Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Xuanwang, Song, Yunze, Wang, Yidong, Tang, Shuyun, Li, Xinfeng, Zeng, Zhengran, Wu, Zhen, Ye, Wei, Xu, Wenyuan, Zhang, Yue, Dai, Xinyu, Zhang, Shikun, Wen, Qingsong
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2408.11381
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910594581397504
author Zhang, Xuanwang
Song, Yunze
Wang, Yidong
Tang, Shuyun
Li, Xinfeng
Zeng, Zhengran
Wu, Zhen
Ye, Wei
Xu, Wenyuan
Zhang, Yue
Dai, Xinyu
Zhang, Shikun
Wen, Qingsong
author_facet Zhang, Xuanwang
Song, Yunze
Wang, Yidong
Tang, Shuyun
Li, Xinfeng
Zeng, Zhengran
Wu, Zhen
Ye, Wei
Xu, Wenyuan
Zhang, Yue
Dai, Xinyu
Zhang, Shikun
Wen, Qingsong
contents Large Language Models (LLMs) demonstrate human-level capabilities in dialogue, reasoning, and knowledge retention. However, even the most advanced LLMs face challenges such as hallucinations and real-time updating of their knowledge. Current research addresses this bottleneck by equipping LLMs with external knowledge, a technique known as Retrieval Augmented Generation (RAG). However, two key issues constrained the development of RAG. First, there is a growing lack of comprehensive and fair comparisons between novel RAG algorithms. Second, open-source tools such as LlamaIndex and LangChain employ high-level abstractions, which results in a lack of transparency and limits the ability to develop novel algorithms and evaluation metrics. To close this gap, we introduce RAGLAB, a modular and research-oriented open-source library. RAGLAB reproduces 6 existing algorithms and provides a comprehensive ecosystem for investigating RAG algorithms. Leveraging RAGLAB, we conduct a fair comparison of 6 RAG algorithms across 10 benchmarks. With RAGLAB, researchers can efficiently compare the performance of various algorithms and develop novel algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2408_11381
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation
Zhang, Xuanwang
Song, Yunze
Wang, Yidong
Tang, Shuyun
Li, Xinfeng
Zeng, Zhengran
Wu, Zhen
Ye, Wei
Xu, Wenyuan
Zhang, Yue
Dai, Xinyu
Zhang, Shikun
Wen, Qingsong
Computation and Language
Large Language Models (LLMs) demonstrate human-level capabilities in dialogue, reasoning, and knowledge retention. However, even the most advanced LLMs face challenges such as hallucinations and real-time updating of their knowledge. Current research addresses this bottleneck by equipping LLMs with external knowledge, a technique known as Retrieval Augmented Generation (RAG). However, two key issues constrained the development of RAG. First, there is a growing lack of comprehensive and fair comparisons between novel RAG algorithms. Second, open-source tools such as LlamaIndex and LangChain employ high-level abstractions, which results in a lack of transparency and limits the ability to develop novel algorithms and evaluation metrics. To close this gap, we introduce RAGLAB, a modular and research-oriented open-source library. RAGLAB reproduces 6 existing algorithms and provides a comprehensive ecosystem for investigating RAG algorithms. Leveraging RAGLAB, we conduct a fair comparison of 6 RAG algorithms across 10 benchmarks. With RAGLAB, researchers can efficiently compare the performance of various algorithms and develop novel algorithms.
title RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation
topic Computation and Language
url https://arxiv.org/abs/2408.11381