# ODIN: A NL2SQL Recommender to Handle Schema Ambiguity

arXiv: https://arxiv.org/abs/2505.19302 · HTML: https://mlsanity.com/paper/2505.19302/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 30 references that are in the map.
- First posted on arXiv 25 May 2025.

## Builds on (most cited first, 3 of 3)

- [CodeS: Towards Building Open-source Language Models for Text-to-SQL](https://mlsanity.com/paper/2402.16347/) (2024)
- [Benchmarking and Improving Text-to-SQL Generation under Ambiguity](https://mlsanity.com/paper/2310.13659/) (2023)
- [VISA: An Ambiguous Subtitles Dataset for Visual Scene-Aware Machine Translation](https://mlsanity.com/paper/2201.08054/) (2022)

## Built on by (most cited first, 4 of 4)

- [CLARITY: A Framework and Benchmark for Conversational Language Ambiguity and Unanswerability in Interactive NL2SQL Systems](https://mlsanity.com/paper/2604.22313/) (2026)
- [EGREFINE: An Execution-Grounded Optimization Framework for Text-to-SQL Schema Refinement](https://mlsanity.com/paper/2605.00628/) (2026)
- [SOMA-SQL: Resolving Multi-Source Ambiguity in NL-to-SQL via Synthetic Log and Execution Probing](https://mlsanity.com/paper/2606.11424/) (2026)
- [LYNX: Analytical Program Synthesis via Grounding and Closed-Loop Refinement](https://mlsanity.com/paper/2610.14777/) (2026)

## Abstract (arXiv)

NL2SQL (natural language to SQL) systems translate natural language into SQL queries, allowing users with no technical background to interact with databases and create tools like reports or visualizations. While recent advancements in large language models (LLMs) have significantly improved NL2SQL accuracy, schema ambiguity remains a major challenge in enterprise environments with complex schemas, where multiple tables and columns with semantically similar names often co-exist. To address schema ambiguity, we introduce ODIN, a NL2SQL recommendation engine. Instead of producing a single SQL query given a natural language question, ODIN generates a set of potential SQL queries by accounting for different interpretations of ambiguous schema components. ODIN dynamically adjusts the number of suggestions based on the level of ambiguity, and ODIN learns from user feedback to personalize future SQL query recommendations. Our evaluation shows that ODIN improves the likelihood of generating the correct SQL query by 1.5-2× compared to baselines.