Zobrazeno 1 - 10
of 132
pro vyhledávání: '"Gaussier, Éric"'
Autor:
Zablocki, Éloi, Gerard, Valentin, Cardiel, Amaia, Gaussier, Eric, Cord, Matthieu, Valle, Eduardo
Understanding deep models is crucial for deploying them in safety-critical applications. We introduce GIFT, a framework for deriving post-hoc, global, interpretable, and faithful textual explanations for vision classifiers. GIFT starts from local fai
Externí odkaz:
http://arxiv.org/abs/2411.15605
The rapid development of large language models (LLMs) like Llama has significantly advanced information retrieval (IR) systems. However, using LLMs for long documents, as in RankLLaMA, remains challenging due to computational complexity, especially c
Externí odkaz:
http://arxiv.org/abs/2411.06254
Tree-based ensemble methods such as random forests, gradient-boosted trees, and Bayesianadditive regression trees have been successfully used for regression problems in many applicationsand research studies. In this paper, we study ensemble versions
Externí odkaz:
http://arxiv.org/abs/2406.14033
Autor:
Li, Minghan, Gaussier, Eric
Recent studies have demonstrated that the ability of dense retrieval models to generalize to target domains with different distributions is limited, which contrasts with the results obtained with interaction-based models. Prior attempts to mitigate t
Externí odkaz:
http://arxiv.org/abs/2403.08970
This paper introduces a new structural causal model tailored for representing threshold-based IT systems and presents a new algorithm designed to rapidly detect root causes of anomalies in such systems. When root causes are not causally related, the
Externí odkaz:
http://arxiv.org/abs/2402.06500
We study the problem of identifiability of the total effect of an intervention from observational time series in the situation, common in practice, where one only has access to abstractions of the true causal graph. We consider here two abstractions:
Externí odkaz:
http://arxiv.org/abs/2310.14691
Autor:
Aït-Bachir, Ali, Assaad, Charles K., de Bignicourt, Christophe, Devijver, Emilie, Ferreira, Simon, Gaussier, Eric, Mohanna, Hosein, Zan, Lei
Information technology (IT) systems are vital for modern businesses, handling data storage, communication, and process automation. Monitoring these systems is crucial for their proper functioning and efficiency, as it allows collecting extensive obse
Externí odkaz:
http://arxiv.org/abs/2307.15678
Autor:
Bystrova, Daria, Assaad, Charles K., Arbel, Julyan, Devijver, Emilie, Gaussier, Eric, Thuiller, Wilfried
Constraint-based methods and noise-based methods are two distinct families of methods proposed for uncovering causal graphs from observational data. However, both operate under strong assumptions that may be challenging to validate or could be violat
Externí odkaz:
http://arxiv.org/abs/2306.08765
Autor:
Li, Minghan, Gaussier, Eric
Although neural information retrieval has witnessed great improvements, recent works showed that the generalization ability of dense retrieval models on target domains with different distributions is limited, which contrasts with the results obtained
Externí odkaz:
http://arxiv.org/abs/2212.06552