# Improving Human-AI Collaboration With Descriptions of AI Behavior

arXiv: https://arxiv.org/abs/2301.06937 · HTML: https://mlsanity.com/paper/2301.06937/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 71 references that are in the map.
- First posted on arXiv 6 Jan 2023.

## Builds on (most cited first, 27 of 27)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Remote Sensing Image Scene Classification: Benchmark and State of the Art](https://mlsanity.com/paper/1703.00121/) (2017)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance](https://mlsanity.com/paper/2006.14779/) (2020)
- [Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making](https://mlsanity.com/paper/2001.02114/) (2020)
- [Improving fairness in machine learning systems: What do industry practitioners need?](https://mlsanity.com/paper/1812.05239/) (2018)
- [Manipulating and Measuring Model Interpretability](https://mlsanity.com/paper/1802.07810/) (2018)
- [On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection](https://mlsanity.com/paper/1811.07901/) (2018)
- [To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making](https://mlsanity.com/paper/2102.09692/) (2021)
- [FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learning](https://mlsanity.com/paper/1904.05419/) (2019)
- ["Why is 'Chicago' deceptive?" Towards Building Model-Driven Tutorials for Humans](https://mlsanity.com/paper/2001.05871/) (2020)
- [A Case for Humans-in-the-Loop: Decisions in the Presence of Erroneous Algorithmic Scores](https://mlsanity.com/paper/2002.08035/) (2020)
- [Automated Data Slicing for Model Validation:A Big data - AI Integration Approach](https://mlsanity.com/paper/1807.06068/) (2018)
- [Towards Accountable AI: Hybrid Human-Machine Analyses for Characterizing System Failure](https://mlsanity.com/paper/1809.07424/) (2018)
- [Conceptual Metaphors Impact Perceptions of Human-AI Collaboration](https://mlsanity.com/paper/2008.02311/) (2020)
- [Improving Human-AI Partnerships in Child Welfare: Understanding Worker Practices, Challenges, and Desires for Algorithmic Decision Support](https://mlsanity.com/paper/2204.02310/) (2022)
- [Are Visual Explanations Useful? A Case Study in Model-in-the-Loop Prediction](https://mlsanity.com/paper/2007.12248/) (2020)
- [Teaching Humans When To Defer to a Classifier via Exemplars](https://mlsanity.com/paper/2111.11297/) (2021)
- [Structure-Invariant Testing for Machine Translation](https://mlsanity.com/paper/1907.08710/) (2019)
- [Discovering and Validating AI Errors With Crowdsourced Failure Reports](https://mlsanity.com/paper/2109.11690/) (2021)
- [Machine Learning Practices Outside Big Tech: How Resource Constraints Challenge Responsible Development](https://mlsanity.com/paper/2110.02932/) (2021)
- [PulseSatellite: A tool using human-AI feedback loops for satellite image analysis in humanitarian contexts](https://mlsanity.com/paper/2001.10685/) (2020)
- [Personalization in Human-AI Teams: Improving the Compatibility-Accuracy Tradeoff](https://mlsanity.com/paper/2004.02289/) (2020)

