Program

Explore our program featuring three interactive sessions and an insightful keynote, showcasing innovative research at the cutting-edge intersection of knowledge representation and conversational AI for advancing the future of recommender systems.

9:00 AM

Opening

9:15 AM

Content-based and Knowledge-aware RSs

Session Chair TBD

The Effect of Semantic Knowledge Graph Richness on Embedding Based Recommender Systems
Daan Di Scala, Xu Wang and Christopher Brewster
LONG 15min
Empowering shilling attacks with Katz and Exclusivity-based relatedness
Felice Antonio Merra, Vito Walter Anelli, Yashar Deldjoo, Tommaso Di Noia and Eugenio Di Sciascio
LONG 15min
Using Semantic-based Adaptive Relevance Prediction to Enhance Entity Recommendation for Personal Knowledge Assistance
Mahta Bakhshizadeh, Heiko Maus and Andreas Dengel
LONG 15min

10:00 AM

LLMs for Recommendation

Session Chair TBD

Can We Integrate Items Into Models? Knowledge Editing To Align LLMs With Product Catalogs
Ahmadou Wagne and Julia Neidhardt
SHORT 15min
Can LLMs reliably reason about user preferences for Recommendation?
Flavian Vasile
POSITION 15min

10:30 AM

Coffee Break

11:00 AM

Keynote: The Dagstuhl CAFE Framework for the Evaluation of Conversational Agents

Nicola Ferro

Conversational Agents (CA) as frontends to Information Retrieval (IR) and Recommender Systems (RS) become more popular in everyday life, with a wider range of users and usages. The latest developments in Large Language Models (LLMs) will have tremendous consequences, especially for the workplace and education. In this talk, the main outcomes of the Dagstuhl Perspectives Workshop 24352 "Conversational Agents: A Framework for Evaluation (CAFE)" will be reported. The workshop focused on the evaluation of conversational systems, as appropriate methods are still missing. The quality of these systems is limited in terms of personalization, veracity and correctness, bias, transparency, trustworthiness, and understandability. Thus, evaluation methods must address these shortcomings.

Nicola Ferro is Full Professor in Computer Science at the Department of Information Engineering at the University of Padua, Italy. His main research interests are information retrieval, data management and representation, and their evaluation. He chairs the Steering Committee of CLEF, the European evaluation initiative on multimodal and multilingual information access systems, and the Steering Committee of ESSIR, the European Summer School on Information Retrieval. He is Senior PC Member in top-tier conferences, like ECIR, ACM SIGIR, ACM CIKM, WSDM. He is General Co-Chair of SIGIR 2025. He was General Chair of ESSIR 2016 and Associate Editor for ACM TOIS. He was inducted into the SIGIR Academy in 2023.

11:40 AM

Conversational RSs

Session Chair TBD

Adapting Sequential Recommender Models to Content Recommendation in Chat Data using Non-Item Page-Models
Albin Zehe, Elisabeth Fischer, Jonas Kaiser, Toni Wagner and Andreas Hotho
LONG 15min
Conversational Recommender Systems based on Extracting Implicit Preferences with Large Language Models
Woo-Seok Kim, Wooseung Kang, Hye-Jin Jeong, Suwon Lee, Chie Hoon Song and Sang-Min Choi
SHORT 15min
A Social Robot as a Meal-Time Companion for Elderly People
Berardina De Carolis, Davide Di Pierro, Stefano Ferilli, Davide Lofrese, Corrado Loglisci and Giuseppe Palestra
SHORT 15min

12:25 PM

Closing