Proceedings

Toward Trustworthy Foundation Models: Mitigating OOD Failure in Adaptation and Deployment

Ping Song

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Doctoral Consortium. Pages 8339-8340.

https://doi.org/10.24963/ijcai.2026/948

Keywords

  • Machine Learning: Robustness
  • Machine Learning: Representation learning
  • Machine Learning: Trustworthy machine learning
  • AI Ethics, Trust, Fairnes: Trustworthy AI

Abstract

Foundation models’ versatile generalization has driven their broad adoption, yet their deployment is constrained by critical gaps in trustworthiness. First, we conduct a survey to present a comprehensive analysis of what constitute trustworthy foundation model and examined approaches for each requirement from a lifecycle perspective. We identify out-of-distribution (OOD) robustness as the primary technical bottleneck, where performance collapse under distribution shifts invalidates other pillars like fairness and accountability. The nature of this vulnerability is two-fold: first, a reliance on spurious background cues during inference, and second, dimensional collapse in the representation space during fine-tuning. This research aims to mitigate these failures by developing mechanistic insights and algorithmic solutions during foundation model adaptation and deployment phases of the lifecycle.

Ping Song. 2026. Toward Trustworthy Foundation Models: Mitigating OOD Failure in Adaptation and Deployment. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 8339–8340. https://doi.org/10.24963/ijcai.2026/948
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards