Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.15196 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909890351464448 |
|---|---|
| author | Jie, Renlong |
| author_facet | Jie, Renlong |
| contents | Effective human-AI collaboration hinges on the ability to dynamically integrate the complementary strengths of human experts and AI models across diverse decision contexts. Context-aware weighted combination of human and AI outputs is a promising technique, which involves the optimization of combination weights based on capabilities of decision agents on a given task. However, existing approaches treat humans and AI as isolated entities, lacking a unified representation to model the heterogeneous capabilities of multiple decision agents. To address this gap, we propose a novel capability-aware architecture that models both human and AI decision-makers using learnable capability vectors. These vectors encode task-relevant competencies in a shared latent space and are used by a transformer-based weight generation module to produce instance-specific aggregation weights. Our framework supports flexible integration of confidence scores or one-hot decisions from a variable number of agents. We further introduce a learning-free baseline using optimized global weights for human-AI collaboration. Extensive experiments on image classification and hate speech detection tasks demonstrate that our approach outperforms state-of-the-art methods under various collaboration settings with both simulated and real human labels. The results highlight the robustness, scalability, and superior accuracy of our method, underscoring its potential for real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15196 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning to Collaborate: A Capability Vectors-based Architecture for Adaptive Human-AI Decision Making Jie, Renlong Human-Computer Interaction Effective human-AI collaboration hinges on the ability to dynamically integrate the complementary strengths of human experts and AI models across diverse decision contexts. Context-aware weighted combination of human and AI outputs is a promising technique, which involves the optimization of combination weights based on capabilities of decision agents on a given task. However, existing approaches treat humans and AI as isolated entities, lacking a unified representation to model the heterogeneous capabilities of multiple decision agents. To address this gap, we propose a novel capability-aware architecture that models both human and AI decision-makers using learnable capability vectors. These vectors encode task-relevant competencies in a shared latent space and are used by a transformer-based weight generation module to produce instance-specific aggregation weights. Our framework supports flexible integration of confidence scores or one-hot decisions from a variable number of agents. We further introduce a learning-free baseline using optimized global weights for human-AI collaboration. Extensive experiments on image classification and hate speech detection tasks demonstrate that our approach outperforms state-of-the-art methods under various collaboration settings with both simulated and real human labels. The results highlight the robustness, scalability, and superior accuracy of our method, underscoring its potential for real-world applications. |
| title | Learning to Collaborate: A Capability Vectors-based Architecture for Adaptive Human-AI Decision Making |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2502.15196 |