Spurthi Setty, Katherine Jijo, Eden Chung, Natan Vidra
{"title":"改进基于 RAG 问题解答模型的金融文档检索","authors":"Spurthi Setty, Katherine Jijo, Eden Chung, Natan Vidra","doi":"arxiv-2404.07221","DOIUrl":null,"url":null,"abstract":"The effectiveness of Large Language Models (LLMs) in generating accurate\nresponses relies heavily on the quality of input provided, particularly when\nemploying Retrieval Augmented Generation (RAG) techniques. RAG enhances LLMs by\nsourcing the most relevant text chunk(s) to base queries upon. Despite the\nsignificant advancements in LLMs' response quality in recent years, users may\nstill encounter inaccuracies or irrelevant answers; these issues often stem\nfrom suboptimal text chunk retrieval by RAG rather than the inherent\ncapabilities of LLMs. To augment the efficacy of LLMs, it is crucial to refine\nthe RAG process. This paper explores the existing constraints of RAG pipelines\nand introduces methodologies for enhancing text retrieval. It delves into\nstrategies such as sophisticated chunking techniques, query expansion, the\nincorporation of metadata annotations, the application of re-ranking\nalgorithms, and the fine-tuning of embedding algorithms. Implementing these\napproaches can substantially improve the retrieval quality, thereby elevating\nthe overall performance and reliability of LLMs in processing and responding to\nqueries.","PeriodicalId":501372,"journal":{"name":"arXiv - QuantFin - General Finance","volume":"27 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Improving Retrieval for RAG based Question Answering Models on Financial Documents\",\"authors\":\"Spurthi Setty, Katherine Jijo, Eden Chung, Natan Vidra\",\"doi\":\"arxiv-2404.07221\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The effectiveness of Large Language Models (LLMs) in generating accurate\\nresponses relies heavily on the quality of input provided, particularly when\\nemploying Retrieval Augmented Generation (RAG) techniques. RAG enhances LLMs by\\nsourcing the most relevant text chunk(s) to base queries upon. Despite the\\nsignificant advancements in LLMs' response quality in recent years, users may\\nstill encounter inaccuracies or irrelevant answers; these issues often stem\\nfrom suboptimal text chunk retrieval by RAG rather than the inherent\\ncapabilities of LLMs. To augment the efficacy of LLMs, it is crucial to refine\\nthe RAG process. This paper explores the existing constraints of RAG pipelines\\nand introduces methodologies for enhancing text retrieval. It delves into\\nstrategies such as sophisticated chunking techniques, query expansion, the\\nincorporation of metadata annotations, the application of re-ranking\\nalgorithms, and the fine-tuning of embedding algorithms. Implementing these\\napproaches can substantially improve the retrieval quality, thereby elevating\\nthe overall performance and reliability of LLMs in processing and responding to\\nqueries.\",\"PeriodicalId\":501372,\"journal\":{\"name\":\"arXiv - QuantFin - General Finance\",\"volume\":\"27 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-03-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - QuantFin - General Finance\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2404.07221\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - QuantFin - General Finance","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2404.07221","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Improving Retrieval for RAG based Question Answering Models on Financial Documents
The effectiveness of Large Language Models (LLMs) in generating accurate
responses relies heavily on the quality of input provided, particularly when
employing Retrieval Augmented Generation (RAG) techniques. RAG enhances LLMs by
sourcing the most relevant text chunk(s) to base queries upon. Despite the
significant advancements in LLMs' response quality in recent years, users may
still encounter inaccuracies or irrelevant answers; these issues often stem
from suboptimal text chunk retrieval by RAG rather than the inherent
capabilities of LLMs. To augment the efficacy of LLMs, it is crucial to refine
the RAG process. This paper explores the existing constraints of RAG pipelines
and introduces methodologies for enhancing text retrieval. It delves into
strategies such as sophisticated chunking techniques, query expansion, the
incorporation of metadata annotations, the application of re-ranking
algorithms, and the fine-tuning of embedding algorithms. Implementing these
approaches can substantially improve the retrieval quality, thereby elevating
the overall performance and reliability of LLMs in processing and responding to
queries.