How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysis
Shaobo Li, Xiaoguang Li, Lifeng Shang, Zhenhua Dong, Chengjie Sun, Bingquan Liu, Zhenzhou Ji, Xin Jiang, Qun Liu
Abstract
Recently, there has been a trend to investigate the factual knowledge captured by Pre-trained Language Models (PLMs). Many works show the PLMs’ ability to fill in the missing factual words in cloze-style prompts such as ”Dante was born in [MASK].” However, it is still a mystery how PLMs generate the results correctly: relying on effective clues or shortcut patterns? We try to answer this question by a causal-inspired analysis that quantitatively measures and evaluates the word-level patterns that PLMs depend on to generate the missing words. We check the words that have three typical associations with the missing words: knowledge-dependent, positionally close, and highly co-occurred. Our analysis shows: (1) PLMs generate the missing factual words more by the positionally close and highly co-occurred words than the knowledge-dependent words; (2) the dependence on the knowledge-dependent words is more effective than the positionally close and highly co-occurred words. Accordingly, we conclude that the PLMs capture the factual knowledge ineffectively because of depending on the inadequate associations.- Anthology ID:
- 2022.findings-acl.136
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2022
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1720–1732
- Language:
- URL:
- https://aclanthology.org/2022.findings-acl.136
- DOI:
- 10.18653/v1/2022.findings-acl.136
- Cite (ACL):
- Shaobo Li, Xiaoguang Li, Lifeng Shang, Zhenhua Dong, Chengjie Sun, Bingquan Liu, Zhenzhou Ji, Xin Jiang, and Qun Liu. 2022. How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysis. In Findings of the Association for Computational Linguistics: ACL 2022, pages 1720–1732, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysis (Li et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.findings-acl.136.pdf
- Data
- LAMA