Pith. sign in

REVIEW 1 cited by

Exploring BERT's Sensitivity to Lexical Cues using Tests from Semantic Priming

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2010.03010 v1 pith:SERBPOWQ submitted 2020-10-06 cs.CL

classification cs.CL
keywords contextwordbertpriminglexicalmodelsprobabilitiesrelated
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Models trained to estimate word probabilities in context have become ubiquitous in natural language processing. How do these models use lexical cues in context to inform their word probabilities? To answer this question, we present a case study analyzing the pre-trained BERT model with tests informed by semantic priming. Using English lexical stimuli that show priming in humans, we find that BERT too shows "priming," predicting a word with greater probability when the context includes a related word versus an unrelated one. This effect decreases as the amount of information provided by the context increases. Follow-up analysis shows BERT to be increasingly distracted by related prime words as context becomes more informative, assigning lower probabilities to related words. Our findings highlight the importance of considering contextual constraint effects when studying word prediction in these models, and highlight possible parallels with human processing.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Kernels of Selfhood: GPT-4o shows humanlike patterns of cognitive consistency moderated by free choice

    cs.CY 2025-01 conditional novelty 6.0 of 10

    GPT-4o's ratings of Putin moved toward the valence of an essay it wrote, and this shift grew when the model was given an illusory free choice about the essay.

Pith tools