Type: Package Package: pangoling Title: Access to Large Language Model Predictions Version: 1.0.3 Authors@R: c( person("Bruno", "Nicenboim", , "b.nicenboim@tilburguniversity.edu", role = c("aut", "cre"), comment = c(ORCID = "0000-0002-5176-3943")), person("Chris", "Emmerly", role = "ctb"), person("Giovanni", "Cassani", role = "ctb"), person("Lisa", "Levinson", role = "rev"), person("Utku", "Turk", role = "rev") ) Description: Provides access to word predictability estimates using large language models (LLMs) based on 'transformer' architectures via integration with the 'Hugging Face' ecosystem . The package interfaces with pre-trained neural networks and supports both causal/auto-regressive LLMs (e.g., 'GPT-2') and masked/bidirectional LLMs (e.g., 'BERT') to compute the probability of words, phrases, or tokens given their linguistic context. For details on GPT-2 and causal models, see Radford et al. (2019) , for details on BERT and masked models, see Devlin et al. (2019) . By enabling a straightforward estimation of word predictability, the package facilitates research in psycholinguistics, computational linguistics, and natural language processing (NLP). License: MIT + file LICENSE URL: https://docs.ropensci.org/pangoling/, https://github.com/ropensci/pangoling BugReports: https://github.com/ropensci/pangoling/issues Depends: R (>= 4.1.0) Imports: cachem, data.table, memoise, reticulate, rstudioapi, stats, tidyselect, tidytable (>= 0.7.2), utils Suggests: brms, knitr, parallel, rmarkdown, spelling, testthat (>= 3.0.0), tictoc, covr Config/testthat/edition: 3 Encoding: UTF-8 Language: en-US LazyData: true Roxygen: list(markdown = TRUE) RoxygenNote: 7.3.1 StagedInstall: yes VignetteBuilder: knitr Config/pak/sysreqs: libpng-dev python3 Repository: https://ropensci.r-universe.dev Date/Publication: 2026-01-13 15:59:45 UTC RemoteUrl: https://github.com/ropensci/pangoling RemoteRef: main RemoteSha: 39916805ecb60c144f6a3bc531bfb7ff539f32d8 NeedsCompilation: no Packaged: 2026-07-01 08:16:06 UTC; root Author: Bruno Nicenboim [aut, cre] (ORCID: ), Chris Emmerly [ctb], Giovanni Cassani [ctb], Lisa Levinson [rev], Utku Turk [rev] Maintainer: Bruno Nicenboim