[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-39989-en":3,"doc-seo-39989-105":29,"detail-sidebar-cat-0-en-105":90},{"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},39989,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","TALLM: A Framework for Text Analysis Using Large Language Models","Large Language Models (LLMs) deliver state-of-the-art performance on translation, summarization, sentiment analysis, and text generation, yet their decisions often remain a “black box.” TALLM presents a framework for text analysis that integrates pre-trained models from repositories with curated datasets. The proposed workflow supports targeted performance while improving reliability and traceability, enabling explainability and transparent evaluation for safer, accountable deployment in practical scenarios.","2025 IEEE 13th International Conference on Healthcare Informatics (ICHI) | 979-8-33 15-2094-6/25/$31.00 ©2025 IEEE | DOI: 10. 1 109/ICHI64645 .2025.00089  \n2025 IEEE 13th International Conference on Healthcare Informatics (ICHI)  \nTALLM: A framework for Text Analysis using  \nLarge Language Models  \nLuca Petrillo∗†, Fabio Martinelli‡, Antonella Santone§ , Francesco Mercaldo§†  \n∗ IMT School for Advanced Studies Lucca, Lucca, Italy  \n[luca.petrillo@imtlucca.it](luca.petrillo@imtlucca.it)  \n†Institute for Informatics and Telematics, National Research Council of Italy (CNR), Pisa, Italy  \n{luca.petrillo, francesco.mercaldo}@iit.cnr.it  \n‡Institute for High Performance Computing and Networking, National Research Council of Italy (CNR), Rende (CS), Italy  \n[fabio.martinelli@icar.cnr.it](fabio.martinelli@icar.cnr.it)  \n§ University of Molise, Campobasso, Italy  \n{francesco.mercaldo, [antonella.santone](antonella.santone}@unimol.it)[}](antonella.santone}@unimol.it)[@unimol.it](antonella.santone}@unimol.it)  \nAbstract—Artificial intelligence systems known as Large Language Models have proven to process and interpret human language. With these models attaining state-of-the-art outcomesin various tasks, such as language translation, text summarization, sentiment analysis, and text production, it is important to understand how the models get their judgments to maintain confidence and dependability. This paper presents the design and the development of TALLM i.e., a framework for text analysis using large language models. TALLM seamlessly allows the integration of pre-trained models sourced from repositories and the use of an appropriate set of curated datasets. This workflow permits achieving the targeted level of model performance and guarantees its reliability and traceability, thereby setting applicable precedents for future development.  \nIndex Terms—llm, explainability, machine learning pipeline  \nI. INTRODUCTION  \nArtificial intelligence (AI) systems known as Large Language Models (LLMs) are made to process and interpret human language. Their vast training data allows them to acquire intricate linguistic context, connections, and patterns—including syntax, semantics, and pragmatics.  \nWith these models attaining state-of-the-art [1] outcomesin various tasks, such as language translation, text summarization, sentiment analysis, and text production, LLMs have significantly influenced Natural Language Processing (NLP) . In the field of language translation, they have proven to be able to translate text across languages with previously unheard-of precision, frequently matching human translators’ output.  \nThese models are built using deep learning techniques, particularly neural networks, and are trained on vast amounts of text data. Even though LLMs have performed quite impressively in various tasks under the spectrum of natural language processing, their nature is often described as a”black-box model.” This term reflects and underlines several prospects and problems related to their functioning. The complex structure and interaction of their billions of parameters make understanding why the model provides a specific answer close to impossible. Their application may cause users to be somewhat disassociated with this technology due to its blackbox approach [2] . The capacity to comprehend and analyze a  \nmodel’s decisions is known as explainability. Explainability is essential in this context for several reasons [3] . It is important to comprehend how the models get their judgments to maintain confidence and dependability, especially in crucial applications like banking, healthcare, and decision-making. Additionally, explainability aids in identifying and reducing biases in training data [4], which can be perpetuated by LLMsand result in biased outputs. It also makes the decision-making process transparent, promoting accountability and ensuring they are utilized appropriately. Given their intricate design and the massive volumes of data","cbCaicNlBdlH3BPm","https://ap.wps.com/l/cbCaicNlBdlH3BPm","pdf",167717,1,2,"English","en",105,"# Introduction\n# The Proposal","[{\"question\":\"What problem does TALLM address in large language model usage?\",\"answer\":\"TALLM addresses the difficulty of understanding how LLMs produce specific outputs, since these systems are often treated as “black boxes.” It targets the need for confidence, dependability, and transparent reasoning.\"},{\"question\":\"How does TALLM integrate models and data in its workflow?\",\"answer\":\"TALLM combines pre-trained models sourced from repositories with an appropriate set of curated datasets. The dataset is split into training, validation, and testing sets, then models are built and evaluated across training epochs.\"},{\"question\":\"What role does explainability play in TALLM?\",\"answer\":\"Explainability is used to assess predictions produced on the training set or a given dataset. It aims to improve transparency and interpretability while helping identify and reduce biases.\"}]",1783088839,5,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":27},"tallm-a-framework-for-text-analysis-using-large-language-models","",{"@graph":35,"@context":84},[36,52,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,46,49],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":21},"https://docshare.wps.com/document/","Document",{"item":47,"name":12,"@type":42,"position":48},"https://docshare.wps.com/document/research-report/",3,{"item":50,"name":13,"@type":42,"position":51},"https://docshare.wps.com/document/tallm-a-framework-for-text-analysis-using-large-language-models/39989/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":23,"description":14,"dateModified":60,"datePublished":61,"encodingFormat":59,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":40,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-07-13","2026-07-03",true,{"@type":64,"interactionType":65,"userInteractionCount":20},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does TALLM address in large language model usage?","Question",{"text":74,"@type":75},"TALLM addresses the difficulty of understanding how LLMs produce specific outputs, since these systems are often treated as “black boxes.” It targets the need for confidence, dependability, and transparent reasoning.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does TALLM integrate models and data in its workflow?",{"text":79,"@type":75},"TALLM combines pre-trained models sourced from repositories with an appropriate set of curated datasets. The dataset is split into training, validation, and testing sets, then models are built and evaluated across training epochs.",{"name":81,"@type":72,"acceptedAnswer":82},"What role does explainability play in TALLM?",{"text":83,"@type":75},"Explainability is used to assess predictions produced on the training set or a given dataset. It aims to improve transparency and interpretability while helping identify and reduce biases.","https://schema.org",{"og:url":50,"og:type":86,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":88,"canonical":50},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":105,"show_sort_weight":106,"slug":107},"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":28,"slug":136},19,"General","general"]