Natural language generation

Benchmarks

Dataset Name	SOTA Method	Metric
E2E (test)	FAA	ROUGE-L89.94	79	4d ago
E2E NLG Challenge	Dual LoRA (r = 4)	BLEU70.6	58	4d ago
SGD (test)	T2G2	BLEU28.6	18	4d ago
WebNLG unseen categories	Adapter_L	BLEU49.8	17	4d ago
WebNLG all categories (test)	HiddenKey	BLEU55.27	13	4d ago
PTB-XL (test)	LLaMA-3-Instruct	BLEU-10.539	12	4d ago
MIMIC-IV-ECG (test)	LLaMA-3-Instruct	BLEU-10.733	12	4d ago
ToDs benchmark GPT-2 backbone (test)		EER3.42	11	4d ago
Flores-101	Embed FT	spBLEU31.4	11	4d ago
WebNLG	LoRA	BLEU55.3	11	4d ago
WebNLG all categories	Adapter_H	BLEU57.7	11	4d ago
WebNLG seen categories		BLEU65.3	11	4d ago
MultiWOZ 2.2 (test)	TOATOD_base	Inform90	10	4d ago
WebNLG+ 2020	DIFFUCOMET-Entity	Exact Match Web Precision80.8	9	4d ago
WebNLG en	SOTA	ROUGE-253.5	9	2d ago
E2E en	SOTA	ROUGE-245.8	9	2d ago
Math	ADORE	BLEU38.8	8	2d ago
EverythingLM		BLEU35.4	8	2d ago
UltraChat	ADORE	BLEU36.8	8	2d ago
NLG 3 tasks one-shot	Lion	Average Exact Match24.7	8	4d ago
E2E	LoRA	BLEU70.4	7	4d ago
WebNLG Seen (test)		BLEU64.2	6	4d ago
CNNDM (test)	Z-Code++	ROUGE-222	6	4d ago
MMLU	SHE-LoRA	STEM Score28.1	5	4d ago
XSum	LTE	GFLOPs/token5.38	5	4d ago

Showing 25 of 48 rows