AI Paper Atlas

Research map / Large language models / AI and society

Coverage-Constrained Human-AI Cooperation with Multiple Experts

Zheng Zhang, Cuong C. Nguyen, Kevin Wells, Thanh-Toan Do, David Rosewarne, Gustavo Carneiro

AAAI 2026 · Large language models › AI and society · approach: Human-centered trust and agency · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add L2C options to defer-only gating (ablation)CL2DC · GalaxyZooAUARC: 92.37 -> 93.57Improved
add L2D options to complement-only gating (ablation)CL2DC · GalaxyZooAUARC: 92.80 -> 93.57Improved
add L2C options to defer-only gating (ablation)CL2DC · MiceBoneAUARC: 84.05 -> 85.27Improved
add L2D options to complement-only gating (ablation)CL2DC · MiceBoneAUARC: 84.45 -> 85.27Improved
lower penalty growth lambda from 1 (ablation)CL2DC · CIFAR-100accuracy vs coverageImproved
increase experts from 2 to 3 (ablation)CL2DC · CIFAR-100 (synthetic experts)AUARCImproved
add more than 3 experts (ablation)CL2DC · CIFAR-100 (synthetic experts)AUARCNo clear effect
use two experts instead of three (ablation)CL2DC vs baselines · Chaoyang2Expaccuracy vs coverageImproved
w/o L2C vs w/o L2D at high coverage (ablation)CL2DC · GalaxyZoo vs MiceBoneaccuracyMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy