{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T03:18:15Z","timestamp":1758079095442,"version":"3.44.0"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686196","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,16]]},"abstract":"<jats:p>In recent years, artificial intelligence technologies represented by large language models (LLMs) have achieved breakthrough progress, driving the development of intelligent applications across various domains. However, LLMs still face several challenges in practical applications, including knowledge update latency, hallucination in generated content, and persistent biases that are difficult to eliminate. This paper investigates the decision-making preferences and behavioral patterns of LLMs when inconsistencies arise between their internal parameterized knowledge and externally retrieved information enhanced by retrieval-augmented techniques. We propose a systematic evaluation method for assessing LLMs\u2019 internal knowledge dependency. First, we establish a data augmentation method for knowledge-intensive question-answering tasks to construct an evaluation dataset. Using the spaCy entity categorization tool combined with an LLM-based verification and filtering mechanism, we classify and annotate entities in QA datasets and corpora. Through LLM-integrated entity recognition and substitution techniques, we generate logically consistent transformed facts and corresponding questions on the TriviaQA dataset, automatically constructing a synthetic transformed fact dataset. Next, we integrate retrieval-augmented LLMs and conduct a systematic evaluation of multiple mainstream LLMs. By comparing model performance differences on original versus transformed facts, we quantitatively analyze their knowledge dependency and generation controllability, revealing significant variations across models and exposing limitations in existing LLM evaluation methods. Additionally, this paper evaluates the impact of different prompting techniques on models\u2019 internal knowledge dependency. Experimental results show that all tested models exhibit varying degrees of reliance on internal knowledge, where chain-of-thought prompting tends to reinforce this dependency, while appropriate instruction design can partially mitigate it. We provide a dialectical analysis of the dual nature of LLMs\u2019 internal knowledge: while such knowledge effectively resists misinformation interference and defends against malicious knowledge injection attacks, it also hinders knowledge updates and reduces model flexibility.<\/jats:p>","DOI":"10.3233\/faia250565","type":"book-chapter","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T13:20:24Z","timestamp":1758028824000},"source":"Crossref","is-referenced-by-count":0,"title":["Research on the Dependence of Large Language Models on Internal Parameterized Knowledge Under Retrieval-Augmented Techniques"],"prefix":"10.3233","author":[{"given":"Shaoyang","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Information Management and Engineering, Shanghai University of Finance and Economics, Shanghai, China, Email: linuszsy@163.com"}]},{"given":"Yinglin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Shanghai University of Finance and Economics, Shanghai, China, Email: wang.yinglin@shufe.edu.cn"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","New Trends in Intelligent Software Methodologies, Tools and Techniques"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA250565","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T13:20:24Z","timestamp":1758028824000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA250565"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"ISBN":["9781643686196"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia250565","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,16]]}}}