# Uncovering and Categorizing Social Biases in Text-to-SQL

arXiv: https://arxiv.org/abs/2305.16253 · HTML: https://mlsanity.com/paper/2305.16253/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 39 references that are in the map.
- First posted on arXiv 25 May 2023.

## Builds on (most cited first, 29 of 29)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [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)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers](https://mlsanity.com/paper/1911.04942/) (2019)
- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models](https://mlsanity.com/paper/2109.05093/) (2021)
- [Context Autoencoder for Self-Supervised Representation Learning](https://mlsanity.com/paper/2202.03026/) (2022)
- [Synchromesh: Reliable code generation from pre-trained language models](https://mlsanity.com/paper/2201.11227/) (2022)
- [Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment](https://mlsanity.com/paper/2207.13085/) (2022)
- [Awakening Latent Grounding from Pretrained Language Models for Semantic Parsing](https://mlsanity.com/paper/2109.10540/) (2021)
- [Group DETR v2: Strong Object Detector with Encoder-Decoder Pretraining](https://mlsanity.com/paper/2211.03594/) (2022)
- [CAE v2: Context Autoencoder with CLIP Target](https://mlsanity.com/paper/2211.09799/) (2022)
- [Uncovering and Quantifying Social Biases in Code Generation](https://mlsanity.com/paper/2305.15377/) (2023)
- [Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspective](https://mlsanity.com/paper/2112.12925/) (2021)
- [Conditional DETR V2: Efficient Detection Transformer with Box Queries](https://mlsanity.com/paper/2207.08914/) (2022)
- [UniSAr: A Unified Structure-Aware Autoregressive Language Model for Text-to-SQL](https://mlsanity.com/paper/2203.07781/) (2022)
- [Point Scene Understanding via Disentangled Instance Mesh Reconstruction](https://mlsanity.com/paper/2203.16832/) (2022)
- [D3ETR: Decoder Distillation for Detection Transformer](https://mlsanity.com/paper/2211.09768/) (2022)
- [Adversarial Scrubbing of Demographic Information for Text Classification](https://mlsanity.com/paper/2109.08613/) (2021)
- [HERB: Measuring Hierarchical Regional Bias in Pre-trained Language Models](https://mlsanity.com/paper/2211.02882/) (2022)
- [Enhance Long Text Understanding via Distilled Gist Detector from Abstractive Summarization](https://mlsanity.com/paper/2110.04741/) (2021)
- [Know What I don't Know: Handling Ambiguous and Unanswerable Questions for Text-to-SQL](https://mlsanity.com/paper/2212.08902/) (2022)
- [Parallel Sentence-Level Explanation Generation for Real-World Low-Resource Scenarios](https://mlsanity.com/paper/2302.10707/) (2023)

## Built on by (most cited first, 5 of 5)

- [Trustworthiness in Retrieval-Augmented Generation Systems: A Survey](https://mlsanity.com/paper/2409.10102/) (2024)
- [The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models](https://mlsanity.com/paper/2406.10130/) (2024)
- [SAFENLIDB: A Privacy-Preserving Safety Alignment Framework for LLM-based Natural Language Database Interfaces](https://mlsanity.com/paper/2511.06778/) (2025)
- [A Communication Theory Perspective on Prompting Engineering Methods for Large Language Models](https://mlsanity.com/paper/2310.18358/) (2023)
- [Improving Long Text Understanding with Knowledge Distilled from Summarization Model](https://mlsanity.com/paper/2405.04955/) (2024)

## Abstract (arXiv)

Content Warning: This work contains examples that potentially implicate stereotypes, associations, and other harms that could be offensive to individuals in certain social groups.} Large pre-trained language models are acknowledged to carry social biases towards different demographics, which can further amplify existing stereotypes in our society and cause even more harm. Text-to-SQL is an important task, models of which are mainly adopted by administrative industries, where unfair decisions may lead to catastrophic consequences. However, existing Text-to-SQL models are trained on clean, neutral datasets, such as Spider and WikiSQL. This, to some extent, cover up social bias in models under ideal conditions, which nevertheless may emerge in real application scenarios. In this work, we aim to uncover and categorize social biases in Text-to-SQL models. We summarize the categories of social biases that may occur in structured data for Text-to-SQL models. We build test benchmarks and reveal that models with similar task accuracy can contain social biases at very different rates. We show how to take advantage of our methodology to uncover and assess social biases in the downstream Text-to-SQL task. We will release our code and data.