SOTAVerified

Linguistic Acceptability

Linguistic Acceptability is the task of determining whether a sentence is grammatical or ungrammatical.

Image Source: Warstadt et al

Papers

Showing 110 of 72 papers

TitleStatusHype
Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective0
Fietje: An open, efficient LLM for DutchCode2
Robust ASR Error Correction with Conservative Data Filtering0
Learning Phonotactics from Linguistic Informants0
MELA: Multilingual Evaluation of Linguistic AcceptabilityCode0
Not all layers are equally as important: Every Layer Counts BERT0
Data-Free Distillation of Language Model by Text-to-Text Transfer0
How well can machine-generated texts be identified and can language models be trained to avoid identification?0
JCoLA: Japanese Corpus of Linguistic AcceptabilityCode1
Defense of Adversarial Ranking Attack in Text Retrieval: Benchmark and Baseline via Detection0
Show:102550
← PrevPage 1 of 8Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1En-BERT + TDA + PCAAccuracy88.6Unverified
2BERT+TDAAccuracy88.2Unverified
3RoBERTa+TDAAccuracy87.3Unverified
4deberta-v3-base+tasksourceAccuracy87.15Unverified
5RoBERTa-large 355M + Entailment as Few-shot LearnerAccuracy86.4Unverified
6LTG-BERT-base 98MAccuracy82.7Unverified
7ELC-BERT-base 98MAccuracy82.6Unverified
8En-BERT + TDAAccuracy82.1Unverified
9FNet-LargeAccuracy78Unverified
10LTG-BERT-small 24MAccuracy77.6Unverified