{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T09:49:58Z","timestamp":1767260998478,"version":"3.41.2"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T00:00:00Z","timestamp":1723075200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Online question-and-answer (Q&amp;amp;A) platforms are frequently replete with extensive human resource support. This study proposes a novel methodology of a customized large language model (LLM) called Chaotic LLM-based Educational Q&amp;amp;A System (CHAQS) to navigate the complexities associated with intelligent Q&amp;amp;A systems for the educational sector.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>It uses an expansive dataset comprising over 383,000 educational data pairs, an intricate fine-tuning process encompassing p-tuning v2, low-rank adaptation (LRA), and strategies for parameter freezing at an open-source large language model ChatGLM as a baseline model. In addition, Fuzzy Logic is implemented to regulate parameters and the system's adaptability with the Lee Oscillator to refine the model's response variability and precision.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Experiment results showed a 5.12% improvement in precision score, an 11% increase in recall metric, and an 8% improvement in the F1 score as compared to other models.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>These results suggest that the CHAQS methodology significantly enhances the performance of educational Q&amp;amp;A systems, demonstrating the effectiveness of combining advanced tuning techniques and fuzzy logic for improved model precision and adaptability.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2024.1404940","type":"journal-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T05:10:44Z","timestamp":1723093844000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Enhancing educational Q&amp;A systems using a Chaotic Fuzzy Logic-Augmented large language model"],"prefix":"10.3389","volume":"7","author":[{"given":"Haoyuan","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nuobei","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ling","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raymond","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2024,8,8]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2403.04652","article-title":"Yi: Open Foundation Models by 01.AI","author":"AI","year":"2024","journal-title":"arXiv preprint"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2309.16609","article-title":"Qwen Technical Report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2310.02031","article-title":"OceanGPT: A Large Language Model for Ocean Science Tasks","author":"Bi","year":"2023","journal-title":"arXiv preprint"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2306.16092","article-title":"ChatLaw: Open-Source Legal Large Language Model with Integrated External Knowledge Bases","author":"Cui","year":"2023","journal-title":"arXiv preprint"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2308.02773","article-title":"EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education","author":"Dan","year":"2023","journal-title":"arXiv preprint"},{"key":"B6","doi-asserted-by":"publisher","first-page":"2940","DOI":"10.3390\/su15042940","article-title":"A meta-analysis and systematic review of the effect of chatbot technology use in sustainable education","volume":"15","author":"Deng","year":"2023","journal-title":"Sustainability"},{"key":"B7","doi-asserted-by":"publisher","first-page":"320","DOI":"10.18653\/v1\/2022.acl-long.26","article-title":"GLM: general language model pretraining with autoregressive blank infilling","volume":"1","author":"Du","year":"2022","journal-title":"Proc. 60th Annu. Meet. Assoc. Comput. Linguist"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2407.02977","article-title":"Large language models as evaluators for scientific synthesis","author":"Evans","year":"2024","journal-title":"arXiv preprint"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2112.13677","article-title":"Agent smith: teaching question answering to Jill Watson","author":"Goel","year":"2021","journal-title":"arXiv preprint"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2106.09685","article-title":"\u201cLoRA: Low-Rank Adaptation of Large Language Models,\u201d","author":"Hu","year":"2022","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1228","DOI":"10.1109\/TNN.2004.832729","article-title":"A transient-chaotic autoassociative network (TCAN) based on Lee Oscillators","volume":"15","author":"Lee","year":"2004","journal-title":"IEEE Trans. Neural Netw."},{"volume-title":"Quantum Finance: Intelligent Forecast and Trading Systems","year":"2019","author":"Lee","key":"B12"},{"key":"B13","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1109\/TFUZZ.2019.2914642","article-title":"Chaotic type-2 transient-fuzzy deep neuro-oscillatory network (CT2TFDNN) for worldwide financial prediction","volume":"28","author":"Lee","year":"2020","journal-title":"IEEE Trans. Fuzzy Syst"},{"key":"B14","first-page":"61","article-title":"\u201cP-tuning: prompt tuning can be comparable to fine-tuning across scales and tasks,\u201d","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","author":"Liu","year":""},{"key":"B15","first-page":"61","article-title":"\u201cP-Tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks,\u201d","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, Vol. 2","author":"Liu","year":""},{"key":"B16","first-page":"311","article-title":"\u201cBLEU: a method for automatic evaluation of machine translation,\u201d","volume-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics","author":"Papineni","year":"2002"},{"key":"B17","doi-asserted-by":"publisher","first-page":"4603237","DOI":"10.2139\/ssrn.4603237","article-title":"Enhancing mathematical capabilities through ChatGPT and similar generative artificial intelligence: roles and challenges in solving mathematical problems","volume":"2023","author":"Rane","year":"2023","journal-title":"SSRN Electron. J"},{"key":"B18","first-page":"255","article-title":"\u201cExploiting cloze-questions for few-shot text classification and natural language inference,\u201d","volume-title":"Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume","author":"Schick","year":"2021"},{"key":"B19","first-page":"4215","article-title":"\u201cLarge language models are not yet human-level evaluators for abstractive summarization,\u201d","author":"Shen","year":"2023","journal-title":"Findings of the Association for Computational Linguistics: EMNLP 2023"},{"key":"B20","doi-asserted-by":"crossref","first-page":"785","DOI":"10.18653\/v1\/2023.bea-1.64","article-title":"\u201cThe BEA 2023 shared task on generating AI teacher responses in educational dialogues,\u201d","volume-title":"Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)","author":"Tack","year":"2023"},{"key":"B21","doi-asserted-by":"crossref","first-page":"438","DOI":"10.1145\/3408877.3432395","article-title":"\u201cGender and engagement in CS courses on piazza,\u201d","volume-title":"Proceedings of the 52nd ACM Technical Symposium on Computer Science Education","author":"Thinnyun","year":"2021"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2307.09288","article-title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.24251\/HICSS.2022.258","article-title":"\u201cAttachment theory as a framework to understand relationships with social chatbots: a case study of Replika,\u201d","author":"Xie","year":"2022","journal-title":"Proceedings of the 55th Hawaii International Conference on System Sciences"},{"year":"2023","author":"Yang","journal-title":"Baichuan 2: Open Large-scale Language Models","key":"B24"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2403.11858","article-title":"GPT-4 as Evaluator: Evaluating Large Language Models on Pest Management in Agriculture","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2305.07490","article-title":"ArtGPT-4: Towards Artistic-Understanding Large Vision-Language Models With Enhanced Adapter","author":"Yuan","year":"2023","journal-title":"arXiv preprint"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2305.15075","article-title":"HuatuoGPT, Towards Taming Language Model to Be a Doctor","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1904.09675","article-title":"\u201cBERTScore: Evaluating Text Generation With BERT,\u201d","author":"Zhang","year":"2019","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"B29","doi-asserted-by":"publisher","first-page":"3848","DOI":"10.1109\/TITS.2019.2935152","article-title":"T-GCN: a temporal graph convolutional network for traffic prediction","volume":"21","author":"Zhao","year":"2020","journal-title":"IEEE Trans. Intell. Transp. Syst"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1404940\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T05:11:02Z","timestamp":1723093862000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1404940\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,8]]},"references-count":29,"alternative-id":["10.3389\/frai.2024.1404940"],"URL":"https:\/\/doi.org\/10.3389\/frai.2024.1404940","relation":{},"ISSN":["2624-8212"],"issn-type":[{"type":"electronic","value":"2624-8212"}],"subject":[],"published":{"date-parts":[[2024,8,8]]},"article-number":"1404940"}}