Members

ola
Aleksandra Piktus

Aleksandra is a PhD student in Data Science at Sapienza University. Her interests include Natural Language Processing and Information Retrieval. Aside from the PhD, she currently works as a research engineer at Cohere, specializing in retrieval augmentation for large language models. Before that he was a member of the science team at HuggingFace. Previously, Aleksandra worked at the Facebook AI Research lab in London, where she carried out research into knowledge-intensive NLP. Before that, she worked on reducing the spread of misinformation on the Facebook platform and on Facebook Search.
AleksandraPiktus.png

Improving wikipedia verifiability with AI
Petroni, Fabio; Broscheit, Samuel; Piktus, Aleksandra; Lewis, Patrick; Izacard, Gautier; Hosseini, Lucas; Dwivedi-Yu, Jane; Lomeli, Maria; Schick, Timo; Bevilacqua, Michele;
2023
The ROOTS Search Tool: Data Transparency for LLMs
Piktus, Aleksandra; Akiki, Christopher; Villegas, Paulo; Laurençon, Hugo; Dupont, Gérard; Luccioni, Alexandra Sasha; Jernite, Yacine; Rogers, Anna;
2023
GAIA Search: Hugging Face and Pyserini Interoperability for NLP Training Data Exploration
Piktus, Aleksandra; Ogundepo, Odunayo; Akiki, Christopher; Oladipo, Akintunde; Zhang, Xinyu; Schoelkopf, Hailey; Biderman, Stella; Potthast, Martin; Lin, Jimmy;
2023
Scaling Data-Constrained Language Models
Muennighoff, Niklas; Rush, Alexander M; Barak, Boaz; Scao, Teven Le; Piktus, Aleksandra; Tazi, Nouamane; Pyysalo, Sampo; Wolf, Thomas; Raffel, Colin;
2023
Spacerini: Plug-and-play Search Engines with Pyserini and Hugging Face
Akiki, Christopher; Ogundepo, Odunayo; Piktus, Aleksandra; Zhang, Xinyu; Oladipo, Akintunde; Lin, Jimmy; Potthast, Martin;
2023
FinGPT: Large Generative Models for a Small Language
Luukkonen, Risto; Komulainen, Ville; Luoma, Jouni; Eskelinen, Anni; Kanerva, Jenna; Kupari, Hanna-Mari; Ginter, Filip; Laippala, Veronika; Muennighoff, Niklas; Piktus, Aleksandra;
2023

Want to print your doc?
This is not the way.
Try clicking the ⋯ next to your doc name or using a keyboard shortcut (
CtrlP
) instead.