請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/93281完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 陳信希 | zh_TW |
| dc.contributor.advisor | Hsin-Hsi Chen | en |
| dc.contributor.author | 張家誠 | zh_TW |
| dc.contributor.author | Chia-Cheng Chang | en |
| dc.date.accessioned | 2024-07-23T16:39:46Z | - |
| dc.date.available | 2024-07-24 | - |
| dc.date.copyright | 2024-07-23 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-07-22 | - |
| dc.identifier.citation | AI@Meta. Llama 3 model card. 2024.
Yuntao Bai, Saurav Kadavath, Sandipan Kundu, Amanda Askell, Jackson Kernion, Andy Jones, Anna Chen, Anna Goldie, Azalia Mirhoseini, Cameron McKinnon, Carol Chen, Catherine Olsson, Christopher Olah, Danny Hernandez, Dawn Drain, Deep Ganguli, Dustin Li, Eli Tran-Johnson, Ethan Perez, Jamie Kerr, Jared Mueller, Jeffrey Ladish, Joshua Landau, Kamal Ndousse, Kamile Lukosuite, Liane Lovitt, Michael Sellitto, Nelson Elhage, Nicholas Schiefer, Noemi Mercado, Nova DasSarma, Robert Lasenby, Robin Larson, Sam Ringer, Scott Johnston, Shauna Kravec, Sheer El Showk, Stanislav Fort, Tamera Lanham, Timothy Telleen-Lawton, Tom Conerly, Tom Henighan, Tristan Hume, Samuel R. Bowman, Zac Hatfield-Dodds, Ben Mann, Dario Amodei, Nicholas Joseph, Sam McCandlish, Tom Brown, and Jared Kaplan. Constitutional ai: Harmlessness from ai feedback, 2022. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. Language models are few-shot learners. In H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin, editors, Advances in Neural Information Processing Systems, volume 33, pages 1877–1901. Curran Associates, Inc., 2020a. Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. Language models are few-shot learners. In Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS ’20, Red Hook, NY, USA, 2020b. Curran Associates Inc. ISBN 9781713829546. Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E. Gonzalez, Ion Stoica, and Eric P. Xing. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality, March 2023. Yihe Deng, Weitong Zhang, Zixiang Chen, and Quanquan Gu. Rephrase and respond: Let large language models ask better questions for themselves, 2024. Shehzaad Zuzar Dhuliawala, Mojtaba Komeili, Jing Xu, Roberta Raileanu, Xian Li, Asli Celikyilmaz, and Jason E Weston. Chain-of-verification reduces hallucination in large language models, 2024. Aiden R. Doherty, Niamh Caprani, Ciarán Ó Conaire, Vaiva Kalnikaite, Cathal Gurrin, Alan F. Smeaton, and Noel E. O＇Connor. Passively recognising human activities through lifelogging. Computers in Human Behavior, 27(5):1948–1958, 2011. ISSN 0747-5632. doi: https://doi.org/10.1016/j.chb.2011.05.002. 2009 Fifth International Conference on Intelligent Computing. Mohan Rajesh Elara, Lee Hyowon, K. S. Jaichandar, and Carlos Acosta Antonio Calderon. Lifevision: integrating heart rate sensing in lifelogging camera for accurate risk diagnosis for the elderly. In Proceedings of the 6th International Conference on Rehabilitation Engineering & Assistive Technology, i-CREATe ’12, Midview City, SGP, 2012. Singapore Therapeutic, Assistive & Rehabilitative Technologies (START) Centre. ISBN 9789810726638. Cathal Gurrin, Hideo Joho, Frank Hopfgartner, Liting Zhou, and Rami Albatal. Ntcir lifelog: The first test collection for lifelog research. In Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’16, page 705–708, New York, NY, USA, 2016. Association for Computing Machinery. ISBN 9781450340694. doi: 10.1145/2911451.2914680. Cathal Gurrin, Hideo Joho, Frank Hopfgartner, Liting Zhou, Duc-Tien Dang-Nguyen, Rashmi Gupta, and Rami Albatal. Overview of NTCIR-13 lifelog-2 task. In The 13th NTCIR Conference, Evaluation of Information Access Technologies, National Center of Sciences, Tokyo, Japan, December 5-8, 2017. National Institute of Informatics (NII), 2017. Cathal Gurrin, H. Joho, Frank Hopfgartner, Liting Zhou, Tu Ninh, Tu-Khiem Le, Rami Albatal, Đặng Nguyên, and Graham Healy. Overview of the ntcir-14 lifelog-3 task. 06 2019. Cathal Gurrin, Tu-Khiem Le, Van-Tu Ninh, Duc-Tien Dang-Nguyen, Björn Þór Jónsson, Jakub Lokoč, Wolfgang Hürst, Minh-Triet Tran, and Klaus Schöffmann. Introduction to the third annual lifelog search challenge (lsc’20). In Proceedings of the 2020 International Conference on Multimedia Retrieval, ICMR ’20, page 584–585, New York, NY, USA, 2020. Association for Computing Machinery. ISBN 9781450370875. doi: 10.1145/3372278.3388043. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, and Ting Liu. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions, 2023. Shaoxiong Ji, Shirui Pan, Erik Cambria, Pekka Marttinen, and Philip S. Yu. A survey on knowledge graphs: Representation, acquisition, and applications. IEEE Transactions on Neural Networks and Learning Systems, 33(2):494–514, 2022. doi: 10.1109/TNNLS. 2021.3070843. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. BART: Denoising sequence-tosequence pre-training for natural language generation, translation, and comprehension. In Dan Jurafsky, Joyce Chai, Natalie Schluter, and Joel Tetreault, editors, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7871–7880, Online, July 2020. Association for Computational Linguistics. doi: 10. 