Towards Trustworthy and Socially Responsible Generative Foundation Models

Generative foundation models (GenFMs), including large language and multimodal models, are transforming information retrieval and knowledge management. However, their rapid adoption raises urgent concerns about social responsibility, trustworthiness, and governance. This tutorial offers a comprehensive, hands-on overview of recent advances in responsible GenFMs, covering foundational concepts, multi-dimensional risk taxonomies, state-of-the-art evaluation benchmarks, and effective mitigation strategies.

We have been maintaining the awesome-llm-safety GitHub repo since 2023, which has over 1.5k stars. It collects thousands of trustworthy LLM papers, as well as comprehensive content such as tutorials, talks, news, etc. Building on this, we integrate real-world case studies and practical exercises using open-source tools, and present key perspectives from both policy and industry, including recent regulatory developments and enterprise practices. The session concludes with a discussion of open challenges and actionable guidance.