A Little Leak Will Sink a Great Ship: Survey of Transparency for Large Language Models from Start to Finish

arXiv:2403.16139v1 Announce Type: new
Abstract: Large Language Models (LLMs) are trained on massive web-crawled corpora. This poses risks of leakage, including personal information, copyrighted texts, and benchmark datasets. Such leakage leads to undermining human trust in AI due to potential unauthorized generation of content or overestimation of performance. We establish the following three criteria concerning the leakage issues: (1) leakage rate: the proportion of leaked data in training data, (2) output rate: the ease of generating leaked data, and (3) …

abstract arxiv benchmark cs.cl datasets human information language language models large language large language models leads leak llms massive personal information risks ship survey transparency trust type web will