ACL Findings2025
Disambiguate First, Parse Later: Generating Interpretations for Ambiguity Resolution in Semantic Parsing
Irina Saparina, Mirella Lapata
Abstract
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 1 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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers1
Builds on22
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- AmbigQA: Answering Ambiguous Open-domain QuestionsSewon Min, Julian Michael, Hannaneh Hajishirzi, Luke ZettlemoyerEMNLP 2020 · 162 citations
- NEFTune: Noisy Embeddings Improve Instruction FinetuningNeel Jain, Ping-yeh Chiang, Yuxin Wen, John Kirchenbauer et al.ICLR 2024 · 120 citations
- Aligner: Efficient Alignment by Learning to CorrectJiaming Ji, Boyuan Chen, Hantao Lou, Donghai Hong et al.NeurIPS 2024 · 115 citations
- Exploring Unexplored Generalization Challenges for Cross-Database Semantic ParsingAlane Suhr, Ming-Wei Chang, Peter Shaw, Kenton LeeACL 2020 · 76 citations
Related papers
- Benchmarking and Improving Text-to-SQL Generation under AmbiguityAdithya Bhaskar, Tushar Tomar, Ashutosh Sathe, Sunita SarawagiEMNLP 2023 · 13 citations
- SQLens: An End-to-End Framework for Error Detection and Correction in Text-to-SQLYue Gong, Chuan Lei, Xiao Qin, Kapil Vaidya et al.NeurIPS 2025 · 21 citations
- CLEAR: A Parser-Independent Disambiguation Framework for NL2SQLMeng Zhang, Kexin Ma, Liyang Xu, Kedi Zhang et al.ICDE 2025 · 4 citations
- Sphinteract: Resolving Ambiguities in NL2SQL Through User InteractionFuheng Zhao, Shaleen Deep, Fotis Psallidas, Avrilia Floratou et al.VLDB 2025 · 12 citations
- Confidence Estimation for Text-to-SQL in Large Language ModelsSepideh Entezari Maleki, Mohammadreza Pourreza, Davood RafieiAAAI 2026 · 1 citation
