5 papers
The PLLuM Instruction Corpus
Piotr Pęzik, Filip Żarnecki, Konrad Kaczyński +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.…
Divide, Cache, Conquer: Dichotomic Prompting for Efficient Multi-Label LLM-Based Classification
Mikołaj Langner, Jan Eliasz, Ewa Rudnicka +1
We introduce a method for efficient multi-label text classification with large language models (LLMs), built on reformulating classification tasks as sequences of dichotomic (yes/n…
PLLuM: A Family of Polish Large Language Models
Jan Kocoń, 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…
LLMSQL: Upgrading WikiSQL for the LLM Era of Text-to-SQL
Dzmitry Pihulski, Karol Charchut, Viktoria Novogrodskaia +1
Converting natural language questions into SQL queries enables non-expert users to interact with relational databases and has long been a central task for natural language interfac…
Language, Culture, and Ideology: Personalizing Offensiveness Detection in Political Tweets with Reasoning LLMs
Dzmitry Pihulski, Jan Kocoń
We explore how large language models (LLMs) assess offensiveness in political discourse when prompted to adopt specific political and cultural perspectives. Using a multilingual su…