Automated essay scoring

Benchmarks

Dataset Name	SOTA Method	Metric
ASAP 1.0 (test)		Prompt 1 QWK0.836	51	3mo ago
IELTS Writing Task 2	Llama-3.1-8B (4-LoRA)	Accuracy99.02	22	2mo ago
ELLIPSE		Quadratic Weighted Kappa0.72	14	1mo ago
ASAP Kaggle 2.0 (test)	Model 5 (Linguistic features)	QWK0.84	13	3mo ago
ASAP and ASAP++ (five-fold cross-validation)	TAPO	Score P10.73	11	8d ago
TCF generalization corpus	Simple Concatenation (SC)	Pearson Correlation (ρ)0.94	10	1d ago
ASAP++ full-data setting	DualBERT+LoRA+SA	Score P10.734	10	3mo ago
ASAP 2.0	TIDE	QWK49.51	7	15d ago
ArGPT	TIDE	QWK53.59	7	15d ago
CEAMC	TIDE	QWK45.64	7	15d ago
TOEFL	StruSim	Prompt 1 Score75.97	7	3mo ago
FCE (In-domain)	DistilBERT	RMSE2.08	6	8d ago
IELTS Task 2 (In-domain)	BERT	RMSE0.632	6	8d ago
ASAP++ 32-data setting (test)	DualBERT + LoRA + SA + UST	QWK (P1)0.635	6	3mo ago
ASAP++	TAPO	QWK0.726	5	8d ago
ASAP	TAPO	QWK0.743	5	8d ago
LAILA (cross-prompt)	TRATES	Relevance Score55.7	5	3mo ago
Feedback Prize (test)	TAPO	QWK (Cohesion)0.603	4	8d ago
ASAP Long Essays (Prompts 1, 2, 8)		Score (P1)83.6	4	3mo ago
FCE public (test)		Pearson's r79.6	4	3mo ago
LAILA	MAPLE	P1 Score0.537	3	1mo ago
ASAP		Score P10.659	3	1mo ago
ASAP 2.0 and ELLIPSE	Baseline (DeBERTa)	QWK0.792	3	3mo ago
ASAP Prompt 8 (val)		QWK0.779	2	1mo ago
ASAP Prompt 7 (All essays cross-validation)		QWK0.838	2	1mo ago

Showing 25 of 32 rows