SIEVES improves selective prediction coverage by up to 3x on OOD VQA benchmarks by training a selector to score the quality of visual evidence produced by reasoner models, generalizing across benchmarks and proprietary models without internal access or per-task retraining.
In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp
2 Pith papers cite this work, alongside 4 external citations. Polarity classification is still indexing.
2
Pith papers citing it
4
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
SIEVES: Selective Prediction Generalizes through Visual Evidence Scoring
SIEVES improves selective prediction coverage by up to 3x on OOD VQA benchmarks by training a selector to score the quality of visual evidence produced by reasoner models, generalizing across benchmarks and proprietary models without internal access or per-task retraining.
- MCMit: Hardware-Software Co-Design for Mid-Circuit Measurement Error Mitigation