-adapted LLMs for software maintenance automation tasks.
#llm#software-maintenance#fine-tuning#deepseek#automation#developer-tools#machine-learning#open-source
Read Original →via arXiv – CS AI
Act on this with AI
Stay ahead of the market.
Connect your wallet to an AI agent. It reads balances, proposes swaps and bridges across 15 chains — you keep full control of your keys.
Related Articles