Uncovering and Categorizing Social Biases in Text-to-SQL
- URL: http://arxiv.org/abs/2305.16253v2
- Date: Wed, 7 Jun 2023 13:30:39 GMT
- Title: Uncovering and Categorizing Social Biases in Text-to-SQL
- Authors: Yan Liu, Yan Gao, Zhe Su, Xiaokang Chen, Elliott Ash, Jian-Guang Lou
- Abstract summary: Large pre-trained language models are acknowledged to carry social biases towards different demographics.
Existing Text-to- models are trained on clean, neutral datasets, such as Spider and Wiki.
This work aims to uncover and categorize social biases in Text-to- models.
- Score: 28.07279278808438
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- ASCenD-BDS: Adaptable, Stochastic and Context-aware framework for Detection of Bias, Discrimination and Stereotyping [0.0]
This paper presents framework named ASCenD BDS (Adaptable, Context and Context-aware framework for Detection of Bias, Discrimination and Stereotyping)
The framework presents approach to detecting bias, discrimination, stereotyping across various categories such as gender caste, age, disability, socioeconomic status, linguistic variations, etc.
The concept has been tested out in SFCLabs as part of product development.
arXiv Detail & Related papers (2025-02-04T07:44:20Z) - IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian Context [32.48196952339581]
We introduce IndiBias, a benchmark dataset for evaluating social biases in the Indian context.
The included bias dimensions encompass gender, religion, caste, age, region, physical appearance, and occupation.
Our dataset contains 800 sentence pairs and 300s for bias measurement across different demographics.
arXiv Detail & Related papers (2024-03-29T12:32:06Z) - SocialStigmaQA: A Benchmark to Uncover Stigma Amplification in
Generative Language Models [8.211129045180636]
We introduce a benchmark meant to capture the amplification of social bias, via stigmas, in generative language models.
Our benchmark, SocialStigmaQA, contains roughly 10K prompts, with a variety of prompt styles, carefully constructed to test for both social bias and model robustness.
We find that the proportion of socially biased output ranges from 45% to 59% across a variety of decoding strategies and prompting styles.
arXiv Detail & Related papers (2023-12-12T18:27:44Z) - Probing Intersectional Biases in Vision-Language Models with
Counterfactual Examples [5.870913541790421]
We employ text-to-image diffusion models to produce counterfactual examples for probing intserctional social biases at scale.
Our approach utilizes Stable Diffusion with cross attention control to produce sets of counterfactual image-text pairs.
We conduct extensive experiments using our generated dataset which reveal the intersectional social biases present in state-of-the-art VLMs.
arXiv Detail & Related papers (2023-10-04T17:25:10Z) - CBBQ: A Chinese Bias Benchmark Dataset Curated with Human-AI
Collaboration for Large Language Models [52.25049362267279]
We present a Chinese Bias Benchmark dataset that consists of over 100K questions jointly constructed by human experts and generative language models.
The testing instances in the dataset are automatically derived from 3K+ high-quality templates manually authored with stringent quality control.
Extensive experiments demonstrate the effectiveness of the dataset in detecting model bias, with all 10 publicly available Chinese large language models exhibiting strong bias in certain categories.
arXiv Detail & Related papers (2023-06-28T14:14:44Z) - Uncovering and Quantifying Social Biases in Code Generation [71.96047133403688]
We propose a new paradigm to construct code prompts and successfully uncover social biases in code generation models.
We develop a dataset along with three metrics to evaluate the overall social bias and fine-grained unfairness across different demographics.
We conduct analysis to provide useful insights for further choice of code generation models with low social bias.
arXiv Detail & Related papers (2023-05-24T17:37:33Z) - Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL
Robustness [115.66421993459663]
Recent studies reveal that text-to- models are vulnerable to task-specific perturbations.
We propose a comprehensive robustness benchmark based on Spider to diagnose the model.
We conduct a diagnostic study of the state-of-the-art models on the set.
arXiv Detail & Related papers (2023-01-21T03:57:18Z) - XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for
Cross-lingual Text-to-SQL Semantic Parsing [70.40401197026925]
In-context learning using large language models has recently shown surprising results for semantic parsing tasks.
This work introduces the XRICL framework, which learns to retrieve relevant English exemplars for a given query.
We also include global translation exemplars for a target language to facilitate the translation process for large language models.
arXiv Detail & Related papers (2022-10-25T01:33:49Z) - The Tail Wagging the Dog: Dataset Construction Biases of Social Bias
Benchmarks [75.58692290694452]
We compare social biases with non-social biases stemming from choices made during dataset construction that might not even be discernible to the human eye.
We observe that these shallow modifications have a surprising effect on the resulting degree of bias across various models.
arXiv Detail & Related papers (2022-10-18T17:58:39Z) - Towards Understanding and Mitigating Social Biases in Language Models [107.82654101403264]
Large-scale pretrained language models (LMs) can be potentially dangerous in manifesting undesirable representational biases.
We propose steps towards mitigating social biases during text generation.
Our empirical results and human evaluation demonstrate effectiveness in mitigating bias while retaining crucial contextual information.
arXiv Detail & Related papers (2021-06-24T17:52:43Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.