# Investigations of Performance and Bias in Human-AI Teamwork in Hiring

arXiv: https://arxiv.org/abs/2202.11812 · HTML: https://mlsanity.com/paper/2202.11812/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 40 references that are in the map.
- First posted on arXiv 21 Feb 2022.

## Builds on (most cited first, 18 of 18)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Explaining Explanations: An Overview of Interpretability of Machine Learning](https://mlsanity.com/paper/1806.00069/) (2018)
- [Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance](https://mlsanity.com/paper/2006.14779/) (2020)
- [Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting](https://mlsanity.com/paper/1901.09451/) (2019)
- [Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making](https://mlsanity.com/paper/2001.02114/) (2020)
- [Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them](https://mlsanity.com/paper/1903.03862/) (2019)
- [Human-level performance in first-person multiplayer games with population-based deep reinforcement learning](https://mlsanity.com/paper/1807.01281/) (2018)
- [Manipulating and Measuring Model Interpretability](https://mlsanity.com/paper/1802.07810/) (2018)
- [Fairness in Machine Learning](https://mlsanity.com/paper/2012.15816/) (2020)
- [Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practices](https://mlsanity.com/paper/1906.09208/) (2019)
- [On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection](https://mlsanity.com/paper/1811.07901/) (2018)
- [Discrimination in Online Ad Delivery](https://mlsanity.com/paper/1301.6822/) (2013)
- [What can AI do for me: Evaluating Machine Learning Interpretations in Cooperative Play](https://mlsanity.com/paper/1810.09648/) (2018)
- [Discrimination in the Age of Algorithms](https://mlsanity.com/paper/1902.03731/) (2019)
- [What's in a Name? Reducing Bias in Bios without Access to Protected Attributes](https://mlsanity.com/paper/1904.05233/) (2019)
- [What You See Is What You Get? The Impact of Representation Criteria on Human Bias in Hiring](https://mlsanity.com/paper/1909.03567/) (2019)

## Built on by (most cited first, 16 of 16)

- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations](https://mlsanity.com/paper/2310.11501/) (2023)
- [RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs](https://mlsanity.com/paper/2404.08555/) (2024)
- [How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions](https://mlsanity.com/paper/2406.14805/) (2024)
- [Explanations, Fairness, and Appropriate Reliance in Human-AI Decision-Making](https://mlsanity.com/paper/2209.11812/) (2022)
- [Human-AI collaboration is not very collaborative yet: A taxonomy of interaction patterns in AI-assisted decision making from a systematic review](https://mlsanity.com/paper/2310.19778/) (2023)
- [A SMART Mnemonic Sounds like "Glue Tonic": Mixing LLMs with Student Feedback to Make Mnemonic Learning Stick](https://mlsanity.com/paper/2406.15352/) (2024)
- [Towards Effective Human-AI Decision-Making: The Role of Human Learning in Appropriate Reliance on AI Advice](https://mlsanity.com/paper/2310.02108/) (2023)
- [No Thoughts Just AI: Biased LLM Hiring Recommendations Alter Human Decision Making and Limit Human Autonomy](https://mlsanity.com/paper/2509.04404/) (2025)
- [On the Relationship Between Explanations, Fairness Perceptions, and Decisions](https://mlsanity.com/paper/2204.13156/) (2022)
- [A Meta-Learning Algorithm for Interrogative Agendas](https://mlsanity.com/paper/2301.01837/) (2023)
- [A Dynamic Model of Performative Human-ML Collaboration: Theory and Empirical Evidence](https://mlsanity.com/paper/2405.13753/) (2024)
- [When Stereotypes GTG: The Impact of Predictive Text Suggestions on Gender Bias in Human-AI Co-Writing](https://mlsanity.com/paper/2409.20390/) (2024)
- [Regret Bounds for Reinforcement Learning from Multi-Source Imperfect Preferences](https://mlsanity.com/paper/2603.20453/) (2026)
- [Turtle Score -- Similarity Based Developer Analyzer](https://mlsanity.com/paper/2205.04876/) (2022)
- [NLPGuard: A Framework for Mitigating the Use of Protected Attributes by NLP Classifiers](https://mlsanity.com/paper/2407.01697/) (2024)

## Abstract (arXiv)

In AI-assisted decision-making, effective hybrid (human-AI) teamwork is not solely dependent on AI performance alone, but also on its impact on human decision-making. While prior work studies the effects of model accuracy on humans, we endeavour here to investigate the complex dynamics of how both a model's predictive performance and bias may transfer to humans in a recommendation-aided decision task. We consider the domain of ML-assisted hiring, where humans -- operating in a constrained selection setting -- can choose whether they wish to utilize a trained model's inferences to help select candidates from written biographies. We conduct a large-scale user study leveraging a re-created dataset of real bios from prior work, where humans predict the ground truth occupation of given candidates with and without the help of three different NLP classifiers (random, bag-of-words, and deep neural network). Our results demonstrate that while high-performance models significantly improve human performance in a hybrid setting, some models mitigate hybrid bias while others accentuate it. We examine these findings through the lens of decision conformity and observe that our model architecture choices have an impact on human-AI conformity and bias, motivating the explicit need to assess these complex dynamics prior to deployment.