HyperAI초신경
홈뉴스최신 연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAI초신경

Knowledge Base Question Answering On 1

평가 지표

Hits@1

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
Hits@1
Paper TitleRepository
UniK-QA (T5-base)76.7UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering
ChatKBQA86.4ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models
ReTraCk Oracle EL74.6ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering
SPARKLE71.2SPARKLE: Enhancing SPARQL Generation with Direct KG Integration in Decoding
UniK-QA (T5-large)79.1UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering
SKP79.6Bridging the KB-Text Gap: Leveraging Structured Knowledge-aware Pre-training for KBQA
ReTraCk71.6ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering
DPA-RAG80.28Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation-
0 of 8 row(s) selected.