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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add L2C options to defer-only gating (ablation) | CL2DC · GalaxyZoo | AUARC: 92.37 -> 93.57 | Improved |
| add L2D options to complement-only gating (ablation) | CL2DC · GalaxyZoo | AUARC: 92.80 -> 93.57 | Improved |
| add L2C options to defer-only gating (ablation) | CL2DC · MiceBone | AUARC: 84.05 -> 85.27 | Improved |
| add L2D options to complement-only gating (ablation) | CL2DC · MiceBone | AUARC: 84.45 -> 85.27 | Improved |
| lower penalty growth lambda from 1 (ablation) | CL2DC · CIFAR-100 | accuracy vs coverage | Improved |
| increase experts from 2 to 3 (ablation) | CL2DC · CIFAR-100 (synthetic experts) | AUARC | Improved |
| add more than 3 experts (ablation) | CL2DC · CIFAR-100 (synthetic experts) | AUARC | No clear effect |
| use two experts instead of three (ablation) | CL2DC vs baselines · Chaoyang2Exp | accuracy vs coverage | Improved |
| w/o L2C vs w/o L2D at high coverage (ablation) | CL2DC · GalaxyZoo vs MiceBone | accuracy | Mixed |
Closest papers by meaning
- A Unifying Post-Processing Framework for Multi-Objective Learn-to-Defer Problems (NeurIPS 2024 · similarity 0.84)
- Exploiting Human-AI Dependence for Learning to Defer (ICML 2024 · similarity 0.84)
- Learning to Decide with AI Assistance under Human-Alignment (NeurIPS 2026 · similarity 0.84)
- A No Free Lunch Theorem for Human-AI Collaboration (AAAI 2025 · similarity 0.84)
- NestRL: A Nested Training Regime for Mutual Adaptation in Human–AI Teaming (NeurIPS 2026 · similarity 0.84)
- Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learning (ICLR 2026 · similarity 0.84)
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.
