[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3476":3,"related-3476":69},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":18,"tags":20,"primary_topic":9,"secondary_topics":21,"classification":22,"search_phrases":48,"slug":49,"view_count":50,"doi":51,"paper":52,"created_at":68},3476,"Explainability and Reliability in Large Language Model Systems: A Survey of SHAP, LIME and Attention Frameworks","https:\u002F\u002Fdoi.org\u002F10.67317\u002Fijmsrt26sep093","Increasing adoption of language models in sensitive sectors such as healthcare, finance, cybersecurity, education, etc., highlights the significance of developing transparent decision support systems. This paper reviews the use of explanation techniques for language and machine learning models, including SHAP, LIME, attention-based explanations and frameworks that transform outputs from models into natural language explanations. It turns out that the existing literature demonstrates that although classical language models demonstrate good predictive and semantic performance, they lack transparency. In this regard, SHAP and LIME help in the detection of feature importance and combination of frameworks lead to explanations being more understandable for users. The literature also outlines some limitations of the existing techniques such as explanation faithfulness, hallucinations, biases, privacy issues, computational complexity and lack of benchmarks for evaluation. The use of explainability in healthcare, finance, cybersecurity, industrial systems and IoT is discussed based on the evidence found in the literature.","语言模型在医疗、金融、网络安全、教育等敏感领域的应用日益广泛，这使得开发透明的决策支持系统变得尤为重要。本文综述了用于语言模型和机器学习模型的可解释性技术，包括SHAP、LIME、基于注意力的解释方法，以及将模型输出转化为自然语言解释的框架。现有文献表明，尽管经典语言模型在预测和语义方面表现良好，但缺乏透明度。在这方面，SHAP和LIME有助于识别特征重要性，而框架的组合则使解释更易于用户理解。文献还指出了现有技术的一些局限性，如解释忠实度、幻觉、偏见、隐私问题、计算复杂性以及缺乏评估基准。基于文献中发现的证据，本文讨论了可解释性在医疗、金融、网络安全、工业系统和物联网中的应用。",null,"International Journal of Modern Science and Research Technology","2026-09-23T00:00:00Z","论文",10,false,0,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":17},"该文为通用大语言模型可解释性综述，未涉及三农或农业信息化场景，与平台主题无关。",[19],{"name":10,"url":6},[12],[],{"status":23,"locked":14,"version":24,"method":25,"evidence":26},"needs_review","2026-10-22.2","rules",{"candidates":27,"agricultural_evidence":14,"reason":47},[28,39],{"code":29,"score":30,"supported":31,"title":32,"abstract":34,"tags":38},"I2",17,true,[33],"large language model",[35,36,37],"机器学习","machine learning","decision support",[],{"code":40,"score":41,"supported":31,"title":42,"abstract":43,"tags":46},"I5",6,[],[44,45],"物联网","IoT",[],"农业相关性需要复核",[],"ExplainabilityandReliabilityinLargeLangu-3476",3,"10.67317\u002Fijmsrt26sep093",{"doi":51,"openalex_id":53,"authors":54,"venue":10,"cited_by_count":15,"oa_url":59,"card":60,"direction":66,"ingested_from":67},"W7214085362",[55,57],{"name":56,"orcid":9},"Mary Shakkina C",{"name":58,"orcid":9},"Miranda Lakshmi Travis","https:\u002F\u002Fwww.ijmsrt.com\u002Fstorages\u002Fdownload-paper\u002FIJMSRT26SEP093",{"tldr":61,"method":62,"finding":63,"direction":64,"opportunity":65},"综述大语言模型可解释性技术SHAP、LIME与注意力框架及其在敏感领域的应用。","文献综述，分析SHAP、LIME、注意力解释及自然语言解释框架。","经典模型预测好但缺乏透明；SHAP\u002FLIME可识别特征重要性，但存在忠实性、幻觉等局限。","农业人工智能与决策模型","农业大模型决策可解释性研究空白：构建面向农业场景的忠实性评估基准与可解释框架。","智慧农业 \u002F 农业物联网","openalex","2026-09-25T23:30:11.362189Z",{"total":15,"page":70,"page_size":70,"items":71},1,[]]