[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-327294-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-327294-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","grounded-optimization-a-layered-engineering-framework-for-reducing-llm-hallucination-in-automated-personal-document-rewriting","Grounded Optimization - A Layered Engineering Framework for Reducing LLM Hallucination in Automated Personal Document Rewriting","","Large language models increasingly optimize resumes for applicant tracking systems, but hallucinations manifest in harmful, resume-specific ways such as temporal fabrication, cross-domain terminology contamination, structural mutation, and content fabrication. Grounded Optimization introduces a five-layer defense-in-depth framework combining temporal context validation, deterministic contamination detection, structural invariant enforcement, prompt-level grounding, and an evaluator agent to constrain distortion of candidates’ career history.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/grounded-optimization-a-layered-engineering-framework-for-reducing-llm-hallucination-in-automated-personal-document-rewriting/327294/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/grounded-optimization-a-layered-engineering-framework-for-reducing-llm-hallucination-in-automated-personal-document-rewriting/327294.png","ImageObject",300,407,{"name":42,"@type":43},"Olivia Brown","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-02","2026-09-21",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",6,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What hallucination modes does the paper identify in automated resume rewriting?","Question",{"text":63,"@type":64},"It categorizes hallucinations into temporal fabrication, cross-domain contamination, structural mutation, and content fabrication that can introduce false or distorted claims.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does Grounded Optimization reduce temporal fabrication?",{"text":68,"@type":64},"It applies temporal context validation by embedding release-date constraints in every prompt to prevent post-hoc technologies from being injected into historical roles.",{"name":70,"@type":61,"acceptedAnswer":71},"What role does the evaluator agent play in the framework?",{"text":72,"@type":64},"An evaluator agent (a separate LLM instance) acts as a quality gate that can reject and re-trigger the pipeline, complementing earlier deterministic and prompt-based defenses.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},327294,1790614524,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,105,110,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},7,"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":111,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":145,"preview_page_count":4},16904993612988,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","Grounded Optimization: A Layered Engineering Framework for Reducing LLM Hallucination in Automated Personal Document Rewriting  \nShashank Indukuri∗ [sinduku1@depaul.edu](sinduku1@depaul.edu)  \nAdarsh Agrawal∗ [adagrawal@cs.stonybrook.edu](adagrawal@cs.stonybrook.edu)  \narXiv :2607 .0 1457v 1 [ cs .CL] 1 Jul 2026  \nAbstract  \nLarge language models (LLMs) are increasingly applied to resume optimization for applicant tracking systems, introducing hallucination failures distinct from general text generation: anachronistic technology injection, cross-domain terminology contamination, structural mutation, and content fabrication. We present Grounded Optimization, a five-layer framework combining temporal context validation, deterministic contamination detection, structural invariant enforcement, promptlevel grounding, and an evaluator agent.  \nIn ablation experiments across three LLMs, four temperature settings, and six layer configurations on 25 synthetic resumes spanning 14 industries, undefended baselines produce 2.48–5.36 detected hallucinations per resume. Among detectors independent of the active defenses, temporal hallucinations are reduced by 50–95% across all conditions; overall detected hallucination rate falls to 0.04–0.24 . Promptlevel grounding alone achieves zero detected hallucinations at low temperature with a capable instruction-following model; higher temperatures and weaker models reveal the need for the deterministic layers as a complement. We release the contamination taxonomy, evaluation code, and raw data.  \n1 Introduction  \nThe use of large language models for document optimization has grown rapidly, with resume tailoring representing one of the most commercially active applications. Services that rewrite resumes to improve alignment with job descriptions and ATS scoring algorithms now process large volumes of documents. Yet the hallucination behaviors documented in LLM general text generation [1, 2] manifest in particularly harmful ways when applied to personal documents:  \n1. Temporal fabrication: An LLM optimizing a 2018 software engineering role may inject references to LangChain (released late 2022) or Mixtral (released December 2023), creating verifiably false claims about the candidate’s experience timeline.  \n2. Cross-domain contamination: When rewriting a role at an AWS-centric company, the model may introduce Azure or GCP terminology to match job description keywords, adding multi-cloud terminology absent from the original role.  \n3. Structural mutation: The model may silently merge, delete, or condense bullet points to reduce output length, removing genuine achievements in the process.  \n4. Content fabrication: The model may invent company names, inflate metrics, or add certifications the candidate never earned.  \n∗Equal contribution.  \nPreprint. Under review.  \nThese failures carry concrete consequences: candidates may unknowingly submit resumes containing false claims, exposing them to disqualification or termination. Unlike hallucination in chatbots or search summaries, where users can verify outputs interactively, resume optimization typically operates in batch mode with minimal human review.  \nHallucination mitigation has been studied extensively in open-domain question answering [3], summarization [4], and retrieval-augmented generation [5] . Prior work on hallucination in personal document optimization specifically is more limited. Concurrent system-level work has begun integrating anti-hallucination mechanisms into resume-tailoring pipelines (e.g., [6]), but to our knowledge no published work characterizes the underlying hallucination modes as a taxonomy or systematically isolates the contribution of individual defense layers.  \nThe ground truth in this domain is not an external knowledge base but the candidate’s own career history, which the LLM receives as input and must enhance without distorting.  \nWe present Grounded Optimization, a five-layer defense-in-depth framework that addresses ","cbCaiaoLrzX8sF3n","https://ap.wps.com/l/cbCaiaoLrzX8sF3n","pdf",316240,13,"English","# Introduction\n## Hallucination modes in resume optimization\n## Defense-in-depth framework overview","[{\"question\":\"What hallucination modes does the paper identify in automated resume rewriting?\",\"answer\":\"It categorizes hallucinations into temporal fabrication, cross-domain contamination, structural mutation, and content fabrication that can introduce false or distorted claims.\"},{\"question\":\"How does Grounded Optimization reduce temporal fabrication?\",\"answer\":\"It applies temporal context validation by embedding release-date constraints in every prompt to prevent post-hoc technologies from being injected into historical roles.\"},{\"question\":\"What role does the evaluator agent play in the framework?\",\"answer\":\"An evaluator agent (a separate LLM instance) acts as a quality gate that can reject and re-trigger the pipeline, complementing earlier deterministic and prompt-based defenses.\"}]","Grounded Optimization - A Layered Engineering Framework for Reducing LLM Hallucination in Automated Personal Document Rewriting | PDF",1789976926,33]