Published on September 19, 2025
–
Updated on September 19, 2025
Dates
on the September 5, 2025
Location
London, United Kingdom
In early September, Paolo Papotti gave two keynotes in London: One at TaDA 2025, and the other at DaSH Workshop @ VLDB 2025.
▸ “Reinforcement Learning to enable Reasoning LLMs for Text2SQL” at TaDA 2025
Abstract: The ability to interact with complex databases using natural language (NL) is a key step in democratizing data access, a long-standing goal in the enterprise world. While Large Language Models (LLMs) have shown remarkable promise in translating NL questions into SQL queries (Text2QL), their performance stall when faced with the complexities of real-world enterprise databases. This talk will report a promising solution to enhance the reasoning capabilities of LLMs for this task. Our "Think2SQL" methodology investigates various strategies for improving LLM performance, including Zero-Shot Learning (ZSL), Supervised Fine-Tuning (SFT), and Reinforcement Learning (RL). RL, using rewards crafted around SQL execution accuracy, significantly boosts the performance of small LLMs, achieving results comparable to those of much larger models on complex datasets. Finally, we will highlight the path forward for Text2SQL systems capable of navigating the nuances of human language, such as ambiguity, in a real-world enterprise context.
▸ "SQL and Large Language Models: A Marriage Made in Heaven?" at DaSH Workshop @ VLDB 2025
Abstract: With the rise of pre-trained Large Language Models (LLMs), there is now an effective solution to store and use information extracted from massive corpora of documents. However, for data-intensive tasks over structured data, relational DBs and SQL queries are at the core of countless applications. While these two technologies may appear distant, in this talk we will see that they can interact effectively and with promising results. LLMs can help users express SQL queries (Semantic Parsing), but SQL queries can be used to evaluate LLMs (Benchmarking). Their combination can be further advanced, with opportunities to query with a unified SQL interface both LLMs and DBs. We present recent results on these topics and then conclude with an overview of the research challenges in effectively leveraging the combined power of SQL and LLMs.
Paolo Papotti has been a 3IA Chairholder since September 2024. He also is an associate professor in the Data Science department at EURECOM.
Learn more about TaDA 2025
Learn more about DaSH Workshop @ VLDB 2025
Abstract: The ability to interact with complex databases using natural language (NL) is a key step in democratizing data access, a long-standing goal in the enterprise world. While Large Language Models (LLMs) have shown remarkable promise in translating NL questions into SQL queries (Text2QL), their performance stall when faced with the complexities of real-world enterprise databases. This talk will report a promising solution to enhance the reasoning capabilities of LLMs for this task. Our "Think2SQL" methodology investigates various strategies for improving LLM performance, including Zero-Shot Learning (ZSL), Supervised Fine-Tuning (SFT), and Reinforcement Learning (RL). RL, using rewards crafted around SQL execution accuracy, significantly boosts the performance of small LLMs, achieving results comparable to those of much larger models on complex datasets. Finally, we will highlight the path forward for Text2SQL systems capable of navigating the nuances of human language, such as ambiguity, in a real-world enterprise context.
▸ "SQL and Large Language Models: A Marriage Made in Heaven?" at DaSH Workshop @ VLDB 2025
Abstract: With the rise of pre-trained Large Language Models (LLMs), there is now an effective solution to store and use information extracted from massive corpora of documents. However, for data-intensive tasks over structured data, relational DBs and SQL queries are at the core of countless applications. While these two technologies may appear distant, in this talk we will see that they can interact effectively and with promising results. LLMs can help users express SQL queries (Semantic Parsing), but SQL queries can be used to evaluate LLMs (Benchmarking). Their combination can be further advanced, with opportunities to query with a unified SQL interface both LLMs and DBs. We present recent results on these topics and then conclude with an overview of the research challenges in effectively leveraging the combined power of SQL and LLMs.
Paolo Papotti has been a 3IA Chairholder since September 2024. He also is an associate professor in the Data Science department at EURECOM.
Learn more about TaDA 2025
Learn more about DaSH Workshop @ VLDB 2025
