Understanding the Effect of Algorithm Transparency of Model Explanations in Text-to-SQL Semantic Parsing
Not on the map. Why?
Abstract (arXiv)
Explaining the decisions of AI has become vital for fostering appropriate user trust in these systems. This paper investigates explanations for a structured prediction task called ``text-to-SQL Semantic Parsing'', which translates a natural language question into a structured query language (SQL) program. In this task setting, we designed three levels of model explanation, each exposing a different amount of the model's decision-making details (called ``algorithm transparency''), and investigated how different model explanations could potentially yield different impacts on the user experience. Our study with ~100 participants shows that (1) the low-/high-transparency explanations often lead to less/more user reliance on the model decisions, whereas the medium-transparency explanations strike a good balance. We also show that (2) only the medium-transparency participant group was able to engage further in the interaction and exhibit increasing performance over time, and that (3) they showed the least changes in trust before and after the study.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 32 of its 54 references that are in the map. First posted on arXiv 5 Oct 2024.
Builds on
32 of 54 references.
References · 32
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2017Axiomatic Attribution for Deep Networkscited by 3,350
- 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
- 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
- 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
- 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
- 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
- 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
- 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 439
- 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 402
20 more
- 2020Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performancecited by 396
- 2020Calibration of Pre-trained Transformerscited by 307
- 2020Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Makingcited by 281
- 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 191
- 2020Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?cited by 189
- 2018On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detectioncited by 159
- 2020Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsingcited by 133
- 2019Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questionscited by 80
- 2018How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanationcited by 71
- 2021Natural SQL: Making SQL Easier to Infer from Natural Language Specificationscited by 66
- 2020Speak to your Parser: Interactive Text-to-SQL with Natural Language Feedbackcited by 44
- 2019Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Studycited by 40
- 2018Confidence Modeling for Neural Semantic Parsingcited by 33
- 2022Calibrated Interpretation: Confidence Estimation in Semantic Parsingcited by 33
- 2020Photon: A Robust Cross-Domain Text-to-SQL Systemcited by 26
- 2023Improving Generalization in Language Model-Based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-Based Techniquescited by 23
- 2023Interactive Text-to-SQL Generation via Editable Step-by-Step Explanationscited by 19
- 2023Are Human Explanations Always Helpful? Towards Objective Evaluation of Human Natural Language Explanationscited by 13
- 2021Local Explanation of Dialogue Response Generationcited by 7
- 2023Explaining Large Language Model-Based Neural Semantic Parsers (Student Abstract)cited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.