Consistency-based Abductive Reasoning over Perceptual Errors of Multiple Pre-trained Models in Novel Environments

Mario A. Leiva, Noel Ngu, Joshua Shay Kricheli, Aditya Taparia, Ransalu Senanayake, Paulo Shakarian, Nathaniel D. Bastian, John Corcoran, Gerardo I. Simari

Proceedings of the AAAI Conference on Artificial Intelligence, 2026

picture_as_pdf PDF

Summary

When pre-trained perception models are deployed in novel environments, distribution shift makes them disagree. We cast the problem of reconciling those conflicting predictions as consistency-based abduction applied at test time rather than during training, achieving average relative improvements of roughly 13.6% in F1 and 16.6% in accuracy over the best individual model across 15 test datasets.

BibTeX

@inproceedings{leiva2026consistency,
    title={Consistency-based Abductive Reasoning over Perceptual Errors of Multiple Pre-trained Models in Novel Environments},
    author={Leiva, Mario A. and Ngu, Noel and Kricheli, Joshua Shay and Taparia, Aditya and Senanayake, Ransalu and Shakarian, Paulo and Bastian, Nathaniel D. and Corcoran, John and Simari, Gerardo I.},
    booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
    pages={19216--19223},
    year={2026}
}