Výsledky vyhledávání - "Morabito, Robert"

Report

STOP! Benchmarking Large Language Models with Sensitivity Testing on Offensive Progressions

Autor: Morabito, Robert, Madhusudan, Sangmitra, McDonald, Tyler, Emami, Ali

Mitigating explicit and implicit biases in Large Language Models (LLMs) has become a critical focus in the field of natural language processing. However, many current methodologies evaluate scenarios in isolation, without considering the broader cont

Externí odkaz: http://arxiv.org/abs/2409.13843

Zobrazit plný text záznamu

Report

Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models

Autor: Kumar, Abhishek, Morabito, Robert, Umbet, Sanzhar, Kabbara, Jad, Emami, Ali

As the use of Large Language Models (LLMs) becomes more widespread, understanding their self-evaluation of confidence in generated responses becomes increasingly important as it is integral to the reliability of the output of these models. We introdu

Externí odkaz: http://arxiv.org/abs/2405.16282

Zobrazit plný text záznamu

Report

Debiasing should be Good and Bad: Measuring the Consistency of Debiasing Techniques in Language Models

Autor: Morabito, Robert, Kabbara, Jad, Emami, Ali

Debiasing methods that seek to mitigate the tendency of Language Models (LMs) to occasionally output toxic or inappropriate text have recently gained traction. In this paper, we propose a standardized protocol which distinguishes methods that yield n

Externí odkaz: http://arxiv.org/abs/2305.14307

Zobrazit plný text záznamu