Výsledky vyhledávání

The increasing capabilities of large generative models and their ever more widespread deployment have raised concerns about their reliability, safety, and potential misuse. To address these issues, recent works have proposed to control model generati

Externí odkaz: http://arxiv.org/abs/2410.23054

Zobrazit plný text záznamu

Akademický článek

Stealing Air and Land – The Politics of Translating Global Environmental Governance in Suau, Papua New Guinea

Autor: Sophie Pascoe

Publikováno v: Conservation & Society, Vol 19, Iss 1, Pp 34-43 (2021)

Global environmental governance today is grounded in a set of ontological assumptions that involve measurement and commodification of carbon emissions as tradeable units between countries for mitigating climate change and preventing deforestation. Th

Externí odkaz: https://doaj.org/article/9b6b3a2899fd41268b63a809492c4f38

Zobrazit plný text záznamu

Report

Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models

Autor: Suau, Xavier, Delobelle, Pieter, Metcalf, Katherine, Joulin, Armand, Apostoloff, Nicholas, Zappella, Luca, Rodríguez, Pau

An important issue with Large Language Models (LLMs) is their undesired ability to generate toxic language. In this work, we show that the neurons responsible for toxicity can be determined by their power to discriminate toxic sentences, and that tox

Externí odkaz: http://arxiv.org/abs/2407.12824

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání