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 (including safety, privacy, robustness, truthfulness, fairness, and machine ethics), state-of-the-art evaluation benchmarks, and effective mitigation strategies. 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, providing actionable guidance for the CIKM community.

Recently, Large Language Models (LLMs) have shown remarkable capabilities, but concerns about their trustworthiness-especially under ''jailbreaking'' attacks-remain unresolved. Prior work often assumes white-box access or relies on fixed prompt templates, limiting practicality. We propose ObscurePrompt, a simple yet effective black-box jailbreak method inspired by fragile LLM alignment on Out-of-Distribution (OOD) inputs. ObscurePrompt constructs base prompts using existing jailbreak techniques, then employs powerful LLMs to iteratively generate obscure variants that evade detection. Extensive experiments demonstrate that ObscurePrompt outperforms existing methods and remains effective against two widely-used defenses.

Vision Language Models (VLMs) have demonstrated remarkable success in downstream applications, yet they often exhibit biases, raising ethical concerns. While previous efforts have aimed to evaluate and improve the moral reasoning capabilities of VLMs, existing approaches are limited by simplified, unimodal settings or overly static visual scenarios. We propose a novel multi-image-based dataset pipeline MIST (Moral Inference through Storytelling with Text and Images) designed to assess moral reasoning in complex, dynamic scenarios to address these limitations. To ensure better alignment between these modalities, we introduce the concept of ''text-image flow,'' which seamlessly integrates visual and textual information across complex scenarios. Using this dataset, we evaluate seven widely used VLMs, offering critical insights into their performance in moral reasoning tasks.

Nowadays, it is common for a person to possess different identities on multiple social platforms. Social network alignment aims to match the identities that from different networks. Recently, unsupervised network alignment methods have received significant attention since no identity anchor is required. However, to capture the relevance between identities, the existing unsupervised methods generally rely heavily on user profiles, which is unobtainable and unreliable in real-world scenarios. In this paper, we propose an unsupervised alignment framework named Large-Scale Network Alignment (LSNA) to integrate the network information and reduce the requirement on user profile. The embedding module of LSNA, named Cross Network Embedding Model (CNEM), aims to integrate the topology information and the network correlation to simultaneously guide the embedding process. Moreover, in order to adapt LSNA to large-scale networks, we propose a network disassembling strategy to divide the costly large-scale network alignment problem into multiple executable sub-problems. The proposed method is evaluated over multiple real-world social network datasets, and the results demonstrate that the proposed method outperforms the state-of-the-art methods.

Similarity search is an important function in many applications, which usually focuses on measuring the similarity between objects with the same type. However, in many scenarios, we need to measure the relatedness between objects with different types. With the surge of study on heterogeneous networks, the relevance measure on objects with different types becomes increasingly important. In this paper, we study the relevance search problem in heterogeneous networks, where the task is to measure the relatedness of heterogeneous objects (including objects with the same type or different types). A novel measure HeteSim is proposed, which has the following attributes: (1) a uniform measure: it can measure the relatedness of objects with the same or different types in a uniform framework; (2) a path-constrained measure: the relatedness of object pairs are defined based on the search path that connects two objects through following a sequence of node types; (3) a semi-metric measure: HeteSim has some good properties (e.g., self-maximum and symmetric), which are crucial to many data mining tasks. Moreover, we analyze the computation characteristics of HeteSim and propose the corresponding quick computation strategies. Empirical studies show that HeteSim can effectively and efficiently evaluate the relatedness of heterogeneous objects.

Knowledge discovery facilitates querying database knowledge and intelligent query answering in database systems. We investigate the application of discovered knowledge, concept hierarchies, and knowledge discovery tools for intelligent query answering in database systems. A knowledge-rich data model is constructed to incorporate discovered knowledge and knowledge discovery tools. Queries are classified into data queries and knowledge queries. Both types of queries can be answered directly by simple retrieval or intelligently by analyzing the intent of query and providing generalized, neighborhood or associated information using stored or discovered knowledge. Techniques have been developed for intelligent query answering using discovered knowledge and/or knowledge discovery tools, which includes generalization, data summarization, concept clustering, rule discovery, query rewriting, deduction, lazy evaluation, application of multiple-layered databases, etc. Our study shows that knowledge discovery substantially broadens the spectrum of intelligent query answering and may have deep implications on query answering in data- and knowledge-base systems.

A prototyped data mining system, DBLearn, has been developed, which efficiently and effectively extracts different kinds of knowledge rules from relational databases. It has the following features: high level learning interfaces, tightly integrated with commercial relational database systems, automatic refinement of concept hierarchies, efficient discovery algorithms and good performance. Substantial extensions of its knowledge discovery power towards knowledge mining in object-oriented, deductive and spatial databases are under research and development.