## Built on by (most cited first, 30 of 36)

- [When combinations of humans and AI are useful: A systematic review and meta-analysis](https://mlsanity.com/paper/2405.06087/) (2024)
- [Towards Human-AI Deliberation: Design and Evaluation of LLM-Empowered Deliberative AI for AI-Assisted Decision-Making](https://mlsanity.com/paper/2403.16812/) (2024)
- [The Impact of Imperfect XAI on Human-AI Decision-Making](https://mlsanity.com/paper/2307.13566/) (2023)
- [Effective Human-AI Teams via Learned Natural Language Rules and Onboarding](https://mlsanity.com/paper/2311.01007/) (2023)
- [When Your Reviewer is an LLM: Biases, Divergence, and Prompt Injection Risks in Peer Review](https://mlsanity.com/paper/2509.09912/) (2025)
- [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)
- [Position: Towards Bidirectional Human-AI Alignment](https://mlsanity.com/paper/2406.09264/) (2024)
- [Perceptions of Sentient AI and Other Digital Minds: Evidence from the AI, Morality, and Sentience (AIMS) Survey](https://mlsanity.com/paper/2407.08867/) (2024)
- [Contrastive Explanations That Anticipate Human Misconceptions Can Improve Human Decision-Making Skills](https://mlsanity.com/paper/2410.04253/) (2024)
- [Towards Optimizing Human-Centric Objectives in AI-Assisted Decision-Making With Offline Reinforcement Learning](https://mlsanity.com/paper/2403.05911/) (2024)
- [AI Reliance and Decision Quality: Fundamentals, Interdependence, and the Effects of Interventions](https://mlsanity.com/paper/2304.08804/) (2023)
- [A No Free Lunch Theorem for Human-AI Collaboration](https://mlsanity.com/paper/2411.15230/) (2024)
- [Linguistic Comparison of AI- and Human-Written Responses to Online Mental Health Queries](https://mlsanity.com/paper/2504.09271/) (2025)
- [AI Agent Behavioral Science](https://mlsanity.com/paper/2506.06366/) (2025)
- [Who's Thinking? A Push for Human-Centered Evaluation of LLMs using the XAI Playbook](https://mlsanity.com/paper/2303.06223/) (2023)
- [Human Delegation Behavior in Human-AI Collaboration: The Effect of Contextual Information](https://mlsanity.com/paper/2401.04729/) (2024)
- [A Survey of AI Reliance](https://mlsanity.com/paper/2408.03948/) (2024)
- [Towards certifiable AI in aviation: landscape, challenges, and opportunities](https://mlsanity.com/paper/2409.08666/) (2024)
- [A Mathematical Framework for AI-Human Integration in Work](https://mlsanity.com/paper/2505.23432/) (2025)
- [Reduced AI Acceptance After the Generative AI Boom: Evidence From a Two-Wave Survey Study](https://mlsanity.com/paper/2510.23578/) (2025)
- [The Consensus Trap: Dissecting Subjectivity and the "Ground Truth" Illusion in Data Annotation](https://mlsanity.com/paper/2602.11318/) (2026)
- [A Risk Taxonomy and Reflection Tool for Large Language Model Adoption in Public Health](https://mlsanity.com/paper/2411.02594/) (2024)
- [Generative AI in Medicine](https://mlsanity.com/paper/2412.10337/) (2024)
- [When Trust Collides: Decoding Human-LLM Cooperation Dynamics through the Prisoner's Dilemma](https://mlsanity.com/paper/2503.07320/) (2025)
- [Achieving Trustworthy Real-Time Decision Support Systems with Low-Latency Interpretable AI Models](https://mlsanity.com/paper/2506.20018/) (2025)
- [AI That Helps Us Help Each Other: A Proactive System for Scaffolding Mentor-Novice Collaboration in Entrepreneurship Coaching](https://mlsanity.com/paper/2508.11052/) (2025)
- [Data-Prompt Co-Evolution: Growing Test Sets to Refine LLM Behavior](https://mlsanity.com/paper/2510.12728/) (2025)
- [Teaching People LLM's Errors and Getting it Right](https://mlsanity.com/paper/2512.21422/) (2025)
- [Human Control Is the Anchor, Not the Answer: Early Divergence of Oversight in Agentic AI Communities](https://mlsanity.com/paper/2602.09286/) (2026)
- [AI-Powered Annotation Pipelines for Stabilizing Large Language Models: A Human-AI Synergy Approach](https://mlsanity.com/paper/2512.13714/) (2025)

## Abstract (arXiv)

People work with AI systems to improve their decision making, but often under- or over-rely on AI predictions and perform worse than they would have unassisted. To help people appropriately rely on AI aids, we propose showing them behavior descriptions, details of how AI systems perform on subgroups of instances. We tested the efficacy of behavior descriptions through user studies with 225 participants in three distinct domains: fake review detection, satellite image classification, and bird classification. We found that behavior descriptions can increase human-AI accuracy through two mechanisms: helping people identify AI failures and increasing people's reliance on the AI when it is more accurate. These findings highlight the importance of people's mental models in human-AI collaboration and show that informing people of high-level AI behaviors can significantly improve AI-assisted decision making.