4 citations · 7 across the 9 of their papers we have counts for
5 papers · 1 filter
Zebra: In-Context Generative Pretraining for Solving Parametric PDEs
Louis Serrano, Armand Kassaï Koupaï, Thomas X Wang +2
Solving time-dependent parametric partial differential equations (PDEs) is challenging for data-driven methods, as these models must adapt to variations in parameters such as coeff…
An Evaluation Framework for Attributed Information Retrieval using Large Language Models
Hanane Djeddal, Pierre Erbacher, Raouf Toukal +4
With the growing success of Large Language models (LLMs) in information-seeking scenarios, search engines are now adopting generative approaches to provide answers along with in-li…
ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training
Adel Nabli, Louis Fournier, Pierre Erbacher +3
Training LLMs relies on distributed implementations using multiple GPUs to compute gradients in parallel with sharded optimizers. However, synchronizing gradients in data parallel…
PAQA: Toward ProActive Open-Retrieval Question Answering
Pierre Erbacher, Jian-Yun Nie, Philippe Preux +1
Conversational systems have made significant progress in generating natural language responses. However, their potential as conversational search systems is currently limited due t…
Navigating Uncertainty: Optimizing API Dependency for Hallucination Reduction in Closed-Book Question Answering
Pierre Erbacher, Louis Falissar, Vincent Guigue +1
While Large Language Models (LLM) are able to accumulate and restore knowledge, they are still prone to hallucination. Especially when faced with factual questions, LLM cannot only…