---
title: "Toward Trustworthy Foundation Models: Mitigating OOD Failure in Adaptation and Deployment"
authors:
  - "Ping Song"
doi: "10.24963/ijcai.2026/948"
url: "https://ijcai.org/proceedings/2026/948"
pdf: "https://ijcai.org/proceedings/2026/0948.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "8339-8340"
track: "Doctoral Consortium"
keywords:
  - "Machine Learning: Robustness"
  - "Machine Learning: Representation learning"
  - "Machine Learning: Trustworthy machine learning"
  - "AI Ethics, Trust, Fairnes: Trustworthy AI"
---

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

Ping Song

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 8339-8340. DOI: [10.24963/ijcai.2026/948](https://doi.org/10.24963/ijcai.2026/948)

## 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.