Articles tagged with
research

07 Mar 2025

How to create a synthetic annotator? The process of developing a domain-specific LLM-as-a-Judge.

In this blogpost we want to introduce the topic of using a Large Language Model (LLM) as an evaluator — a novel approach to tackling the complexities of evaluating advanced machine learning systems, particularly in tasks like Automatic Summarization, Text Generation, and Machine Translation, where traditional metrics struggle to capture nuances like cross-lingual accuracy and bias detection.

Zuzanna Rękawek, Agata Hajduk-Smak

---

18 Apr 2023

Trust no one, not even your training data! Machine learning from noisy data

Label noise is ever-present in machine learning practice. Allegro datasets are no exception. We compared 7 methods for training classifiers robust to label noise. All of them improved the model’s performance on noisy datasets. Some of the methods decreased the model’s performance in the absence of label noise.

Alicja Rączkowska, Aleksandra Osowska-Kurczab, Jacek Szczerbiński, Klaudia Nazarko, Kalina Kobus

---

14 Apr 2022

Turn-Based Offline Reinforcement Learning

This blogpost is the result of a research collaboration between the Allegro Machine Learning Research team and the Institute of Mathematics of the Polish Academy of Sciences (IMPAN), Warsaw.

Riccardo Belluzzo, Tomasz Bocheński, Michał Zając, Łukasz Kuciński, Piotr Miłoś