Package: FMAT 2026.1

FMAT: The Fill-Mask Association Test

The Fill-Mask Association Test ('FMAT') <doi:10.1037/pspa0000396> is an integrative, probability-based social computing method using Masked Language Models to measure conceptual associations (e.g., attitudes, biases, stereotypes, social norms, cultural values) as propositional semantic representations in natural language. Supported language models include 'BERT' <doi:10.48550/arXiv.1810.04805> and its variants available at 'Hugging Face' <https://huggingface.co/models?pipeline_tag=fill-mask>. Methodological references and installation guidance are provided at <https://psychbruce.github.io/FMAT/>.

Authors:Han Wu Shuang Bao [aut, cre]

FMAT_2026.1.tar.gz
FMAT_2026.1.zip(r-4.7-any)FMAT_2026.1.zip(r-4.6-any)FMAT_2026.1.zip(r-4.5-any)
FMAT_2026.1.tgz(r-4.6-any)FMAT_2026.1.tgz(r-4.5-any)
FMAT_2026.1.tar.gz(r-4.7-any)FMAT_2026.1.tar.gz(r-4.6-any)
FMAT_2026.1.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
FMAT/json (API)

# Install 'FMAT' in R:

install.packages('FMAT', repos = c('https://psychbruce.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/psychbruce/fmat/issues

Pkgdown/docs site:https://psychbruce.github.io

On CRAN:

ai artificial-intelligence bert bert-model bert-models contextualized-representation fill-in-the-blank fill-mask huggingface language-model language-models large-language-models masked-language-models natural-language-processing natural-language-understanding nlp pretrained-models transformer transformers

4.51 score 16 stars 7 scripts 465 downloads 16 exports 49 dependencies

Last updated from:4341b67f87. Checks:9 OK. Indexed: yes.

Target	Result	Time
linux-devel	OK	182
source / vignettes	OK	256
linux-release	OK	177
macos-release	OK	94
macos-oldrel	OK	112
windows-devel	OK	95
windows-release	OK	91
windows-oldrel	OK	104
wasm-release	OK	159

Exports:.BERT_download BERT_info BERT_info_date BERT_remove BERT_vocab fill_mask fill_mask_check FMAT_query FMAT_query_bind FMAT_run ICC_models LPR_reliability set_cache_folder special_case weight_decay

Dependencies:askpass cli cpp11 crayon curl data.table dplyr forcats generics glue GPArotation here httr irr jsonlite lattice lifecycle lpSolve magrittr Matrix mime mnormt nlme openssl pillar pkgconfig plyr png psych purrr R6 rappdirs Rcpp RcppTOML reticulate rlang rprojroot rvest selectr stringi stringr sys tibble tidyr tidyselect utf8 vctrs withr xml2

Citation

Development and contributors

Readme and manuals

Help Manual

Help page	Topics
Download and save BERT models to local cache folder.	BERT_download
Get basic information of BERT models.	BERT_info
Scrape the initial commit date of BERT models.	BERT_info_date
Remove BERT models from local cache folder.	BERT_remove
Check if mask words are in the model vocabulary.	BERT_vocab
Run the fill-mask pipeline and check the raw results.	fill_mask fill_mask_check
Prepare a data.table of queries and variables for the FMAT.	FMAT_query
Combine multiple query data.tables and renumber query ids.	FMAT_query_bind
Run the fill-mask pipeline on multiple models (CPU / GPU).	FMAT_run
Intraclass correlation coefficient (ICC) of BERT models.	ICC_models
Reliability analysis (Cronbach's alpha) of LPR.	LPR_reliability
Set (change) HuggingFace cache folder temporarily.	set_cache_folder
Specify models that require special treatment to ensure accuracy.	special_case
[S3 method] Summarize the results for the FMAT.	summary.fmat
Compute a vector of weights with a decay rate.	weight_decay