Workshop Details

By bringing together researchers and practitioners, the workshop aims to foster collaboration, knowledge exchange, and the development of novel solutions. Through this collective effort, we can advance the understanding and implementation of transparent and interpretable approaches in adaptive and personalized systems, including integrating Language Models (LLMs) to enhance transparency and enable users to comprehend the internal mechanisms guiding these systems.


Adaptive and personalized systems, including Large Language Models (LLMs) have rapidly emerged as transformative technologies, deeply integrated into various aspects of modern life. From conversational agents that provide human-like interactions to recommendation algorithms that curate personalized content such as music, movies, or products, these systems are reshaping how individuals interact with digital platforms. As their influence grows in supporting decision-making, content delivery, and user engagement, it becomes increasingly important to address key issues such as transparency, fairness, and user trust. Frameworks like the EU General Data Protection Regulation (GDPR) and EU AI-Act have highlighted the 'right to explanation,' underscoring the need for users to understand the mechanisms driving these intelligent systems. Despite that, a significant portion of research in these fields has been geared toward maximizing performance, i.e., improving the relevance of the results of personalized systems, often at the expense of explainability. This trade-off risks eroding user trust and poses problems of compliance with ethical and regulatory standards. This initiative aims to create a forum for discussing the pressing challenges, innovative methodologies, and future directions in exploring how transparency, explainability, and user-centric design can be incorporated into these technologies to make them not only effective but also trustworthy, ethical, and aligned with the diverse needs and expectations of their users.



Topics of interests include but are not limited to:


Transparent and Explainable Personalization Strategies

o   Scrutable User Models

o   Transparent User Profiling and Personal Data Extraction

o   Explainable Personalization and Adaptation Methodologies

o   Novel strategies (e.g., conversational recommender systems) for building transparent algorithms

o   Transparent Personalization and Adaptation to Groups of users


Transparent personalization based on Large Language Models


Designing Explanation Algorithms

o   Explanation algorithms based on item description and item properties

o   Explanation algorithms based on user-generated content (e.g., reviews)

o   Explanation algorithms based on collaborative information

o   Building explanation algorithms for opaque personalization techniques (e.g., neural networks, matrix factorization, deep learning approaches)

o   Explanation algorithms based on methods to build group models


Designing Transparent and Explainable User Interfaces

o   Transparent User Interfaces

o   Designing Transparent Interaction methodologies

o   Novel paradigms (e.g. chatbots, LLMs) for building transparent models


Evaluating Transparency and Explainability

o   Evaluating Transparency in interaction or personalization

o   Evaluating Explainability of the algorithms

o   Designing User Studies for evaluating transparency and explainability

o   Novel metrics and experimental protocols


Open Issues in Transparent and Explainable User Models and Personalized Systems

o   Ethical issues (fairness and biases) in user / group models and personalized systems

o   Privacy management of personal and social data

o   Discussing Recent Regulations (GDPR) and future directions