Human-AI Complementarity

Follow this topic Ask about this topic

Latest papers

16 papers3 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Towards Human-AI Complementarity for AI Safety
Oct 18, 2026Sander Lanbo Shi, Miranda Anna Christ, Eric Modesitt +20Human-AI Complementarity Human Oversight of AI
Sampura Research · University of California, Berkeley · University of Illinois Urbana-Champaign +6
Indirect Influences of Artificial Intelligence Advice on Complex Sepsis Treatment Decisions
Oct 16, 2026Venkatesh Sivaraman, Joel Levin, Eric P. Mason +6AI-Assisted Decision Making Human-AI Decision Making
Department of Epidemiology and Biostatistics, University of California, San Francisco, San Francisco, California, United States · Rady School of Management, University of California, San Diego, La Jolla, California, United States · Human-Computer Interaction Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, United States +3
Better together? A performance theory of human-machine skill policies under generalization difficulty
Oct 12, 2026Riccardo ZanardelliHuman-AI Complementarity Human-AI Decision Making
Available but Unclaimed: An Empirical Study of Human-AI Synergy
Sep 15, 2026Robin Welsch, Michelle Rausch, Pascal Knierim +4Human-AI Complementarity AI-Assisted Decision Making
Aalto University, Espoo, Finland · University of Innsbruck, Innsbruck, Austria · Humboldt-Universität zu Berlin, Berlin, Germany +1
CentaurBench: Benchmarking LLM Capabilities on Augmenting vs. Automating Real-World Work Tasks
Aug 19, 2026Pattaraphon Kenny Wongchamcharoen, Kris Gulati, Min Min Fong +1LLM Agent Evaluation Human-AI Collaboration
Data Innovation and AI Lab (DIAL) at the Haas School of Business, UC Berkeley · UC Berkeley · UC Berkeley and NBER
Robust Human-AI Complementarity under Uncertainty
Jul 7, 2026Yewon Byun, Bryan WilderHuman-AI Complementarity Human-AI Decision Making
Machine Learning Department, Carnegie Mellon University.
Human Capital, Not Model Benchmarks, Predicts Hybrid Intelligence in Forecasting
Jul 2, 2026Vivienne MingHuman-AI Complementarity Probabilistic Forecasting
The Human Trust; Possibility Science; UCL Global Business School for Health
Tree-Based Formalization of Multi-Agent Complementarity in Human-AI Interactions
Jun 3, 2026Andrea FerrarioHuman-AI Complementarity Ensemble Learning
Institute of Biomedical Ethics and History of Medicine, University of Zurich, Zurich, Switzerland · SUPSI, Dalle Molle Institute for Artificial Intelligence (IDSIA), Lugano, Switzerland · ETH Zurich, Zurich, Switzerland
Rationalize: Shared Semantic Reasoning for Human-AI Alignment
May 28, 2026Aritra Dasgupta, Naga Datha Saikiran Battula, Avina Nakarmi +3AI Alignment Human-AI Interaction
New Jersey Institute of Technology Newark, USA
Generative AI and the Productivity Divide: Human-AI Complementarities in Education
May 18, 2026Lihi Idan, Bharat AnandHuman-AI Complementarity AI in Education
Industrial and Systems Engineering Department, Texas A&M University · Leonard N. Stern School of Business, New York University
When Can Human-AI Teams Outperform Individuals? Tight Bounds with Impossibility Guarantees
May 9, 2026Dongxin Guo, Jikun Wu, Siu-Ming YiuHuman-AI Complementarity Ensemble Learning
The University of Hong Kong, Hong Kong, China · Stellaris AI Limited, Hong Kong, China · Brain Investing Limited, Hong Kong, China
Toward Human-AI Complementarity Across Diverse Tasks
Apr 13, 2026Yuzheng Xu, Annya Dahmani, Matthew D. Blanchard +13Human-AI Complementarity Human-AI Decision Making
The University of Tokyo · UC Berkeley · University of Sydney +6
Self++: Co-Determined Agency for Human--AI Symbiosis in Extended Reality
Mar 30, 2026Thammathip PiumsomboonHuman-AI Collaboration Human-AI Complementarity
School of Product Design, University of Canterbury, Christchurch, New Zealand
Align When They Want, Complement When They Need! Human-Centered Ensembles for Adaptive Human-AI Collaboration
Feb 23, 2026Hasan Amin, Ming Yin, Rajiv KhannaHuman-AI Complementarity Human-AI Collaboration
Purdue University, USA
Multi-Round Human-AI Collaboration with User-Specified Requirements
Feb 19, 2026Sima Noorani, Shayan Kiyani, Hamed Hassani +1Human-AI Complementarity Human-AI Collaboration
University of Pennsylvania
Human-AI Complementarity: A Goal for Amplified Oversight
Oct 30, 2025Rishub Jain, Sophie Bridgers, Lili Janzer +3Human-AI Complementarity Claim Verification
1Google DeepMind · 2Work done while previously at Google DeepMind

Oct 18, 2026J/K move · Enter open · S save

Towards Human-AI Complementarity for AI Safety

Sander Lanbo Shi, Miranda Anna Christ, Eric Modesitt, Andrew Louis+19

Sampura Research · University of California, Berkeley · University of Illinois Urbana-Champaign+6

Human-AI Complementarity Human Oversight of AI AI Safety Evaluation Human-in-the-Loop Evaluation

Open paper AskPDF arXiv

Safely overseeing AI is increasingly challenging for the humans doing it, as they must evaluate longer and more complex outputs with every new model generation. To mitigate this challenge, we could leverage complementarity: where humans and models make different mistakes, combining their judgements could yield an oversight signal stronger than either produces alone. We study this opportunity in realistic, safety-relevant settings, contributing the largest known suite of such tasks (3,957 instances across 8 datasets and 6 domains) as well as a platform and data pipeline for measuring human, AI, and human-AI performance on matched items. We collected 35,613 judgements from 416 human raters, finding a considerable opportunity for a complementarity effect. We also found that with the assistance methods we tested, human raters corrected the AI's errors less often, even when overall human accuracy rose, and the hybridisation methods we tested added little over the better single source on average. While complementarity is an important and feasible engineering target for safe oversight, achieving it remains an open challenge for future work.