mlsanityData to 7 Oct 2026

Learning to Simulate Natural Language Feedback for Interactive Semantic Parsing

arXiv 2305.08195 ↗First posted 14 May 2023cs.CLcited by 19

Not on the map. Why?

Abstract (arXiv)

Interactive semantic parsing based on natural language (NL) feedback, where users provide feedback to correct the parser mistakes, has emerged as a more practical scenario than the traditional one-shot semantic parsing. However, prior work has heavily relied on human-annotated feedback data to train the interactive semantic parser, which is prohibitively expensive and not scalable. In this work, we propose a new task of simulating NL feedback for interactive semantic parsing. We accompany the task with a novel feedback evaluator. The evaluator is specifically designed to assess the quality of the simulated feedback, based on which we decide the best feedback simulator from our proposed variants. On a text-to-SQL dataset, we show that our feedback simulator can generate high-quality NL feedback to boost the error correction ability of a specific parser. In low-data settings, our feedback simulator can help achieve comparable error correction performance as trained using the costly, full set of human annotations.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 45 of its 69 references that are in the map. First posted on arXiv 14 May 2023.

Builds on

45 of 69 references.

References · 45

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  5. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  6. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  7. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
  8. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  9. 2020COMET: A Neural Framework for MT Evaluationcited by 1,024
  10. 2023Teaching Large Language Models to Self-Debugcited by 963
  11. 2021BARTScore: Evaluating Generated Text as Text Generationcited by 719
  12. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
33 more
  1. 2023Language Models can Solve Computer Taskscited by 371
  2. 2020Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Basescited by 169
  3. 2016Language to Logical Form with Neural Attentioncited by 158
  4. 2020Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsingcited by 133
  5. 2020Task-Oriented Dialogue as Dataflow Synthesiscited by 122
  6. 2019Learning from Dialogue after Deployment: Feed Yourself, Chatbot!cited by 102
  7. 2018Semantic Parsing for Task Oriented Dialog using Hierarchical Representationscited by 101
  8. 2017Learning a Neural Semantic Parser from User Feedbackcited by 98
  9. 2019Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questionscited by 80
  10. 2018BLEU is Not Suitable for the Evaluation of Text Simplificationcited by 78
  11. 2021Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generationcited by 60
  12. 2016A User Simulator for Task-Completion Dialoguescited by 56
  13. 2021A Plug-and-Play Method for Controlled Text Generationcited by 55
  14. 2019How to Build User Simulators to Train RL-based Dialog Systemscited by 44
  15. 2020Speak to your Parser: Interactive Text-to-SQL with Natural Language Feedbackcited by 44
  16. 2016Learning Language Games through Interactioncited by 43
  17. 2020Towards Ecologically Valid Research on Language User Interfacescited by 42
  18. 2019Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Studycited by 40
  19. 2020Conversational Semantic Parsing for Dialog State Trackingcited by 40
  20. 2021NL-EDIT: Correcting semantic parse errors through natural language interactioncited by 33
  21. 2020Photon: A Robust Cross-Domain Text-to-SQL Systemcited by 26
  22. 2020Simulated Chats for Building Dialog Systems: Learning to Generate Conversations from Instructionscited by 25
  23. 2022Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deploymentcited by 25
  24. 2020An Imitation Game for Learning Semantic Parsers from User Interactioncited by 23
  25. 2021NeuralWOZ: Learning to Collect Task-Oriented Dialogue via Model-Based Simulationcited by 16
  26. 2020"What Do You Mean by That?" A Parser-Independent Interactive Approach for Enhancing Text-to-SQLcited by 11
  27. 2021Towards Transparent Interactive Semantic Parsing via Step-by-Step Correctioncited by 9
  28. 2018Interactive Semantic Parsing for If-Then Recipes via Hierarchical Reinforcement Learningcited by 7
  29. 2019Learning to Learn Semantic Parsers from Natural Language Supervisioncited by 7
  30. 2021Improving Neural Model Performance through Natural Language Feedback on Their Explanationscited by 5
  31. 2019Encoding Database Schemas with Relation-Aware Self-Attention for Text-to-SQL Parserscited by 4
  32. 2019Self-Regulated Interactive Sequence-to-Sequence Learningcited by 2
  33. 2021Error-Aware Interactive Semantic Parsing of OpenStreetMapcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 9; 2025: 5; 2026: 1.

19 papers.

Sort:

By area:

  1. 2023MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedbackcited by 293
  2. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 236
  3. 2023Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselvescited by 123
  4. 2024VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Modelscited by 88
  5. 2024Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Modelscited by 47
  6. 2025A Survey of Large Language Model Agents for Question Answeringcited by 46
  7. 2023CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Updatecited by 42
  8. 2024AutoPSV: Automated Process-Supervised Verifiercited by 28
  9. 2024Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agentscited by 17
  10. 2024Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinementcited by 16
  11. 2024Position: Towards Bidirectional Human-AI Alignmentcited by 15
  12. 2024Naturally Occurring Feedback is Common, Extractable and Usefulcited by 14
7 more
  1. 2024FB-Bench: A Fine-Grained Multi-Task Benchmark for Evaluating LLMs' Responsiveness to Human Feedbackcited by 11
  2. 2025SGIC: A Self-Guided Iterative Calibration Framework for RAGcited by 8
  3. 2025Unraveling Misinformation Propagation in LLM Reasoningcited by 6
  4. 2025Learning from Natural Language Feedback for Personalized Question Answeringcited by 5
  5. 2024Sharing the Cost of Success: A Game for Evaluating and Learning Collaborative Multi-Agent Instruction Giving and Following Policiescited by 2
  6. 2025GBV-SQL: Guided Generation and SQL2Text Back-Translation Validation for Multi-Agent Text2SQLcited by 1
  7. 2026User Feedback Provides a Unique Signal that LLMs Can not Detectcited by 0