Saad Ezzini
2 papers · Latest:
Artificial Intelligence
LeGo-Code: Can Modular Curriculum Learning Advance Complex Code Generation? Insights from Text-to-SQL
LeGo-Code uses a Modular Adapter Composition strategy to improve LLM performance on complex Text-to-SQL tasks by sequentially training complexity-specific adapters.
2604.18254
Natural Language ProcessingEmpirical Evaluation of PDF Parsing and Chunking for Financial Question Answering with RAG
This paper empirically evaluates PDF parsing and chunking strategies for RAG-based financial question answering, offering practical guidelines.
2604.12047
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.