4 papers
Walk&Retrieve: Simple Yet Effective Zero-shot Retrieval-Augmented Generation via Knowledge Graph Walks
Martin Böckling, Heiko Paulheim, Andreea Iana
Large Language Models (LLMs) have showcased impressive reasoning abilities, but often suffer from hallucinations or outdated knowledge. Knowledge Graph (KG)-based Retrieval-Augment…
News Without Borders: Domain Adaptation of Multilingual Sentence Embeddings for Cross-lingual News Recommendation
Andreea Iana, Fabian David Schmidt, Goran Glavaš +1
Rapidly growing numbers of multilingual news consumers pose an increasing challenge to news recommender systems in terms of providing customized recommendations. First, existing ne…
Peeling Back the Layers: An In-Depth Evaluation of Encoder Architectures in Neural News Recommenders
Andreea Iana, Goran Glavaš, Heiko Paulheim
Encoder architectures play a pivotal role in neural news recommenders by embedding the semantic and contextual information of news and users. Thus, research has heavily focused on…
Train Once, Use Flexibly: A Modular Framework for Multi-Aspect Neural News Recommendation
Andreea Iana, Goran Glavaš, Heiko Paulheim
Recent neural news recommenders (NNRs) extend content-based recommendation (1) by aligning additional aspects (e.g., topic, sentiment) between candidate news and user history or (2…