Context-Dependent Affordance Reports in Vision-Language Models
Quick summary
arXiv:2603.04419v3 Announce Type: replace-cross Abstract: Vision-language models produce different object and use descriptions under different persona prompts, but low overlap alone does not identify an affordance effect. We audit an earlier seven-prompt study and add matched-question controls. In the historical Qwen pilot, 363 of 3,213 parsed responses contain empty object lists. These affect 2,037 of 9,244 comparisons, with the implementation assigning zero lexical overlap to every affected pair. Conditioning on nonempty reports raises pooled word Jaccard from 0.095 to 0.121 and sentence cos
Key takeaways
- arXiv:2603.04419v3 Announce Type: replace-cross Abstract: Vision-language models produce different object and use descriptions under different persona prompts, but low overlap alone does not identify an affordance effect.
- We audit an earlier seven-prompt study and add matched-question controls.
- In the historical Qwen pilot, 363 of 3,213 parsed responses contain empty object lists.
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