Jin Xu, Hongyu Lin, Xianpei Han, Lingyong Yan, Le Sun, Meng Liao, Boxi Cao, Tong Xue
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Previous literatures show that pre-trained masked language models (MLMs) such as BERT can achieve competitive factual knowledge extraction performance on some datasets, indicating that MLMs can potentially be a reliable knowledge source. In this paper, we conduct a rigorous study to explore the underlying predicting mechanisms of MLMs over different extraction paradigms. By investigating the behaviors of MLMs, we find that previous decent performance mainly owes to the biased prompts which overfit dataset artifacts. Furthermore, incorporating illustrative cases and external contexts improve knowledge prediction mainly due to entity type guidance and golden answer leakage. Our findings shed light on the underlying predicting mechanisms of MLMs, and strongly question the previous conclusion that current MLMs can potentially serve as reliable factual knowledge bases 1 .
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2106.09231")
get_code_for_paper("2106.09231")
have("2106.09231")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2106.09231.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2106.09231)
Connect an agent — have() is free.