Dated Data: Tracing Knowledge Cutoffs in Large Language Models

arXiv:2403.12958v1 Announce Type: new
Abstract: Released Large Language Models (LLMs) are often paired with a claimed knowledge cutoff date, or the dates at which training data was gathered. Such information is crucial for applications where the LLM must provide up to date information. However, this statement only scratches the surface: do all resources in the training data share the same knowledge cutoff date? Does the model's demonstrated knowledge for these subsets closely align to their cutoff dates? In this work, …

abstract applications arxiv cs.cl data however information knowledge language language models large language large language models llm llms surface tracing training training data type up to date