# Comparing Humans and Models on a Similar Scale: Towards Cognitive Gender Bias Evaluation in Coreference Resolution

arXiv: https://arxiv.org/abs/2305.15389 · HTML: https://mlsanity.com/paper/2305.15389/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 41 references that are in the map.
- First posted on arXiv 24 May 2023.

## Builds on (most cited first, 17 of 17)

- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [Gender Bias in Coreference Resolution](https://mlsanity.com/paper/1804.09301/) (2018)
- [Evaluating Gender Bias in Machine Translation](https://mlsanity.com/paper/1906.00591/) (2019)
- [The Right Tool for the Job: Matching Model and Instance Complexities](https://mlsanity.com/paper/2004.07453/) (2020)
- [Gender Bias in Machine Translation](https://mlsanity.com/paper/2104.06001/) (2021)
- [Competency Problems: On Finding and Removing Artifacts in Language Data](https://mlsanity.com/paper/2104.08646/) (2021)
- [Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions](https://mlsanity.com/paper/2106.05022/) (2021)
- [Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation](https://mlsanity.com/paper/2109.03858/) (2021)
- [Welcome to the Modern World of Pronouns: Identity-Inclusive Natural Language Processing beyond Gender](https://mlsanity.com/paper/2202.11923/) (2022)
- [Large-Scale QA-SRL Parsing](https://mlsanity.com/paper/1805.05377/) (2018)
- [Coreference Resolution without Span Representations](https://mlsanity.com/paper/2101.00434/) (2021)
- [Bridging Information-Seeking Human Gaze and Machine Reading Comprehension](https://mlsanity.com/paper/2009.14780/) (2020)
- [On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations](https://mlsanity.com/paper/2204.12708/) (2022)

## Built on by (most cited first, 3 of 3)

- [Fairness in Large Language Models: A Taxonomic Survey](https://mlsanity.com/paper/2404.01349/) (2024)
- [Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model](https://mlsanity.com/paper/2310.12611/) (2023)
- [Psychometric Predictive Power of Large Language Models](https://mlsanity.com/paper/2311.07484/) (2023)

## Abstract (arXiv)

Spurious correlations were found to be an important factor explaining model performance in various NLP tasks (e.g., gender or racial artifacts), often considered to be ''shortcuts'' to the actual task. However, humans tend to similarly make quick (and sometimes wrong) predictions based on societal and cognitive presuppositions. In this work we address the question: can we quantify the extent to which model biases reflect human behaviour? Answering this question will help shed light on model performance and provide meaningful comparisons against humans. We approach this question through the lens of the dual-process theory for human decision-making. This theory differentiates between an automatic unconscious (and sometimes biased) ''fast system'' and a ''slow system'', which when triggered may revisit earlier automatic reactions. We make several observations from two crowdsourcing experiments of gender bias in coreference resolution, using self-paced reading to study the ''fast'' system, and question answering to study the ''slow'' system under a constrained time setting. On real-world data humans make ~3% more gender-biased decisions compared to models, while on synthetic data models are ~12% more biased.