mlsanityData to 7 Oct 2026

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

arXiv 2502.18448 ↗First posted 25 Feb 2025cs.CL cs.AIcited by 12

Not on the map. Why?

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.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 33 of its 44 references that are in the map. First posted on arXiv 25 Feb 2025.

Builds on

33 of 44 references.

References · 33

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2024Qwen2.5 Technical Reportcited by 4,713
  4. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,928
  5. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  6. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 385
  7. 2022Generating Sequences by Learning to Self-Correctcited by 271
  8. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 230
  9. 2020Structure-Grounded Pretraining for Text-to-SQLcited by 126
  10. 2023We're Afraid Language Models Aren't Modeling Ambiguitycited by 124
  11. 2021Towards Robustness of Text-to-SQL Models against Synonym Substitutioncited by 110
  12. 2023NEFTune: Noisy Embeddings Improve Instruction Finetuningcited by 99
21 more
  1. 2024Aligner: Efficient Alignment by Learning to Correctcited by 96
  2. 2024Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questionscited by 70
  3. 2023Selectively Answering Ambiguous Questionscited by 63
  4. 2024Aligning Language Models to Explicitly Handle Ambiguitycited by 55
  5. 2023ClarifyGPT: Empowering LLM-based Code Generation with Intention Clarificationcited by 37
  6. 2024E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQLcited by 35
  7. 2023Evaluating Cross-Domain Text-to-SQL Models and Benchmarkscited by 32
  8. 2024AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queriescited by 32
  9. 2023Benchmarking and Improving Text-to-SQL Generation under Ambiguitycited by 31
  10. 2024Learning to Refine with Fine-Grained Natural Language Feedbackcited by 27
  11. 2023Asking Clarification Questions to Handle Ambiguity in Open-Domain QAcited by 24
  12. 2024PRACTIQ: A Practical Conversational Text-to-SQL dataset with Ambiguous and Unanswerable Queriescited by 17
  13. 2022Python Code Generation by Asking Clarification Questionscited by 16
  14. 2023Zero and Few-shot Semantic Parsing with Ambiguous Inputscited by 16
  15. 2021Weakly Supervised Text-to-SQL Parsing through Question Decompositioncited by 15
  16. 2023Answering Ambiguous Questions via Iterative Promptingcited by 13
  17. 2023Semantic Decomposition of Question and SQL for Text-to-SQL Parsingcited by 13
  18. 2021SPARQLing Database Queries from Intermediate Question Decompositionscited by 7
  19. 2024Learning from Natural Language Explanations for Generalizable Entity Matchingcited by 6
  20. 2024Improving Generalization in Semantic Parsing by Increasing Natural Language Variationcited by 4
  21. 2024KeyInst: Keyword Instruction for Improving SQL Formulation in Text-to-SQLcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 7.

12 papers.

  1. 2025AmbiSQL: Interactive Ambiguity Detection and Resolution for Text-to-SQLcited by 10
  2. 2025Asking a Language Model for Diverse Responsescited by 9
  3. 2026LLMs Exhibit Significantly Lower Uncertainty in Creative Writing Than Professional Writerscited by 4
  4. 2025Are We Asking the Right Questions? On Ambiguity in Natural Language Queries for Tabular Data Analysiscited by 3
  5. 2026Disentangling Ambiguity from Instability in Large Language Models: A Clinical Text-to-SQL Case Studycited by 2
  6. 2025NRR-Core: Non-Resolution Reasoning as a Computational Framework for Contextual Identity and Ambiguity Preservationcited by 1
  7. 2026Beyond Text-to-SQL: An Agentic LLM System for Governed Enterprise Analytics APIscited by 1
  8. 2025Ambiguity in LLMs is a concept missing problemcited by 0
  9. 2026NRR-Phi: A Typed External Text-to-State Interface and Update Contract for Inspectable Ambiguity-State Maintenancecited by 0
  10. 2026PleaSQLarify: Visual Pragmatic Repair for Natural Language Database Queryingcited by 0
  11. 2026Localizing Prompt Ambiguity in Large Language Models with Probe-Targeted Attributioncited by 0
  12. 2026Prospective Interpretation Risk: Principled Communication Control Between LLMscited by 0