Papers › Language Models Use Monotonicity to Assess NPI Licensing

Language Models Use Monotonicity to Assess NPI Licensing

28 May 2021Findings (ACL) 2021 8arXiv:2105.13818archive 2025-07-28

Jaap Jumelet, Milica Denić, Jakub Szymanik, Dieuwke Hupkes, Shane Steinert-Threlkeld

We investigate the semantic knowledge of language models (LMs), focusing on (1) whether these LMs create categories of linguistic environments based on their semantic monotonicity properties, and (2) whether these categories play a similar role in LMs as in human language understanding, using negative polarity item licensing as a case study. We introduce a series of experiments consisting of probing with diagnostic classifiers (DCs), linguistic acceptability tasks, as well as a novel DC ranking method that tightly connects the probing results to the inner workings of the LM. By applying our experimental pipeline to LMs trained on various filtered corpora, we are able to gain stronger insights into the semantic generalizations that are acquired by these models.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

jumelet/monotonicity-npi-lm officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DiagnosticLinguistic Acceptability

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections