The Queen of England is not England's Queen: On the Lack of Factual Coherency in PLMs
This addresses the problem of unreliable knowledge retrieval in PLMs for AI researchers, highlighting an incremental limitation in their use as knowledge bases.
The study investigated the coherency of factual knowledge in Pre-trained Language Models (PLMs), finding that they have low coherency in predicting subject entities from object entities, but including evidence paragraphs leads to substantial improvement.
Factual knowledge encoded in Pre-trained Language Models (PLMs) enriches their representations and justifies their use as knowledge bases. Previous work has focused on probing PLMs for factual knowledge by measuring how often they can correctly predict an object entity given a subject and a relation, and improving fact retrieval by optimizing the prompts used for querying PLMs. In this work, we consider a complementary aspect, namely the coherency of factual knowledge in PLMs, i.e., how often can PLMs predict the subject entity given its initial prediction of the object entity. This goes beyond evaluating how much PLMs know, and focuses on the internal state of knowledge inside them. Our results indicate that PLMs have low coherency using manually written, optimized and paraphrased prompts, but including an evidence paragraph leads to substantial improvement. This shows that PLMs fail to model inverse relations and need further enhancements to be able to handle retrieving facts from their parameters in a coherent manner, and to be considered as knowledge bases.