[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121396-en":3,"doc-seo-121396-105":30,"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":27,"seo_description":14,"update_tm":28,"read_time":29},121396,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Using Language for Efficient, Explainable, and Interactive Machine Learning","Language is fundamental in human learning and pedagogy, yet modern AI—especially large-scale deep learning—often relies on extensive data and produces opaque decisions that limit interpretability and trust. This dissertation embeds language into key stages of the machine-learning workflow to create systems that are more efficient, transparent, and adaptive. It develops entailment-based zero-shot categorization, benchmarks with human explanations, faithful rationale generation, language-guided error diagnosis and data augmentation, and dialogue-driven interactive concept learning.","USING LANGUAGE FOR EFFICIENT, EXPLAINABLE, AND INTERACTIVE MACHINE  \nLEARNING  \nRakesh Radhakrishnan Menon  \nA dissertation submitted to the faculty at the University of North Carolina at Chapel Hill in partial fulfillment of the requirements for the degree of Doctor of Philosophy in the Department of  \nComputer Science.  \nChapel Hill  \n2025  \nApproved by: Shashank Srivastava Mohit Bansal Snigdha Chaturvedi Dan Roth  \nYunyao Li  \n©2025  \nRakesh Radhakrishnan Menon ALL RIGHTS RESERVED  \nii  \nABSTRACT  \nRakesh Radhakrishnan Menon: Using Language for Efficient, Explainable, and Interactive Machine  \nLearning  \n(Under the direction of Shashank Srivastava)  \nLanguage is fundamental in human learning and pedagogy. We can use language to convey complex concepts, resolve ambiguities, and refine our understanding. In contrast, modern AI systems – especially large-scale deep learning models – rely on large datasets to deliver high predictive accuracies. Yet, their opaque decision-making processes limit interpretability and trust. In this thesis, we infuse language into key stages of the machine learning workflow, demonstrating how language explanations and interactions yield more efficient, transparent, and adaptive AI systems.  \nFirst, we explore natural language explanations as an alternative to large-scale dataset annotations for classification. We introduce ExEnt, an entailment-based method that leverages these explanations for zero-shot categorization of novel concepts. To systematically assess model performance in this setting, we propose CLUES, a benchmark pairing structured classification tasks with human-written explanations for rigorous evaluation.  \nNext, we use natural language to explain broader patterns in how trained classifiers make decisions. We introduce MaNtLE, a model-agnostic framework that generates rationales describing aclassifier’s reasoning across different inputs. Unlike traditional attribution-based methods, MaNtLE explanations are more faithful to the classifier’s decision process and easier for users to understand.  \nBeyond explanations, we also explore how language can diagnose and rectify systematic errors in text classifiers. We introduce DiScErN, a framework that detects and precisely describes error-prone data groups using natural language. These descriptions then guide targeted data augmentation, improving model performance in underperforming regions.  \nFinally, we study how language interactions can be used to actively learn new concepts. Here, we present INTERACT, an interactive learning framework enabling large language models to acquire andrefine concepts through question-driven dialogues with experts. Empirically, we demonstrate that  \nlanguage models achieve strong performance in just a few dialogue turns, highlighting the efficiency and effectiveness of interactive learning.  \nCollectively, these contributions demonstrate that language – in the form of explanations or interactive queries – offers a versatile mechanism for guiding machine learning models. By embedding language into the machine learning pipeline, we enable AI systems that are not only adaptable but also interpretable, trustworthy, and efficient in real-world settings.  \nTo Mummy, Pappa, and Appu  \nACKNOWLEDGMENTS  \nFirstly, I would like to extend my deepest gratitude to my advisor, Shashank Srivastava. His mentorship has been instrumental in shaping both my research and my approach to learning. He consistently encouraged me to ask thought-provoking questions and pursue meaningful problems, rather than follow prevailing trends. This guidance broadened my understanding of how things work and instilled in me a lasting passion for inquiry. His unwavering support, insightful feedback, and readiness to challenge my assumptions have profoundly influenced my academic journey. I am also deeply grateful to my thesis committee members: Dan Roth, Yunyao Li, Mohit Bansal, and Snigdha Chaturvedi. Our discussions have brought valuable clarity t","cbCaidtkaryds3NV","https://ap.wps.com/l/cbCaidtkaryds3NV","pdf",5698455,1,190,"English","en",105,"# Abstract\n# Contributions Overview\n## Natural Language Explanations for Zero-Shot Categorization\n## Faithful Rationale Generation for Classifier Decisions\n## Language-Driven Error Diagnosis and Data Augmentation\n## Interactive Dialogue Learning for New Concepts\n# Acknowledgments","[{\"question\":\"How does the thesis use language to improve interpretability in machine learning?\",\"answer\":\"It integrates natural-language explanations to replace or complement large-scale annotations and to generate rationales for classifier decisions, making models’ reasoning more transparent to users.\"},{\"question\":\"What is ExEnt and how is it used in this work?\",\"answer\":\"ExEnt is an entailment-based method that leverages language explanations for zero-shot categorization of novel concepts.\"},{\"question\":\"How does the work address systematic errors in text classifiers?\",\"answer\":\"It introduces DiScErN to detect and precisely describe error-prone data groups in natural language, then uses those descriptions to guide targeted data augmentation.\"}]","Using Language for Efficient, Explainable, and Interactive Machine Learning | PDF",1785735490,479,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"using-language-for-efficient-explainable-and-interactive-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/using-language-for-efficient-explainable-and-interactive-machine-learning/121396/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",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},"How does the thesis use language to improve interpretability in machine learning?","Question",{"text":75,"@type":76},"It integrates natural-language explanations to replace or complement large-scale annotations and to generate rationales for classifier decisions, making models’ reasoning more transparent to users.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is ExEnt and how is it used in this work?",{"text":80,"@type":76},"ExEnt is an entailment-based method that leverages language explanations for zero-shot categorization of novel concepts.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the work address systematic errors in text classifiers?",{"text":84,"@type":76},"It introduces DiScErN to detect and precisely describe error-prone data groups in natural language, then uses those descriptions to guide targeted data augmentation.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"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":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]