6 papers
GNN2R: Weakly-Supervised Rationale-Providing Question Answering over Knowledge Graphs
Ruijie Wang, Luca Rossetto, Michael Cochez +1
Despite the rapid progress of large language models (LLMs), knowledge graph-based question answering (KGQA) remains essential for producing verifiable and hallucination-resistant a…
Deep Generative Model-Based Generation of Synthetic Individual-Specific Brain MRI Segmentations
Ruijie Wang, Luca Rossetto, Susan Mérillat +3
To the best of our knowledge, all existing methods that can generate synthetic brain magnetic resonance imaging (MRI) scans for a specific individual require detailed structural or…
ConceptFormer: Towards Efficient Use of Knowledge-Graph Embeddings in Large Language Models
Joel Barmettler, Abraham Bernstein, Luca Rossetto
Retrieval Augmented Generation (RAG) has enjoyed increased attention in the recent past and recent advancements in Large Language Models (LLMs) have highlighted the importance of i…
Whom do Explanations Serve? A Systematic Literature Survey of User Characteristics in Explainable Recommender Systems Evaluation
Kathrin Wardatzky, Oana Inel, Luca Rossetto +1
Adding explanations to recommender systems is said to have multiple benefits, such as increasing user trust or system transparency. Previous work from other application areas sugge…
Performance Evaluation in Multimedia Retrieval
Loris Sauter, Ralph Gasser, Heiko Schuldt +2
Performance evaluation in multimedia retrieval, as in the information retrieval domain at large, relies heavily on retrieval experiments, employing a broad range of techniques and…
Task Presentation and Human Perception in Interactive Video Retrieval
Nina Willis, Abraham Bernstein, Luca Rossetto
Interactive video retrieval is a cooperative process between humans and retrieval systems. Large-scale evaluation campaigns, however, often overlook human factors, such as the effe…