7 papers
Test-Time Verification for Text-to-SQL via Outcome Reward Models
Mattia Tritto, Giuseppe Farano, Dario Di Palma +4
Improving the reliability of large language models (LLMs) at inference time is a central challenge in structured reasoning tasks such as Text-to-SQL. Common test-time inference str…
Discovery Agents for Real-Time Analytics: Toward Proactive Insight Systems
Gaetano Rossiello, Dharmashankar Subramanian
Modern analytics systems are fundamentally reactive, requiring users to define queries over increasingly complex and continuously evolving data. In real-time streaming environments…
Process Supervision for Chain-of-Thought Reasoning via Monte Carlo Net Information Gain
Corentin Royer, Debarun Bhattacharjya, Gaetano Rossiello +2
Multi-step reasoning improves the capabilities of large language models (LLMs) but increases the risk of errors propagating through intermediate steps. Process reward models (PRMs)…
ConstrainedSQL: Training LLMs for Text2SQL via Constrained Reinforcement Learning
Weiqin Chen, Nhan Huu Pham, Michael Robert Glass +4
Reinforcement learning (RL) has demonstrated significant promise in enhancing the reasoning capabilities of Text2SQL LLMs, especially with advanced algorithms such as GRPO and DAPO…
GradeSQL: Test-Time Inference with Outcome Reward Models for Text-to-SQL Generation from Large Language Models
Mattia Tritto, Giuseppe Farano, Dario Di Palma +4
Text-to-SQL, the task of translating natural language questions into SQL queries, has significantly advanced with the introduction of Large Language Models (LLMs), broadening datab…
Rationalization Models for Text-to-SQL
Gaetano Rossiello, Nhan Pham, Michael Glass +2
We introduce a framework for generating Chain-of-Thought (CoT) rationales to enhance text-to-SQL model fine-tuning. These rationales consist of intermediate SQL statements and expl…