Pith. sign in

REVIEW 3 cited by

What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models

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 1907.13528 v2 pith:OXS46RLF submitted 2019-07-31 cs.CL cs.AI

classification cs.CLcs.AI
keywords languagediagnosticsmodelsbertpopularpre-trainingsuitewhat
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Pre-training by language modeling has become a popular and successful approach to NLP tasks, but we have yet to understand exactly what linguistic capacities these pre-training processes confer upon models. In this paper we introduce a suite of diagnostics drawn from human language experiments, which allow us to ask targeted questions about the information used by language models for generating predictions in context. As a case study, we apply these diagnostics to the popular BERT model, finding that it can generally distinguish good from bad completions involving shared category or role reversal, albeit with less sensitivity than humans, and it robustly retrieves noun hypernyms, but it struggles with challenging inferences and role-based event prediction -- and in particular, it shows clear insensitivity to the contextual impacts of negation.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Similarity Gates Approve Reversals: A Validity Audit of Embedding-Cosine Thresholds in Agent Systems

    cs.CL 2026-08 accept novelty 6.0 of 10

    Embedding-cosine thresholds used as meaning gates instead measure lexical overlap, so in the target cases of reversal-versus-paraphrase the gates fire backwards; a matched-pair audit reveals the regime.

  2. Evaluation Benchmarks and Learning Criteria for Discourse-Aware Sentence Representations

    cs.CL 2019-08 conditional novelty 6.0 of 10

    DiscoEval is a new benchmark for measuring discourse awareness in sentence embeddings, and Wikipedia-structure training losses modestly change, but do not beat, pretrained encoders.

  3. Does BERT agree? Evaluating knowledge of structure dependence through agreement relations

    cs.CL 2019-08 conditional novelty 6.0 of 10

    BERT achieves about 94% category-level accuracy on agreement relations across 26 languages and four agreement types, with modest declines as dependency distance and distractor count increase.

Pith tools