CLMar 31, 2022

How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysis

arXiv:2203.16747v1657 citations
Originality Incremental advance
AI Analysis

This addresses the problem of understanding PLM behavior for researchers in NLP, revealing limitations in factual knowledge acquisition, though it is incremental in analysis.

The paper investigates how pre-trained language models (PLMs) capture factual knowledge, finding that they rely more on positional and co-occurrence patterns than knowledge-dependent words, leading to ineffective knowledge capture.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes