collaborators

6 papers

cs.CL2026

Are We Evaluating Knowledge or Phrasing? Mitigating MCQA Sensitivity with ParaEval

João Maria Janeiro, Mathurin Videau, Andrea Caciolai +3

Multiple-choice (MCQA) benchmarks are the standard for evaluating pretrained large language models, but their reliance on log-likelihood scoring makes them unreliable. Specifically…

cs.IR2026

STORM: Stepwise Token Optimization with Reward-Guided Beam Search

Arthur Satouf, Giulio D'Erasmo, Yuxuan Zong +3

Modern retrieval increasingly relies on dense and learned-sparse neural models that are effective but require encoding the entire corpus into a specialized index, rebuilt whenever…

cs.CL2026

Give it Space! Explicit Disentangling of Positional and Semantic Representations in Encoders

Pierre-Antoine Lequeu, Camille Barboule, Benjamin Piwowarski

Positional encoding (PE) underpins how permutation-invariant Transformers represent sequence order, yet how positional information is processed and stored remains poorly understood…

cs.IR2026

A Voronoi Cell Formulation for Principled Token Pruning in Late-Interaction Retrieval Models

Yash Kankanampati, Yuxuan Zong, Nadi Tomeh +2

Late-interaction models such as ColBERT offer competitive performance across various retrieval tasks but require storing a dense embedding for each document token, leading to a sub…

cs.CL2025

Survey on Question Answering over Visually Rich Documents: Methods, Challenges, and Trends

Camille Barboule, Benjamin Piwowarski, Yoan Chabot

The field of visually-rich document understanding, which involves interacting with visually-rich documents (whether scanned or born-digital), is rapidly evolving and still lacks co…

cs.CL2025

Structural Deep Encoding for Table Question Answering

Raphaël Mouravieff, Benjamin Piwowarski, Sylvain Lamprier

Although Transformers-based architectures excel at processing textual information, their naive adaptation for tabular data often involves flattening the table structure. This simpl…