Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Bhan, Milan"'
Autor:
Bhan, Milan, Vittaut, Jean-Noel, Achache, Nina, Legrand, Victor, Chesneau, Nicolas, Blangero, Annabelle, Murris, Juliette, Lesot, Marie-Jeanne
Toxicity mitigation consists in rephrasing text in order to remove offensive or harmful meaning. Neural natural language processing (NLP) models have been widely used to target and mitigate textual toxicity. However, existing methods fail to detoxify
Externí odkaz:
http://arxiv.org/abs/2405.09948
Incorporating natural language rationales in the prompt and In-Context Learning (ICL) have led to a significant improvement of Large Language Models (LLMs) performance. However, generating high-quality rationales require human-annotation or the use o
Externí odkaz:
http://arxiv.org/abs/2402.12038
Counterfactual examples explain a prediction by highlighting changes of instance that flip the outcome of a classifier. This paper proposes TIGTEC, an efficient and modular method for generating sparse, plausible and diverse counterfactual explanatio
Externí odkaz:
http://arxiv.org/abs/2304.12425
Attention mechanisms have played a crucial role in the development of complex architectures such as Transformers in natural language processing. However, Transformers remain hard to interpret and are considered as black-boxes. This paper aims to asse
Externí odkaz:
http://arxiv.org/abs/2303.15190