Can Generative Pre-trained Language Models Serve as Knowledge Bases for Closed-book QA?

2021/06/03 by Cunxiang Wang, Wang, Cunxiang, Pai Liu +3 · 3 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2106.01561

openalex publication_date 2021/06/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Recent work has investigated the interesting question using pre-trained language models (PLMs) as knowledge bases for answering open questions. However, existing work is limited in using small benchmarks with high test-train overlaps. We construct a new dataset of closed-book QA using SQuAD, and investigate the performance of BART. Experiments show that it is challenging for BART to remember training facts in high precision, and also challenging to answer closed-book questions even if relevant knowledge is retained. Some promising directions are found, including decoupling the knowledge memorizing process and the QA finetune process, forcing the model to recall relevant knowledge when question answering.

Cited by

• Adapting Small Language Models to Low-Resource Domains: A Case Study in Hindi Tourism QA
• Explaining Black-box Language Models with Knowledge Probing Systems: A Post-hoc Explanation Perspective
• Comparing Knowledge Injection Methods for LLMs in a Low-Resource Regime

Related

• Studying Strategically: Learning to Mask for Closed-book QA
• Language Models as Knowledge Bases?
• 60 Data Points are Sufficient to Fine-Tune LLMs for Question-Answering
• Context Generation Improves Open Domain Question Answering
• Instruction-tuned Language Models are Better Knowledge Learners