How Much Knowledge Can You Pack Into the Parameters of a Language Model?
This work addresses the problem of knowledge storage in AI for researchers and practitioners, demonstrating a practical approach that is incremental but offers strong performance gains.
The paper investigates the capacity of language models to store and retrieve knowledge by fine-tuning pre-trained models to answer questions without external context, showing that performance scales with model size and is competitive with open-domain retrieval systems.
It has recently been observed that neural language models trained on unstructured text can implicitly store and retrieve knowledge using natural language queries. In this short paper, we measure the practical utility of this approach by fine-tuning pre-trained models to answer questions without access to any external context or knowledge. We show that this approach scales with model size and performs competitively with open-domain systems that explicitly retrieve answers from an external knowledge source when answering questions. To facilitate reproducibility and future work, we release our code and trained models at https://goo.gle/t5-cbqa.