Tessera
Folgen

Paul Lerner

@lernerp.bsky.social

Postdoc @mlia_isir@sciences.re (Sorbonne Université, CNRS, ISIR) / Teacher @ aivancity / Teacher Assistant @ Sorbonne Université https://paullerner.github.io/

47 Posts50 Follower56 Folgt
Inria Paris NLP (ALMAnaCH team)@inriaparisnlp.bsky.social · 3mo ago

Parallel Corpora of Scholarly Documents for English-French Machine Translation Ziqian Peng, Lichao Zhu, Rachel Bawden, Maud Bénard, Éric de la Clergerie, Mathilde Huguin, Natalie Kübler, Paul Lerner, Alexandra Mestivier & François Yvon 📅 11th May | 16:30–16:54 | BUCC (remote)

MLIA ISIR@mlia-isir.bsky.social · 8mo ago

The team meeting of the week was presented by Alexandre Vérine, from PSL, about "Quality and Diversity in generative models through the lens of f-divergences." Thanks a lot for this interesting talk!

Bild
Paul Lerner@lernerp.bsky.social · 10mo ago

We find that LLMs translate some political parties unfairly using a new version of EuroParl, fully multi-parallel and including (political) metadata hal.science/hal-05328251

Assessing the Political Fairness of Multilingual LLMs: A Case Study based on a 21-way Multiparallel EuroParl Dataset

The political biases of Large Language Models (LLMs) are usually assessed by simulating their answers to English surveys. In this work, we propose an alternative framing of political biases, relying on principles of fairness in multilingual translation. We systematically compare the translation quality of speeches in the European Parliament (EP), observing systematic differences with majority parties from left, center, and right being better translated than outsider parties. This study is made possible by a new, 21-way multiparallel version of EuroParl, the parliamentary proceedings of the EP, which includes the political affiliations of each speaker. The dataset consists of 1.5M sentences for a total of 40M words and 249M characters. It covers three years, 1000+ speakers, 7 countries, 12 EU parties, 25 EU committees, and hundreds of national parties.

hal.science

Paul Lerner@lernerp.bsky.social · last yr.

Last week, I presented my work on "Assessing the Political Biases of Multilingual LLMs" at the EALM workshop @ TALN 2025 ! Thanks again to the ANR Diké project for organizing the workshop

Bild
MLIA ISIR@mlia-isir.bsky.social · last yr.

📢 🎉 The team has one paper accepted to #MTsummit2025! "Investigating Length Issues in Document-level Machine Translation" by @ziqianpeng.bsky.social, @rachelbawden.bsky.social and @yvofr.bsky.social in collaboration with @inriaparisnlp.bsky.social 📍 Geneva | 🗓️ 23-27,June 📕 arxiv.org/abs/2412.17592

Investigating Length Issues in Document-level Machine Translation

Transformer architectures are increasingly effective at processing and generating very long chunks of texts, opening new perspectives for document-level machine translation (MT). In this work, we chal...

arxiv.org

Paul Lerner@lernerp.bsky.social · last yr.

Am I the only reviewer that actually fills this "Reviewer Checklist"? And why do Area Chairs never answer when the paper needs to be desk-rejected? And reviews are due in 3 days 🫠

Yoav Goldberg@yoavgo.bsky.social · 2y ago

RL promises "systems that can adapt to their environment". However, no RL system that I know of actually fulfill anything close to this goal, and, furthermore, I'd argue that all the current RL methodologies are actively hostile to this goal. Prove me wrong.

Paul Lerner@lernerp.bsky.social · 2y ago

We offer a M2 internship on Visual Question Answering at LISN (Paris-Saclay University, co-supervised by Thomas Gerald, Sahar Ghannay, and Anne Vilnat) The goal is to create a dataset of questions for education (based on schoolbook content) Duration of 5 or 6 months (starting in March or April)