Výsledky vyhledávání - "Zhao, Qingfei"

Report

Towards Multi-Source Retrieval-Augmented Generation via Synergizing Reasoning and Preference-Driven Retrieval

Autor: Zhao, Qingfei, Wang, Ruobing, Wang, Xin, Zha, Daren, Mu, Nan

Retrieval-Augmented Generation (RAG) has emerged as a reliable external knowledge augmentation technique to mitigate hallucination issues and parameterized knowledge limitations in Large Language Models (LLMs). Existing Adaptive RAG (ARAG) systems st

Externí odkaz: http://arxiv.org/abs/2411.00689

Zobrazit plný text záznamu

Report

LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering

Autor: Zhao, Qingfei, Wang, Ruobing, Cen, Yukuo, Zha, Daren, Tan, Shicheng, Dong, Yuxiao, Tang, Jie

Long-Context Question Answering (LCQA), a challenging task, aims to reason over long-context documents to yield accurate answers to questions. Existing long-context Large Language Models (LLMs) for LCQA often struggle with the "lost in the middle" is

Externí odkaz: http://arxiv.org/abs/2410.18050

Zobrazit plný text záznamu

Report

Retriever-and-Memory: Towards Adaptive Note-Enhanced Retrieval-Augmented Generation

Autor: Wang, Ruobing, Zha, Daren, Yu, Shi, Zhao, Qingfei, Chen, Yuxuan, Wang, Yixuan, Wang, Shuo, Yan, Yukun, Liu, Zhenghao, Han, Xu, Liu, Zhiyuan, Sun, Maosong

Retrieval-Augmented Generation (RAG) mitigates issues of the factual errors and hallucinated outputs generated by Large Language Models (LLMs) in open-domain question-answering tasks (OpenQA) via introducing external knowledge. For complex QA, howeve

Externí odkaz: http://arxiv.org/abs/2410.08821

Zobrazit plný text záznamu

Report

OAG-Bench: A Human-Curated Benchmark for Academic Graph Mining

Publikováno v: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '24), August 25--29, 2024, Barcelona, Spain

With the rapid proliferation of scientific literature, versatile academic knowledge services increasingly rely on comprehensive academic graph mining. Despite the availability of public academic graphs, benchmarks, and datasets, these resources often

Externí odkaz: http://arxiv.org/abs/2402.15810

Zobrazit plný text záznamu