HyperAI초신경

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

한국어

HyperAI초신경

Knowledge Base Question Answering On 1

평가 지표

Hits@1

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Hits@1	Paper Title	Repository
UniK-QA (T5-base)	76.7	UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering	-
ChatKBQA	86.4	ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models	-
ReTraCk Oracle EL	74.6	ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering
SPARKLE	71.2	SPARKLE: Enhancing SPARQL Generation with Direct KG Integration in Decoding	-
UniK-QA (T5-large)	79.1	UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering	-
SKP	79.6	Bridging the KB-Text Gap: Leveraging Structured Knowledge-aware Pre-training for KBQA	-
ReTraCk	71.6	ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering
DPA-RAG	80.28	Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation	-

0 of 8 row(s) selected.

Knowledge Base Question Answering On 1 | SOTA | HyperAI초신경