[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82204-en":3,"doc-seo-82204-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},82204,2336464648746,"Skyler","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Augmenting Fundamental Analysis with Large Language Models A RAG-Based System for Generating Investor Briefs","The study explores how large language models (LLMs) can augment fundamental company analysis using reports, macroeconomic indicators such as GDP and inflation changes, and regulatory filings from the U.S. SEC available via EDGAR. Data preprocessing is followed by API-based querying of a GPT-4o model in a retrieval-augmented generation (RAG) setup. An investor knowledge document based on Kitchin cycles guides the generation of automatic investor briefs. Briefs are evaluated by nine individual investors for usefulness over four weeks.","arXiv :2607 .09 12 1v 1 [ cs .CL] 10 Jul 2026  \nAugmenting Fundamental Analysis with Large Language Models: A RAG-Based System for Generating Investor Briefs  \nBartosz Zi´olko and Kacper Dobrzeniewski  \nFaculty of Computer Science, AGH University of Krakow, Poland  \nJuly 13, 2026  \nAbstract  \nIn this study, we examine the opportunities brought by Large Language Models (LLMs) to various aspects of fundamental analysis of companies based on their reports as well as data and documents describing macroeconomic situation like GDP and inflation changes as well as documents filled to the U.S. Securities and Exchange Commission (SEC) which can be found in EDGAR. We were preprocessing those data and than sending via API to gpt-4o model in a Retrieval-Augmented Generation (RAG) like regime. We prepared as well a document describing an exemplar investor knowledge based on Kitchin cycles. We were scanning data important for analysis of 9 companies for 4 weeks. Using LLM we were producing automatic briefs about them. They were sent to nine participants who are individual investors to evaluate usefulness of such approach to data analysis.  \nKeywords: Natural Language Processing in Finance, investing, Large Language Models (LLM), Retrieval-Augmented Generation (RAG), Investor Decision Support Systems, Artificial Intelligence in Investment  \nJEL codes: G11 (Portfolio Choice; Investment Decisions), G14 (Information and Market Efficiency; Event Studies), G17 (Financial Forecasting and Simulation), C45 (Neural Networks and Related Topics)  \n1 Introduction  \nFundamental analysis, the cornerstone of investment strategies, traditionally relies on the in-depth evaluation of financial statements, industry reports, and macroeconomic indicators. This process, however, is time-consuming and requires analysts to process vast amounts of data, much of which is unstructured, such as the text from annual reports, earnings call transcripts, or documents filed with regulatory bodies like SEC via the EDGAR system. The rapid development in Natural Language Processing (NLP), and particularly the advent of LLMs, presents unprecedented opportunities to automate and deepen this process.  \n1.1 Literature Review  \nEarly work on the application of NLP in finance primarily focused on sentiment analysis. The seminal study Loughran and McDonald (2011) demonstrated that general-purpose sentiment dictionaries are inadequate for the specific language of finance, leading to the development of specialized lexicons. With the advent of the Transformer architecture and models like BERT Devlin et al. (2019), it became possible to create contextual models specifically pre-trained on financial corpora. An example is FinBERT Araci (2019), which significantly improved performance on sentiment classification tasks in financial texts.  \nThe current revolution in NLP is fundamentally built upon the Transformer architecture, introduced by Vaswani et al. (2017) . Its core innovation, the self-attention mechanism, allows models to weigh the importance of different words in the input data, enabling a more profound contextual understanding and parallel processing capabilities that were not feasible with previous sequential architectures like Recurrent Neural Networks (RNNs) or Long Short-Term Memory (LSTM) . This architectural breakthrough paved the way for the development of modern LLMs. Today, the field continues to  \nadvance at a rapid pace, with leading research labs pushing the boundaries of model capabilities. For instance, OpenAI’s GPT-4o demonstrates a move towards natively multimodal models that can seamlessly process and reason across text, audio, and vision, increasing both efficiency and user interaction possibilities OpenAI (2024) .  \nThe emergence of large-scale generative models, such as those from the GPT family, has revolutionized the approach to text analysis. These models, with their ability to understand and generate text in a zero-shot or few-shot setting, can perform tas","cbCaicAAVVBYmIeZ","https://ap.wps.com/l/cbCaicAAVVBYmIeZ","pdf",714003,1,16,"English","en",105,"# Introduction\n## Literature Review","[{\"question\":\"What problem does the document address in fundamental analysis?\",\"answer\":\"Fundamental analysis is time-consuming because it requires processing large volumes of often unstructured text from company reports and regulatory filings such as SEC documents in EDGAR.\"},{\"question\":\"How does the proposed system use LLMs and RAG?\",\"answer\":\"The system preprocesses relevant data and sends it via an API to a GPT-4o model operating in a retrieval-augmented generation (RAG) regime, grounding generated content in provided source documents.\"},{\"question\":\"How are the generated investor briefs evaluated?\",\"answer\":\"Automatic briefs for nine companies are produced using the LLM approach and then sent to nine individual investor participants, who assess the usefulness of the data analysis method over a four-week period.\"}]",1784178794,40,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"augmenting-fundamental-analysis-with-large-language-models-a-rag-based-system-for-generating-investor-briefs","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/augmenting-fundamental-analysis-with-large-language-models-a-rag-based-system-for-generating-investor-briefs/82204/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the document address in fundamental analysis?","Question",{"text":75,"@type":76},"Fundamental analysis is time-consuming because it requires processing large volumes of often unstructured text from company reports and regulatory filings such as SEC documents in EDGAR.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed system use LLMs and RAG?",{"text":80,"@type":76},"The system preprocesses relevant data and sends it via an API to a GPT-4o model operating in a retrieval-augmented generation (RAG) regime, grounding generated content in provided source documents.",{"name":82,"@type":73,"acceptedAnswer":83},"How are the generated investor briefs evaluated?",{"text":84,"@type":76},"Automatic briefs for nine companies are produced using the LLM approach and then sent to nine individual investor participants, who assess the usefulness of the data analysis method over a four-week period.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":28,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]