4 papers
The PLLuM Instruction Corpus
Piotr PÄzik, Filip Å»arnecki, Konrad KaczyÅski +50
This paper describes the instruction dataset used to fine-tune a set of transformer-based large language models (LLMs) developed in the PLLuM (Polish Large Language Model) project.…
PLLuM: A Family of Polish Large Language Models
Jan KocoÅ, Maciej Piasecki, Arkadiusz Janz +96
Large Language Models (LLMs) play a central role in modern artificial intelligence, yet their development has been primarily focused on English, resulting in limited support for ot…
OBSR: Open Benchmark for Spatial Representations
Julia Moska, Oleksii Furman, Kacper Kozaczko +4
GeoAI is evolving rapidly, fueled by diverse geospatial datasets like traffic patterns, environmental data, and crowdsourced OpenStreetMap (OSM) information. While sophisticated AI…
Rethinking the Evaluation of Alignment Methods: Insights into Diversity, Generalisation, and Safety
Denis Janiak, Julia Moska, Dawid Motyka +4
Large language models (LLMs) require careful alignment to balance competing objectives - factuality, safety, conciseness, proactivity, and diversity. Existing studies focus on indi…