5 papers
Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training
Michal Chudoba, Sergey Alyaev, Petra Galuscakova +1
There are two main Parameter-Efficient Fine-Tuning (PEFT) techniques for Large Language Models (LLMs). While Low-Rank Adaptation (LoRA) introduces additional weights between the LL…
A Reproducibility Study of Metacognitive Retrieval-Augmented Generation
Gabriel Iturra-Bocaz, Petra Galuscakova
Recently, Retrieval Augmented Generation (RAG) has shifted focus to multi-retrieval approaches to tackle complex tasks such as multi-hop question answering. However, these systems…
LongEval at CLEF 2025: Longitudinal Evaluation of IR Systems on Web and Scientific Data
Matteo Cancellieri, Alaa El-Ebshihy, Tobias Fink +11
The LongEval lab focuses on the evaluation of information retrieval systems over time. Two datasets are provided that capture evolving search scenarios with changing documents, que…
Navigating Speech Recording Collections with AI-Generated Illustrations
Sirina HÃ¥land, Trond Karlsen Strøm, Petra GaluÅ¡Äáková
Although the amount of available spoken content is steadily increasing, extracting information and knowledge from speech recordings remains challenging. Beyond enhancing traditiona…
Impact of Shallow vs. Deep Relevance Judgments on BERT-based Reranking Models
Gabriel Iturra-Bocaz, Danny Vo, Petra Galuscakova
This paper investigates the impact of shallow versus deep relevance judgments on the performance of BERT-based reranking models in neural Information Retrieval. Shallow-judged data…