collaborators

7 papers

cs.DB2026

Towards Trustworthy and Cost-Efficient Data Integration: From Naïve RAG to Agentic RAG

Chuangtao Ma, Arijit Khan

Large language models (LLMs) and AI agents have demonstrated strong potential for data integration in zero-shot and few-shot settings. However, they continue to face significant ac…

cs.DB2026

LLM+Graph@VLDB'2025 Workshop Summary

Yixiang Fang, Arijit Khan, Tianxing Wu +2

The integration of large language models (LLMs) with graph-structured data has become a pivotal and fast evolving research frontier, drawing strong interest from both academia and…

cs.DB2026

Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based Exploration

Chuangtao Ma, Zeyu Zhang, Arijit Khan +2

Retrieval-augmented generation (RAG) enhances LLM reasoning in knowledge-intensive tasks, but existing RAG pipelines incur substantial retrieval and generation overhead when applie…

cs.DB2025

SQL-to-Text Generation with Weighted-AST Few-Shot Prompting

Sriom Chakrabarti, Chuangtao Ma, Arijit Khan +1

SQL-to-Text generation aims at translating structured SQL queries into natural language descriptions, thereby facilitating comprehension of complex database operations for non-tech…

cs.CL2025

Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunities

Chuangtao Ma, Yongrui Chen, Tianxing Wu +2

Large language models (LLMs) have demonstrated remarkable performance on question-answering (QA) tasks because of their superior capabilities in natural language understanding and…

cs.DB2025

LLM+KG@VLDB'24 Workshop Summary

Arijit Khan, Tianxing Wu, Xi Chen

The unification of large language models (LLMs) and knowledge graphs (KGs) has emerged as a hot topic. At the LLM+KG'24 workshop, held in conjunction with VLDB 2024 in Guangzhou, C…