Controllable Complementarity: Subjective Preferences in Human-AI Collaboration
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916646460850176 |
|---|---|
| author | McDonald, Chase Gonzalez, Cleotilde |
| author_facet | McDonald, Chase Gonzalez, Cleotilde |
| contents | Research on human-AI collaboration often prioritizes objective performance. However, understanding human subjective preferences is essential to improving human-AI complementarity and human experiences. We investigate human preferences for controllability in a shared workspace task with AI partners using Behavior Shaping (BS), a reinforcement learning algorithm that allows humans explicit control over AI behavior.
In one experiment, we validate the robustness of BS in producing effective AI policies relative to self-play policies, when controls are hidden. In another experiment, we enable human control, showing that participants perceive AI partners as more effective and enjoyable when they can directly dictate AI behavior. Our findings highlight the need to design AI that prioritizes both task performance and subjective human preferences. By aligning AI behavior with human preferences, we demonstrate how human-AI complementarity can extend beyond objective outcomes to include subjective preferences. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_05455 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Controllable Complementarity: Subjective Preferences in Human-AI Collaboration McDonald, Chase Gonzalez, Cleotilde Human-Computer Interaction Artificial Intelligence Multiagent Systems Research on human-AI collaboration often prioritizes objective performance. However, understanding human subjective preferences is essential to improving human-AI complementarity and human experiences. We investigate human preferences for controllability in a shared workspace task with AI partners using Behavior Shaping (BS), a reinforcement learning algorithm that allows humans explicit control over AI behavior. In one experiment, we validate the robustness of BS in producing effective AI policies relative to self-play policies, when controls are hidden. In another experiment, we enable human control, showing that participants perceive AI partners as more effective and enjoyable when they can directly dictate AI behavior. Our findings highlight the need to design AI that prioritizes both task performance and subjective human preferences. By aligning AI behavior with human preferences, we demonstrate how human-AI complementarity can extend beyond objective outcomes to include subjective preferences. |
| title | Controllable Complementarity: Subjective Preferences in Human-AI Collaboration |
| topic | Human-Computer Interaction Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2503.05455 |