[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82815-en":3,"doc-seo-82815-105":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},82815,4398048950312,"Violet","https://ap-avatar.wpscdn.com/avatar/400002538284de19e3c?_k=1778320343897328908",8,"Research & Report","A Retrieval-Augmented Framework for Detecting and Resolving Pragmatic Ambiguities in Natural Language Requirements","Natural language requirements (NLRs) enable communication among diverse stakeholders in software development, yet their context-dependent wording can cause pragmatic ambiguity and lead to misinterpretations. The paper proposes a retrieval-augmented approach that uses domain knowledge bases representing novice, intermediate, and expert stakeholders to detect interpretation discrepancies. It generates candidate disambiguated requirements via the expert knowledge base and requires analyst validation for functional alignment. Evaluation on PURE dataset documents with multiple LLMs shows effective detection and producing relevant, clear, consistent candidates, with GPT-4o-mini leading in detection recall and F2.","A Retrieval-Augmented Framework for Detecting and Resolving Pragmatic Ambiguities in Natural Language Requirements  \nPavithra PM Nair  \nTata Consultancy Services Pune, India [pavithra.nair@tcs.com](pavithra.nair@tcs.com)  \nPreethu Rose Anish  \nTata Consultancy Services Pune, India [preethu.rose@tcs.com](preethu.rose@tcs.com)  \narXiv :2607 .04436v 1 [ cs . SE] 5 Jul 2026  \nAbstract  \nNatural language requirements (NLRs) are essential for bridging communication gaps among diverse stakeholders in software development. However, the inherent ambiguity in NLRs can pose significant challenges. In particular, some requirements may be misinterpreted due to varying contextual knowledge and domainspecific expectations of the stakeholders, a phenomenon known as pragmatic ambiguity. This paper presents an approach for detecting and resolving pragmatic ambiguities in NLRs. The approach leverages retrieval-augmented generation techniques with novice, intermediate, and expert domain knowledge bases to simulate stakeholders with varying domain expertise and detect discrepancies in requirement interpretation. Candidate disambiguated requirements are generated using the expert domain knowledge base, with final validation by a requirements analyst required to ensure alignment with the intended system functionality. We evaluate the approach on two requirements specification documents from the PUblic REquirements (PURE) dataset, using four large language models: GPT-4o-mini, Mistral-7B, Llama-3.1-8B, and Qwen2.5-7B. Detection performance is assessed using macro-averaged accuracy, precision, recall, F1, and F2 scores. The resolution quality of the candidate disambiguated requirements is measured through human evaluation of relevance, clarity, and consistency. In this initial evaluation, results show that the proposed approach can detect pragmatic ambiguities and produce candidate disambiguated requirements that are relevant, clear, and consistent with the intended system functionality. Among the evaluated models, GPT-4o-mini achieved the highest macro-averaged recall (0.75) and F2 score (0.75) for pragmatic ambiguity detection. In the resolution task, GPT-4o-mini received the highest relevance scores from human evaluators, while Mistral-7B achieved the highest scores for clarity and consistency.  \nCCS Concepts  \n• Software and its engineering → Requirements analysis.  \nKeywords  \nPragmatic Ambiguity, Requirements Engineering, Natural Language Requirements, Large Language Models, Retrieval-Augmented Generation  \nThis work is licensed under a Creative Commons Attribution 4 .0 International License. EASE’26, Glasgow, United Kingdom  \n© 2026 Copyright held by the owner/author(s) .  \nACM ISBN 979-8-4007-2348-3/2026/06  \n[https://doi.org/10.1145/3816483.3816519](https://doi.org/10.1145/3816483.3816519)  \nACM Reference Format:  \nPavithra PM Nair and Preethu Rose Anish. 2026. A Retrieval-Augmented Framework for Detecting and Resolving Pragmatic Ambiguities in Natural Language Requirements. In International Conference on Evaluation and Assessment in Software Engineering (EASE ’26), June 09–12, 2026, Glasgow, United Kingdom. ACM, New York, NY, USA, 11 pages. [https://doi.org/10](https://doi.org/10) . 1145/3816483.3816519  \n1 Introduction  \nNatural language requirements (NLRs) are a crucial element in the software development life cycle (SDLC), as they capture both the functional specifications and non-functional attributes of the software to be developed. Serving as a communication bridge between different stakeholders in the SDLC, NLRs guide the design, implementation, and validation of software systems. However, the inherent flexibility and context-dependence of natural language often introduce ambiguities in these requirements [3, 23] . NLRs may be interpreted differently depending on each stakeholder’s background, experience, and perspective [14] .  \nMisinterpretations can arise not only between requirements analysts (RAs) and domain experts, but also amo","cbCaiqShJc17BZ79","https://ap.wps.com/l/cbCaiqShJc17BZ79","pdf",1616251,1,11,"English","en",105,"# Introduction\n## Motivation and Background\n## Example of Pragmatic Ambiguity\n## Gap in Existing Research\n## Remaining Challenges","[{\"question\":\"What problem does the paper address in natural language requirements?\",\"answer\":\"It addresses pragmatic ambiguity, where NLRs are misinterpreted due to different contextual knowledge and domain expectations among stakeholders.\"},{\"question\":\"How does the proposed framework detect pragmatic ambiguities?\",\"answer\":\"It uses retrieval-augmented generation with novice, intermediate, and expert domain knowledge bases to simulate stakeholders and identify discrepancies in how requirements are interpreted.\"},{\"question\":\"How are the ambiguous requirements resolved and validated?\",\"answer\":\"Candidate disambiguated requirements are generated using the expert domain knowledge base, and a requirements analyst validates them to ensure alignment with intended system functionality.\"}]",1784183150,28,{"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},"a-retrieval-augmented-framework-for-detecting-and-resolving-pragmatic-ambiguities-in-natural-language-requirements","",{"@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/a-retrieval-augmented-framework-for-detecting-and-resolving-pragmatic-ambiguities-in-natural-language-requirements/82815/",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 paper address in natural language requirements?","Question",{"text":75,"@type":76},"It addresses pragmatic ambiguity, where NLRs are misinterpreted due to different contextual knowledge and domain expectations among stakeholders.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed framework detect pragmatic ambiguities?",{"text":80,"@type":76},"It uses retrieval-augmented generation with novice, intermediate, and expert domain knowledge bases to simulate stakeholders and identify discrepancies in how requirements are interpreted.",{"name":82,"@type":73,"acceptedAnswer":83},"How are the ambiguous requirements resolved and validated?",{"text":84,"@type":76},"Candidate disambiguated requirements are generated using the expert domain knowledge base, and a requirements analyst validates them to ensure alignment with intended system functionality.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]