mlsanityData to 14 Oct 2026

Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderation

arXiv 2204.11788 ↗First posted 25 Apr 2022cs.AI cs.HC cs.LGcited by 67

Not on the map. Why?

Abstract (arXiv)

Despite impressive performance in many benchmark datasets, AI models can still make mistakes, especially among out-of-distribution examples. It remains an open question how such imperfect models can be used effectively in collaboration with humans. Prior work has focused on AI assistance that helps people make individual high-stakes decisions, which is not scalable for a large amount of relatively low-stakes decisions, e.g., moderating social media comments. Instead, we propose conditional delegation as an alternative paradigm for human-AI collaboration where humans create rules to indicate trustworthy regions of a model. Using content moderation as a testbed, we develop novel interfaces to assist humans in creating conditional delegation rules and conduct a randomized experiment with two datasets to simulate in-distribution and out-of-distribution scenarios. Our study demonstrates the promise of conditional delegation in improving model performance and provides insights into design for this novel paradigm, including the effect of AI explanations.

Key facts. Cited by 67 papers in the map (data through 14 Oct 2026). Builds on 38 of its 113 references that are in the map. First posted on arXiv 25 Apr 2022.

Builds on

38 of 113 references.

References · 38

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  3. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  4. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,218
  5. 2018A Survey Of Methods For Explaining Black Box Modelscited by 973
  6. 2019Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inferencecited by 876
  7. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 571
  8. 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
  9. 2020Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performancecited by 399
  10. 2016Rationalizing Neural Predictionscited by 281
  11. 2020Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Makingcited by 281
  12. 2019Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biasescited by 280
26 more
  1. 2018Manipulating and Measuring Model Interpretabilitycited by 256
  2. 2020Questioning the AI: Informing Design Practices for Explainable AI User Experiencescited by 253
  3. 2016Ex Machina: Personal Attacks Seen at Scalecited by 210
  4. 2018On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detectioncited by 159
  5. 2018Reducing Gender Bias in Abusive Language Detectioncited by 152
  6. 2020Proxy Tasks and Subjective Measures Can Be Misleading in Evaluating Explainable AI Systemscited by 139
  7. 2019A Benchmark Dataset for Learning to Intervene in Online Hate Speechcited by 129
  8. 2020Learning to Complement Humanscited by 124
  9. 2021To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-makingcited by 118
  10. 2019Human-Centered Tools for Coping with Imperfect Algorithms during Medical Decision-Makingcited by 109
  11. 2020"Why is 'Chicago' deceptive?" Towards Building Model-Driven Tutorials for Humanscited by 86
  12. 2019Human-AI Collaboration in Data Science: Exploring Data Scientists' Perceptions of Automated AIcited by 79
  13. 2021Towards Unbiased and Accurate Deferral to Multiple Expertscited by 72
  14. 2021Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Makingcited by 58
  15. 2019Ask Not What AI Can Do, But What AI Should Do: Towards a Framework of Task Delegabilitycited by 36
  16. 2019Explaining Models: An Empirical Study of How Explanations Impact Fairness Judgmentcited by 31
  17. 2017Calendar.help: Designing a Workflow-Based Scheduling Agent with Humans in the Loopcited by 26
  18. 2019A Human-Grounded Evaluation of SHAP for Alert Processingcited by 23
  19. 2021A Framework of Severity for Harmful Content Onlinecited by 23
  20. 2020Explainable Active Learning (XAL): An Empirical Study of How Local Explanations Impact Annotator Experiencecited by 20
  21. 2021How Much Automation Does a Data Scientist Want?cited by 20
  22. 2020Keeping Community in the Loop: Understanding Wikipedia Stakeholder Values for Machine Learning-Based Systemscited by 16
  23. 2021The Irrationality of Neural Rationale Modelscited by 16
  24. 2019Discovering the Sweet Spot of Human-Computer Configurations: A Case Study in Information Extractioncited by 11
  25. 2019Content Removal as a Moderation Strategy: Compliance and Other Outcomes in the ChangeMyView Communitycited by 9
  26. 2019Trajectories of Blocked Community Members: Redemption, Recidivism and Departurecited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 19; 2024: 18; 2025: 13; 2026: 13.

67 papers.

Sort:

By area:

