10 papers
Semantic-Guided Reading Order Reconstruction in Historical Armenian Newspapers with LLMs
Chahan Vidal-Gorène, Nadi Tomeh, Victoria Khurshudyan
This paper addresses reading order reconstruction in historical Armenian newspapers, which combine complex layouts with limited language resources. We introduce a new annotated dat…
Diffusion-MF: Approximate Structured Diffusion for Sequence Labelling
Nicolas Floquet, Joseph Le Roux, Nadi Tomeh
We introduce Diffusion-MF, a discrete diffu- sion sequence labeller that places a linear-chain conditional random field (LCRF) inside the denoising loop. Unlike prior diffusion lab…
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…
ToMMeR -- Efficient Entity Mention Detection from Large Language Models
Victor Morand, Nadi Tomeh, Josiane Mothe +1
Identifying which text spans refer to entities - mention detection - is both foundational for information extraction and a known performance bottleneck. We introduce ToMMeR, a ligh…
Sparsity-Aware Evolution for Model Merging
Huan Zhang, Yanjian Zhang, Guillaume Wisniewski +2
We propose a sparsity-aware evolutionary (SAE) framework for model merging that involves iterative pruning-merging cycles to act as a novel mutation operator. We incorporate the sp…
Reasoning Strategies in Large Language Models: Can They Follow, Prefer, and Optimize?
Yanjian Zhang, Guillaume Wisniewski, Nadi Tomeh +1
Human reasoning involves different strategies, each suited to specific problems. Prior work shows that large language model (LLMs) tend to favor a single reasoning strategy, potent…