Related papers: Prompting as Probing: Using Language Models for Knowledge Base Construction

Prompting as Probing: Using Language Models for Knowledge Base Construction

URL: http://arxiv.org/abs/2208.11057v3
Date: Mon, 19 Jun 2023 15:06:46 GMT
Title: Prompting as Probing: Using Language Models for Knowledge Base Construction
Authors: Dimitrios Alivanistos, Selene B\'aez Santamar\'ia, Michael Cochez, Jan-Christoph Kalo, Emile van Krieken, Thiviyan Thanapalasingam
Abstract summary: We present ProP (Prompting as Probing), which utilizes GPT-3, a large Language Model originally proposed by OpenAI in 2020. ProP implements a multi-step approach that combines a variety of prompting techniques to achieve this. Our evaluation study indicates that these proposed techniques can substantially enhance the quality of the final predictions.
Score: 1.6050172226234583
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Language Models (LMs) have proven to be useful in various downstream applications, such as summarisation, translation, question answering and text classification. LMs are becoming increasingly important tools in Artificial Intelligence, because of the vast quantity of information they can store. In this work, we present ProP (Prompting as Probing), which utilizes GPT-3, a large Language Model originally proposed by OpenAI in 2020, to perform the task of Knowledge Base Construction (KBC). ProP implements a multi-step approach that combines a variety of prompting techniques to achieve this. Our results show that manual prompt curation is essential, that the LM must be encouraged to give answer sets of variable lengths, in particular including empty answer sets, that true/false questions are a useful device to increase precision on suggestions generated by the LM, that the size of the LM is a crucial factor, and that a dictionary of entity aliases improves the LM score. Our evaluation study indicates that these proposed techniques can substantially enhance the quality of the final predictions: ProP won track 2 of the LM-KBC competition, outperforming the baseline by 36.4 percentage points. Our implementation is available on https://github.com/HEmile/iswc-challenge.