  1. 2023Appropriate Reliance on AI Advice: Conceptualization and the Effect of Explanationscited by 83
  2. 2023Who Should I Trust: AI or Myself? Leveraging Human and AI Correctness Likelihood to Promote Appropriate Trust in AI-Assisted Decision-Makingcited by 67
  3. 2022"Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interactioncited by 63
  4. 2025Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistantcited by 54
  5. 2024Towards Human-AI Deliberation: Design and Evaluation of LLM-Empowered Deliberative AI for AI-Assisted Decision-Makingcited by 38
  6. 2023COBRA Frames: Contextual Reasoning about Effects and Harms of Offensive Statementscited by 34
  7. 2023Human-AI Collaboration: The Effect of AI Delegation on Human Task Performance and Task Satisfactioncited by 32
  8. 2023AXNav: Replaying Accessibility Tests from Natural Languagecited by 31
  9. 2024SLM-Mod: Small Language Models Surpass LLMs at Content Moderationcited by 27
  10. 2024Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Functioncited by 24
  11. 2023Effective Human-AI Teams via Learned Natural Language Rules and Onboardingcited by 20
  12. 2025As Confidence Aligns: Exploring the Effect of AI Confidence on Human Self-confidence in Human-AI Decision Makingcited by 19
38 more
  1. 2023Human-AI collaboration is not very collaborative yet: A taxonomy of interaction patterns in AI-assisted decision making from a systematic reviewcited by 18
  2. 2024Position: Towards Bidirectional Human-AI Alignmentcited by 18
  3. 2022On the Effect of Information Asymmetry in Human-AI Teamscited by 17
  4. 2023"It Felt Like Having a Second Mind": Investigating Human-AI Co-creativity in Prewriting with Large Language Modelscited by 17
  5. 2025Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversightcited by 16
  6. 2023Learning Personalized Decision Support Policiescited by 14
  7. 2023Watch Your Language: Investigating Content Moderation with Large Language Modelscited by 14
  8. 2024Moderating Illicit Online Image Promotion for Unsafe User-Generated Content Games Using Large Vision-Language Modelscited by 14
  9. 2024Modulating Language Model Experiences through Frictionscited by 13
  10. 2024Evaluating the Utility of Conformal Prediction Sets for AI-Advised Image Labelingcited by 12
  11. 2023Competent but Rigid: Identifying the Gap in Empowering AI to Participate Equally in Group Decision-Makingcited by 11
  12. 2024NaijaHate: Evaluating Hate Speech Detection on Nigerian Twitter Using Representative Datacited by 10
  13. 2024Charting the Future of AI in Project-Based Learning: A Co-Design Exploration with Studentscited by 8
  14. 2024Comparing Zealous and Restrained AI Recommendations in a Real-World Human-AI Collaboration Taskcited by 8
  15. 2022Reliable Decision from Multiple Subtasks through Threshold Optimization: Content Moderation in the Wildcited by 7
  16. 2023Learning Complementary Policies for Human-AI Teamscited by 7
  17. 2023BiasX: "Thinking Slow" in Toxic Content Moderation with Explanations of Implied Social Biasescited by 7
  18. 2024DeMod: A Holistic Tool with Explainable Detection and Personalized Modification for Toxicity Censorshipcited by 7
  19. 2025When Should We Orchestrate Multiple Agents?cited by 7
  20. 2023Collaboration with Conversational AI Assistants for UX Evaluation: Questions and How to Ask them (Voice vs. Text)cited by 6
  21. 2023May I Ask a Follow-up Question? Understanding the Benefits of Conversations in Neural Network Explainabilitycited by 5
  22. 2024Interrogating AI: Characterizing Emergent Playful Interactions with ChatGPTcited by 5
  23. 2024SciCapenter: Supporting Caption Composition for Scientific Figures with Machine-Generated Captions and Ratingscited by 5
  24. 2024Allowing humans to interactively guide machines where to look does not always improve human-AI team's classification accuracycited by 5
  25. 2025Designing Algorithmic Delegates: The Role of Indistinguishability in Human-AI Handoffcited by 5
  26. 2023Human-AI Collaboration in Thematic Analysis using ChatGPT: A User Study and Design Recommendationscited by 3
  27. 2025Evalet: Evaluating Large Language Models through Functional Fragmentationcited by 3
  28. 2023Explain To Decide: A Human-Centric Review on the Role of Explainable Artificial Intelligence in AI-assisted Decision Makingcited by 2
  29. 2024Leveraging Large Language Models (LLMs) to Support Collaborative Human-AI Online Risk Data Annotationcited by 2
  30. 2024A Dynamic Model of Performative Human-ML Collaboration: Theory and Empirical Evidencecited by 2
  31. 2026Incentive-Tuning: Understanding and Designing Incentives for Empirical Human-AI Decision-Making Studiescited by 2
  32. 2026The Consensus Trap: Dissecting Subjectivity and the "Ground Truth" Illusion in Data Annotationcited by 2
  33. 2022A Human-ML Collaboration Framework for Improving Video Content Reviewscited by 1
  34. 2023Optimising Human-Machine Collaboration for Efficient High-Precision Information Extraction from Text Documentscited by 1
  35. 2023On the Perception of Difficulty: Differences between Humans and AIcited by 1
  36. 2025Adaptive Human-Agent Teaming: A Review of Empirical Studies from the Process Dynamics Perspectivecited by 1
  37. 2025AdvisingWise: Supporting Academic Advising in Higher Education Settings Through a Human-in-the-Loop Multi-Agent Frameworkcited by 1
  38. 2025Teaching People LLM's Errors and Getting it Rightcited by 1

50 most cited of 67 All 67 (JSON)