# Pre-training Language Models with Deterministic Factual Knowledge

arXiv: https://arxiv.org/abs/2210.11165 · HTML: https://mlsanity.com/paper/2210.11165/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 41 references that are in the map.
- First posted on arXiv 20 Oct 2022.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [Measuring and Improving Consistency in Pretrained Language Models](https://mlsanity.com/paper/2102.01017/) (2021)
- [ERNIE: Enhanced Representation through Knowledge Integration](https://mlsanity.com/paper/1904.09223/) (2019)
- [Factual Probing Is [MASK]: Learning vs. Learning to Recall](https://mlsanity.com/paper/2104.05240/) (2021)
- [The Lottery Ticket Hypothesis for Pre-trained BERT Networks](https://mlsanity.com/paper/2007.12223/) (2020)
- [MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension](https://mlsanity.com/paper/1910.09753/) (2019)
- [Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets](https://mlsanity.com/paper/2008.02637/) (2020)
- [Learning a Deep ConvNet for Multi-label Classification with Partial Labels](https://mlsanity.com/paper/1902.09720/) (2019)
- [Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases](https://mlsanity.com/paper/2106.09231/) (2021)
- [Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model](https://mlsanity.com/paper/1912.09637/) (2019)
- [E-BERT: Efficient-Yet-Effective Entity Embeddings for BERT](https://mlsanity.com/paper/1911.03681/) (2019)
- [Multi-Label Learning from Single Positive Labels](https://mlsanity.com/paper/2106.09708/) (2021)
- [ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning](https://mlsanity.com/paper/2012.15022/) (2020)
- [Few-Shot Question Answering by Pretraining Span Selection](https://mlsanity.com/paper/2101.00438/) (2021)
- [Can Generative Pre-trained Language Models Serve as Knowledge Bases for Closed-book QA?](https://mlsanity.com/paper/2106.01561/) (2021)
- [REL: An Entity Linker Standing on the Shoulders of Giants](https://mlsanity.com/paper/2006.01969/) (2020)
- [PMI-Masking: Principled masking of correlated spans](https://mlsanity.com/paper/2010.01825/) (2020)
- [KgPLM: Knowledge-guided Language Model Pre-training via Generative and Discriminative Learning](https://mlsanity.com/paper/2012.03551/) (2020)

## Built on by (most cited first, 4 of 4)

- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [FactKB: Generalizable Factuality Evaluation using Language Models Enhanced with Factual Knowledge](https://mlsanity.com/paper/2305.08281/) (2023)
- [Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE](https://mlsanity.com/paper/2212.01853/) (2022)
- [Self-Evolution Learning for Discriminative Language Model Pretraining](https://mlsanity.com/paper/2305.15275/) (2023)

## Abstract (arXiv)

Previous works show that Pre-trained Language Models (PLMs) can capture factual knowledge. However, some analyses reveal that PLMs fail to perform it robustly, e.g., being sensitive to the changes of prompts when extracting factual knowledge. To mitigate this issue, we propose to let PLMs learn the deterministic relationship between the remaining context and the masked content. The deterministic relationship ensures that the masked factual content can be deterministically inferable based on the existing clues in the context. That would provide more stable patterns for PLMs to capture factual knowledge than randomly masking. Two pre-training tasks are further introduced to motivate PLMs to rely on the deterministic relationship when filling masks. Specifically, we use an external Knowledge Base (KB) to identify deterministic relationships and continuously pre-train PLMs with the proposed methods. The factual knowledge probing experiments indicate that the continuously pre-trained PLMs achieve better robustness in factual knowledge capturing. Further experiments on question-answering datasets show that trying to learn a deterministic relationship with the proposed methods can also help other knowledge-intensive tasks.