HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Extreme Summarization On Citesum

평가 지표

ROUGE-1

ROUGE-2

ROUGE-L

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	ROUGE-1	ROUGE-2	ROUGE-L	Paper Title	Repository
BART-large (s=abs, t= TLDR/Title/Disci)	41.89	19.51	33.73	CiteSum: Citation Text-guided Scientific Extreme Summarization and Domain Adaptation with Limited Supervision
PEGASUS (s=abs, t=TLDR)	41.56	18.63	33.45	CiteSum: Citation Text-guided Scientific Extreme Summarization and Domain Adaptation with Limited Supervision
EXT-LEAD	21.94	7.35	17.36	CiteSum: Citation Text-guided Scientific Extreme Summarization and Domain Adaptation with Limited Supervision
BART-large (s=abs+disci, t=TLDR)	42.01	19.34	33.72	CiteSum: Citation Text-guided Scientific Extreme Summarization and Domain Adaptation with Limited Supervision
BART-large (s=abs, t=TLDR/title)	41.85	19.21	33.42	CiteSum: Citation Text-guided Scientific Extreme Summarization and Domain Adaptation with Limited Supervision
BART-large (s=abs+title, t=TLDR)	42.02	19.44	33.78	CiteSum: Citation Text-guided Scientific Extreme Summarization and Domain Adaptation with Limited Supervision
BART-large (s=abs, t=TLDR)	41.86	19.36	33.72	CiteSum: Citation Text-guided Scientific Extreme Summarization and Domain Adaptation with Limited Supervision
EXT-HEURISTIC	29.32	12.53	23.99	CiteSum: Citation Text-guided Scientific Extreme Summarization and Domain Adaptation with Limited Supervision
EXT-ORACLE	44.17	27.22	38.32	CiteSum: Citation Text-guided Scientific Extreme Summarization and Domain Adaptation with Limited Supervision

0 of 9 row(s) selected.

Extreme Summarization On Citesum | SOTA | HyperAI초신경