Pierre Colombo

BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation

arXiv 2026

Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document Embeddings

arXiv 2025

Should We Still Pretrain Encoders with Masked Language Modeling?

arXiv 2025

Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs

arXiv 2024

Towards Trustworthy Reranking: A Simple yet Effective Abstention Mechanism

arXiv 2024

CroissantLLM: A Truly Bilingual French-English Language Model

arXiv 2024

Hallucinations in Large Multilingual Translation Models

arXiv 2023

Revisiting Instruction Fine-tuned Model Evaluation to Guide Industrial Applications

arXiv 2023

Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation

COLING 2022 10

What are the best systems? New perspectives on NLP Benchmarking

arXiv 2022

NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation

arXiv 2021

Céline Hudelot

Manuel Faysse

Nicolas Boizard

André F. T. Martins

Emmanuel Malherbe

Gautier Viaud

Hippolyte Gisserot-Boukhlef

Duarte M. Alves

Nuno M. Guerreiro

A Tabassum