Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Beigi, Alimohammad"'
Model attribution for LLM-generated disinformation poses a significant challenge in understanding its origins and mitigating its spread. This task is especially challenging because modern large language models (LLMs) produce disinformation with human
Externí odkaz:
http://arxiv.org/abs/2407.21264
Autor:
Tan, Zhen, Li, Dawei, Wang, Song, Beigi, Alimohammad, Jiang, Bohan, Bhattacharjee, Amrita, Karami, Mansooreh, Li, Jundong, Cheng, Lu, Liu, Huan
Data annotation generally refers to the labeling or generating of raw data with relevant information, which could be used for improving the efficacy of machine learning models. The process, however, is labor-intensive and costly. The emergence of adv
Externí odkaz:
http://arxiv.org/abs/2402.13446