# Toward Deconfounding the Influence of Entity Demographics for Question Answering Accuracy

arXiv: https://arxiv.org/abs/2104.07571 · HTML: https://mlsanity.com/paper/2104.07571/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 38 references that are in the map.
- First posted on arXiv 15 Apr 2021.

## Builds on (most cited first, 15 of 15)

- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [On the Cross-lingual Transferability of Monolingual Representations](https://mlsanity.com/paper/1910.11856/) (2019)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [MLQA: Evaluating Cross-lingual Extractive Question Answering](https://mlsanity.com/paper/1910.07475/) (2019)
- [Evaluating Gender Bias in Machine Translation](https://mlsanity.com/paper/1906.00591/) (2019)
- [UnQovering Stereotyping Biases via Underspecified Questions](https://mlsanity.com/paper/2010.02428/) (2020)
- [Measuring Social Biases in Grounded Vision and Language Embeddings](https://mlsanity.com/paper/2002.08911/) (2020)
- [What Makes Reading Comprehension Questions Easier?](https://mlsanity.com/paper/1808.09384/) (2018)
- [What do Models Learn from Question Answering Datasets?](https://mlsanity.com/paper/2004.03490/) (2020)
- [A BERT Baseline for the Natural Questions](https://mlsanity.com/paper/1901.08634/) (2019)
- [What Question Answering can Learn from Trivia Nerds](https://mlsanity.com/paper/1910.14464/) (2019)

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

- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)
- [NLPositionality: Characterizing Design Biases of Datasets and Models](https://mlsanity.com/paper/2306.01943/) (2023)
- [Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models](https://mlsanity.com/paper/2206.08325/) (2022)
- [Mitigating Bias for Question Answering Models by Tracking Bias Influence](https://mlsanity.com/paper/2310.08795/) (2023)
- [Open-DeBias: Toward Mitigating Open-Set Bias in Language Models](https://mlsanity.com/paper/2509.23805/) (2025)

## Abstract (arXiv)

The goal of question answering (QA) is to answer any question. However, major QA datasets have skewed distributions over gender, profession, and nationality. Despite that skew, model accuracy analysis reveals little evidence that accuracy is lower for people based on gender or nationality; instead, there is more variation on professions (question topic). But QA's lack of representation could itself hide evidence of bias, necessitating QA datasets that better represent global diversity.