# On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective

arXiv: https://arxiv.org/abs/2502.14296 · HTML: https://mlsanity.com/paper/2502.14296/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2025.

## Built on by (most cited first, 30 of 41)

- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [One Token to Fool LLM-as-a-Judge](https://mlsanity.com/paper/2507.08794/) (2025)
- [Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation](https://mlsanity.com/paper/2502.17521/) (2025)
- [Building a Foundational Guardrail for General Agentic Systems via Synthetic Data](https://mlsanity.com/paper/2510.09781/) (2025)
- [ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models](https://mlsanity.com/paper/2505.16517/) (2025)
- [FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning](https://mlsanity.com/paper/2510.04040/) (2025)
- [LangCoop: Collaborative Driving with Language](https://mlsanity.com/paper/2504.13406/) (2025)
- [Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models](https://mlsanity.com/paper/2505.15406/) (2025)
- [Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets](https://mlsanity.com/paper/2506.05346/) (2025)
- [HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluation](https://mlsanity.com/paper/2505.11454/) (2025)
- [Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study](https://mlsanity.com/paper/2506.04810/) (2025)
- [ToolGate: Contract-Grounded and Verified Tool Execution for LLMs](https://mlsanity.com/paper/2601.04688/) (2026)
- [SocialMaze: A Benchmark for Evaluating and Enhancing Social Reasoning in Large Language Models in Complex Social Environments](https://mlsanity.com/paper/2505.23713/) (2025)
- [Privacy Reasoning in Ambiguous Contexts](https://mlsanity.com/paper/2506.12241/) (2025)
- [Beyond Surface-Level Patterns: An Essence-Driven Defense Framework Against Jailbreak Attacks in LLMs](https://mlsanity.com/paper/2502.19041/) (2025)
- [ProbeLLM: Automating Principled Diagnosis of LLM Failures](https://mlsanity.com/paper/2602.12966/) (2026)
- [Privacy-Aware Decoding: Mitigating Privacy Leakage of Large Language Models in Retrieval-Augmented Generation](https://mlsanity.com/paper/2508.03098/) (2025)
- [Beyond Accuracy: The Role of Calibration in Self-Improving Large Language Models](https://mlsanity.com/paper/2504.02902/) (2025)
- [Generative AI for Autonomous Driving: Frontiers and Opportunities](https://mlsanity.com/paper/2505.08854/) (2025)
- [Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base](https://mlsanity.com/paper/2503.23361/) (2025)
- [SUV: Scalable Large Language Model Copyright Compliance with Regularized Selective Unlearning](https://mlsanity.com/paper/2503.22948/) (2025)
- [Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?](https://mlsanity.com/paper/2508.03644/) (2025)
- [Secure and Robust Watermarking for AI-generated Images: A Comprehensive Survey](https://mlsanity.com/paper/2510.02384/) (2025)
- [Cache Mechanism for Agent RAG Systems](https://mlsanity.com/paper/2511.02919/) (2025)
- [Emergent Risks in Generative Multi-Agent Systems](https://mlsanity.com/paper/2603.27771/) (2026)
- [Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates](https://mlsanity.com/paper/2509.18076/) (2025)
- [Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy](https://mlsanity.com/paper/2605.25603/) (2026)
- [The Role of Open-Source LLMs in Shaping the Future of GeoAI](https://mlsanity.com/paper/2504.17833/) (2025)
- [SafeCoop: Unravelling Full Stack Safety in Agentic Collaborative Driving](https://mlsanity.com/paper/2510.18123/) (2025)
- [Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projection](https://mlsanity.com/paper/2603.27240/) (2026)

## Abstract (arXiv)

Generative Foundation Models (GenFMs) have emerged as transformative tools. However, their widespread adoption raises critical concerns regarding trustworthiness across dimensions. This paper presents a comprehensive framework to address these challenges through three key contributions. First, we systematically review global AI governance laws and policies from governments and regulatory bodies, as well as industry practices and standards. Based on this analysis, we propose a set of guiding principles for GenFMs, developed through extensive multidisciplinary collaboration that integrates technical, ethical, legal, and societal perspectives. Second, we introduce TrustGen, the first dynamic benchmarking platform designed to evaluate trustworthiness across multiple dimensions and model types, including text-to-image, large language, and vision-language models. TrustGen leverages modular components--metadata curation, test case generation, and contextual variation--to enable adaptive and iterative assessments, overcoming the limitations of static evaluation methods. Using TrustGen, we reveal significant progress in trustworthiness while identifying persistent challenges. Finally, we provide an in-depth discussion of the challenges and future directions for trustworthy GenFMs, which reveals the complex, evolving nature of trustworthiness, highlighting the nuanced trade-offs between utility and trustworthiness, and consideration for various downstream applications, identifying persistent challenges and providing a strategic roadmap for future research. This work establishes a holistic framework for advancing trustworthiness in GenAI, paving the way for safer and more responsible integration of GenFMs into critical applications. To facilitate advancement in the community, we release the toolkit for dynamic evaluation.