DomainRAG: A Chinese Benchmark for Evaluating Domain-specific Retrieval-Augmented Generation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Shuting, Liu, Jiongnan, Song, Shiren, Cheng, Jiehan, Fu, Yuqi, Guo, Peidong, Fang, Kun, Zhu, Yutao, Dou, Zhicheng
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929387823169536
author Wang, Shuting
Liu, Jiongnan
Song, Shiren
Cheng, Jiehan
Fu, Yuqi
Guo, Peidong
Fang, Kun
Zhu, Yutao
Dou, Zhicheng
author_facet Wang, Shuting
Liu, Jiongnan
Song, Shiren
Cheng, Jiehan
Fu, Yuqi
Guo, Peidong
Fang, Kun
Zhu, Yutao
Dou, Zhicheng
contents Retrieval-Augmented Generation (RAG) offers a promising solution to address various limitations of Large Language Models (LLMs), such as hallucination and difficulties in keeping up with real-time updates. This approach is particularly critical in expert and domain-specific applications where LLMs struggle to cover expert knowledge. Therefore, evaluating RAG models in such scenarios is crucial, yet current studies often rely on general knowledge sources like Wikipedia to assess the models' abilities in solving common-sense problems. In this paper, we evaluated LLMs by RAG settings in a domain-specific context, college enrollment. We identified six required abilities for RAG models, including the ability in conversational RAG, analyzing structural information, faithfulness to external knowledge, denoising, solving time-sensitive problems, and understanding multi-document interactions. Each ability has an associated dataset with shared corpora to evaluate the RAG models' performance. We evaluated popular LLMs such as Llama, Baichuan, ChatGLM, and GPT models. Experimental results indicate that existing closed-book LLMs struggle with domain-specific questions, highlighting the need for RAG models to solve expert problems. Moreover, there is room for RAG models to improve their abilities in comprehending conversational history, analyzing structural information, denoising, processing multi-document interactions, and faithfulness in expert knowledge. We expect future studies could solve these problems better.
format Preprint
id arxiv_https___arxiv_org_abs_2406_05654
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DomainRAG: A Chinese Benchmark for Evaluating Domain-specific Retrieval-Augmented Generation
Wang, Shuting
Liu, Jiongnan
Song, Shiren
Cheng, Jiehan
Fu, Yuqi
Guo, Peidong
Fang, Kun
Zhu, Yutao
Dou, Zhicheng
Computation and Language
Information Retrieval
Retrieval-Augmented Generation (RAG) offers a promising solution to address various limitations of Large Language Models (LLMs), such as hallucination and difficulties in keeping up with real-time updates. This approach is particularly critical in expert and domain-specific applications where LLMs struggle to cover expert knowledge. Therefore, evaluating RAG models in such scenarios is crucial, yet current studies often rely on general knowledge sources like Wikipedia to assess the models' abilities in solving common-sense problems. In this paper, we evaluated LLMs by RAG settings in a domain-specific context, college enrollment. We identified six required abilities for RAG models, including the ability in conversational RAG, analyzing structural information, faithfulness to external knowledge, denoising, solving time-sensitive problems, and understanding multi-document interactions. Each ability has an associated dataset with shared corpora to evaluate the RAG models' performance. We evaluated popular LLMs such as Llama, Baichuan, ChatGLM, and GPT models. Experimental results indicate that existing closed-book LLMs struggle with domain-specific questions, highlighting the need for RAG models to solve expert problems. Moreover, there is room for RAG models to improve their abilities in comprehending conversational history, analyzing structural information, denoising, processing multi-document interactions, and faithfulness in expert knowledge. We expect future studies could solve these problems better.
title DomainRAG: A Chinese Benchmark for Evaluating Domain-specific Retrieval-Augmented Generation
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2406.05654