complementarity

Tag

Cards List
#complementarity

When Can Human-AI Teams Outperform Individuals? Tight Bounds with Impossibility Guarantees

arXiv cs.AI · yesterday Cached

This paper derives tight theoretical bounds for human-AI teams, proving when confidence-based aggregation leads to complementarity and establishing impossibility results under specific error correlations.

0 favorites 0 likes
← Back to home

Submit Feedback