# Disambiguate First, Parse Later: Generating Interpretations for Ambiguity Resolution in Semantic Parsing

arXiv: https://arxiv.org/abs/2502.18448 · HTML: https://mlsanity.com/paper/2502.18448/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 44 references that are in the map.
- First posted on arXiv 25 Feb 2025.

## Builds on (most cited first, 30 of 33)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [Generating Sequences by Learning to Self-Correct](https://mlsanity.com/paper/2211.00053/) (2022)
- [When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs](https://mlsanity.com/paper/2406.01297/) (2024)
- [Structure-Grounded Pretraining for Text-to-SQL](https://mlsanity.com/paper/2010.12773/) (2020)
- [We're Afraid Language Models Aren't Modeling Ambiguity](https://mlsanity.com/paper/2304.14399/) (2023)
- [Towards Robustness of Text-to-SQL Models against Synonym Substitution](https://mlsanity.com/paper/2106.01065/) (2021)
- [NEFTune: Noisy Embeddings Improve Instruction Finetuning](https://mlsanity.com/paper/2310.05914/) (2023)
- [Aligner: Efficient Alignment by Learning to Correct](https://mlsanity.com/paper/2402.02416/) (2024)
- [Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions](https://mlsanity.com/paper/2410.13788/) (2024)
- [Selectively Answering Ambiguous Questions](https://mlsanity.com/paper/2305.14613/) (2023)
- [Aligning Language Models to Explicitly Handle Ambiguity](https://mlsanity.com/paper/2404.11972/) (2024)
- [ClarifyGPT: Empowering LLM-based Code Generation with Intention Clarification](https://mlsanity.com/paper/2310.10996/) (2023)
- [AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries](https://mlsanity.com/paper/2406.19073/) (2024)
- [E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQL](https://mlsanity.com/paper/2409.16751/) (2024)
- [Benchmarking and Improving Text-to-SQL Generation under Ambiguity](https://mlsanity.com/paper/2310.13659/) (2023)
- [Evaluating Cross-Domain Text-to-SQL Models and Benchmarks](https://mlsanity.com/paper/2310.18538/) (2023)
- [Learning to Refine with Fine-Grained Natural Language Feedback](https://mlsanity.com/paper/2407.02397/) (2024)
- [Asking Clarification Questions to Handle Ambiguity in Open-Domain QA](https://mlsanity.com/paper/2305.13808/) (2023)
- [PRACTIQ: A Practical Conversational Text-to-SQL dataset with Ambiguous and Unanswerable Queries](https://mlsanity.com/paper/2410.11076/) (2024)
- [Python Code Generation by Asking Clarification Questions](https://mlsanity.com/paper/2212.09885/) (2022)
- [Zero and Few-shot Semantic Parsing with Ambiguous Inputs](https://mlsanity.com/paper/2306.00824/) (2023)
- [Weakly Supervised Text-to-SQL Parsing through Question Decomposition](https://mlsanity.com/paper/2112.06311/) (2021)
- [Semantic Decomposition of Question and SQL for Text-to-SQL Parsing](https://mlsanity.com/paper/2310.13575/) (2023)
- [Answering Ambiguous Questions via Iterative Prompting](https://mlsanity.com/paper/2307.03897/) (2023)
- [SPARQLing Database Queries from Intermediate Question Decompositions](https://mlsanity.com/paper/2109.06162/) (2021)

## Built on by (most cited first, 13 of 13)

- [AmbiSQL: Interactive Ambiguity Detection and Resolution for Text-to-SQL](https://mlsanity.com/paper/2508.15276/) (2025)
- [Asking a Language Model for Diverse Responses](https://mlsanity.com/paper/2509.17570/) (2025)
- [LLMs Exhibit Significantly Lower Uncertainty in Creative Writing Than Professional Writers](https://mlsanity.com/paper/2602.16162/) (2026)
- [Are We Asking the Right Questions? On Ambiguity in Natural Language Queries for Tabular Data Analysis](https://mlsanity.com/paper/2511.04584/) (2025)
- [Disentangling Ambiguity from Instability in Large Language Models: A Clinical Text-to-SQL Case Study](https://mlsanity.com/paper/2602.12015/) (2026)
- [NRR-Core: Non-Resolution Reasoning as a Computational Framework for Contextual Identity and Ambiguity Preservation](https://mlsanity.com/paper/2512.13478/) (2025)
- [Beyond Text-to-SQL: An Agentic LLM System for Governed Enterprise Analytics APIs](https://mlsanity.com/paper/2605.21027/) (2026)
- [Ambiguity in LLMs is a concept missing problem](https://mlsanity.com/paper/2505.11679/) (2025)
- [NRR-Phi: A Typed External Text-to-State Interface and Update Contract for Inspectable Ambiguity-State Maintenance](https://mlsanity.com/paper/2601.19933/) (2026)
- [PleaSQLarify: Visual Pragmatic Repair for Natural Language Database Querying](https://mlsanity.com/paper/2603.01795/) (2026)
- [Localizing Prompt Ambiguity in Large Language Models with Probe-Targeted Attribution](https://mlsanity.com/paper/2606.05486/) (2026)
- [Prospective Interpretation Risk: Principled Communication Control Between LLMs](https://mlsanity.com/paper/2609.33885/) (2026)
- [What Is a Clarification? Estimating Model-Dependent Input Ambiguity](https://mlsanity.com/paper/2610.20052/) (2026)

## Abstract (arXiv)

Handling ambiguity and underspecification is an important challenge in natural language interfaces, particularly for tasks like text-to-SQL semantic parsing. We propose a modular approach that resolves ambiguity using natural language interpretations before mapping these to logical forms (e.g., SQL queries). Although LLMs excel at parsing unambiguous utterances, they show strong biases for ambiguous ones, typically predicting only preferred interpretations. We constructively exploit this bias to generate an initial set of preferred disambiguations and then apply a specialized infilling model to identify and generate missing interpretations. To train the infilling model, we introduce an annotation method that uses SQL execution to validate different meanings. Our approach improves interpretation coverage and generalizes across datasets with different annotation styles, database structures, and ambiguity types.