TraceSQL: Traceable Answerability Estimation for Reference-Free Text-to-SQL Verification
Text-to-SQL systems are commonly evaluated using ground-truth SQL queries or reference execution results, but such supervision is unavailable at inference time in real-world deployments. This creates a critical verification problem: given only a user question, database context, and generated SQL, can a system estimate whether the generated query is likely to correctly answer the question? Recent approaches use LLMs as judge or specialized agents to inspect generated SQL, but their decisions can be difficult to trace. Outcome Reward Models (ORMs) address this by learning from execution-labeled
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 51%Show HN: Sqlsure – deterministic semantic checks for AI-generated SQL →
- LinkedLinked via arxiv author · 85%Neelesh Kumar Shukla →
“TraceSQL: Traceable Answerability Estimation for Reference-Free Text-to-SQL Verification”
- LinkedLinked via arxiv author · 85%Debasmita Panda →
“TraceSQL: Traceable Answerability Estimation for Reference-Free Text-to-SQL Verification”
- LinkedLinked via arxiv author · 85%Srutanik Bhaduri →
“TraceSQL: Traceable Answerability Estimation for Reference-Free Text-to-SQL Verification”
- LinkedLinked via arxiv author · 85%Aditya Banerjee →
“TraceSQL: Traceable Answerability Estimation for Reference-Free Text-to-SQL Verification”
- LinkedLinked via arxiv author · 85%Viji Krishnamurthy →
“TraceSQL: Traceable Answerability Estimation for Reference-Free Text-to-SQL Verification”
- FuzzyOverlapping authors or contributors · 62%open-webui/open-webui →
“Shared author/contributor keys: panda”
- FuzzyOverlapping authors or contributors · 62%f/prompts.chat →
“Shared author/contributor keys: panda”