Referential Uncertainty in Human--AI Collaboration
Quick summary
arXiv:2609.39518v1 Announce Type: new Abstract: Effective human-AI collaboration requires partners to establish references through interaction, which becomes fragile when descriptions are ambiguous, similar referents compete, or partners see different things. We study referential uncertainty - uncertainty over which candidate object a description refers to - in a collaborative puzzle task where a human Helper instructs an AI Worker to place pieces. The Worker must identify and communicate its uncertainty, and the Helper must recognize and act on it. We show that a separately elicited belief di
Key takeaways
- arXiv:2609.39518v1 Announce Type: new Abstract: Effective human-AI collaboration requires partners to establish references through interaction, which becomes fragile when descriptions are ambiguous, similar referents compete, or partners see different things.
- We study referential uncertainty - uncertainty over which candidate object a description refers to - in a collaborative puzzle task where a human Helper instructs an AI Worker to place pieces.
- The Worker must identify and communicate its uncertainty, and the Helper must recognize and act on it.
Why it matters
The value of this work lies as much in how it was tested as in the claim itself. Sample design, baselines, uncertainty and replication help separate a laboratory result from real-world impact.
Member comments