18653/v1/2020.acl-main.703. Jiwei Li, Alan Ritter, Claire Cardie, and Eduard Hovy. Major life event extraction from Twitter based on congratulations/condolences speech acts. In Alessandro Moschitti, Bo Pang, and Walter Daelemans, editors, Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1997–2007, Doha, Qatar, October 2014. Association for Computational Linguistics. doi: 10.3115/v1/D14-1214. You-En Lin, An-Zi Yen, Hen-Hsen Huang, and Hsin-Hsi Chen. SEEN: Structured event enhancement network for explainable need detection of information recall assistance. In Yoav Goldberg, Zornitsa Kozareva, and Yue Zhang, editors, Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 5438–5451, Abu Dhabi, United Arab Emirates, December 2022. Association for Computational Linguistics. doi: 10.18653/v1/2022.emnlp-main.365. Xinbei Ma, Yeyun Gong, Pengcheng He, Hai Zhao, and Nan Duan. Query rewriting for retrieval-augmented large language models, 2023. Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe,Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, Shashank Gupta, Bodhisattwa Prasad Majumder, Katherine Hermann, Sean Welleck, Amir Yazdanbakhsh, and Peter Clark. Self-refine: Iterative refinement with self-feedback. In Thirty-seventh Conference on Neural Information Processing Systems, 2023. Takuya Maekawa. A sensor device for automatic food lifelogging that is embedded in home ceiling light: A preliminary investigation. In 2013 7th International Conference on Pervasive Computing Technologies for Healthcare and Workshops, pages 405–407, 2013. doi: 10.4108/icst.pervasivehealth.2013.252128. OpenAI. Chatgpt, 2023. Shirui Pan, Linhao Luo, Yufei Wang, Chen Chen, Jiapu Wang, and Xindong Wu. Unifying large language models and knowledge graphs: A roadmap. IEEE Transactions on Knowledge and Data Engineering, 36(7):3580–3599, 2024. doi: 10.1109/TKDE.2024.3352100. Ciyuan Peng, Feng Xia, Mehdi Naseriparsa, and Francesco Osborne. Knowledge graphs: Opportunities and challenges, 2023. Ofir Press, Muru Zhang, Sewon Min, Ludwig Schmidt, Noah A. Smith, and Mike Lewis. Measuring and narrowing the compositionality gap in language models, 2023. Alec Radford and Karthik Narasimhan. Improving language understanding by generative pre-training. 2018. Alec Radford, Jeff Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. Language models are unsupervised multitask learners. 2019. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res., 21(1), jan 2020. ISSN 1532-4435. Nils Reimers and Iryna Gurevych. Sentence-bert: Sentence embeddings using siamese bert-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 11 2019a. Nils Reimers and Iryna Gurevych. Sentence-BERT: Sentence embeddings using Siamese BERT-networks. In Kentaro Inui, Jing Jiang, Vincent Ng, and Xiaojun Wan, editors, Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3982–3992, Hong Kong, China, November 2019b. Association for Computational Linguistics. doi: 10.18653/v1/D19-1410. Y. Shi, H. Ma, W. Zhong, Q. Tan, G. Mai, X. Li, T. Liu, and J. Huang. Chatgraph: Interpretable text classification by converting chatgpt knowledge to graphs. In 2023 IEEE International Conference on Data Mining Workshops (ICDMW), pages 515–520, Los Alamitos, CA, USA, dec 2023. IEEE Computer Society. doi: 10.1109/ICDMW60847.2023.00073. Jiabin Tang, Yuhao Yang, Wei Wei, Lei Shi, Lixin Su, Suqi Cheng, Dawei Yin, and Chao Huang. Graphgpt: Graph instruction tuning for large language models, 2024. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. Self-consistency improves chain of thought reasoning in language models, 2023. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed Huai hsin Chi, F. Xia, Quoc Le, and Denny Zhou. Chain of thought prompting elicits reasoning in large language models. ArXiv, abs/2201.11903, 2022. Yilin Wen, Zifeng Wang, and Jimeng Sun. Mindmap: Knowledge graph prompting sparks graph of thoughts in large language models, 2024. An-Zi Yen, Hen-Hsen Huang, and Hsin-Hsi Chen. Personal knowledge base construction from text-based lifelogs. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR’19, page 185–194, New York, NY, USA, 2019. Association for Computing Machinery. ISBN 9781450361729. doi: 10.1145/3331184.3331209. An-Zi Yen, Hen-Hsen Huang, and Hsin-Hsi Chen. Multimodal joint learning for personal knowledge base construction from twitter-based lifelogs. Information Processing Management, 57(6):102148, 2020. ISSN 0306-4573. doi: https://doi.org/10.1016/j.ipm.2019.102148. An-Zi Yen, Hen-Hsen Huang, and Hsin-Hsi Chen. Ten questions in lifelog mining and information recall. In Proceedings of the 2021 International Conference on Multimedia Retrieval, ICMR ’21, page 511–518, New York, NY, USA, 2021a. Association for Computing Machinery. ISBN 9781450384636. doi: 10.1145/3460426.3463607. An-Zi Yen, Hen-Hsen Huang, and Hsin-Hsi Chen. Unanswerable question correction in question answering over personal knowledge base. Proceedings of the AAAI Conference on Artificial Intelligence, 35(16):14266–14275, May 2021b. doi: 10.1609/aaai.v35i16.17678. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/93281 | - |
| dc.description.abstract | 在日常生活中，人們常會碰到需要回憶過往生活的時刻。然而人們不可能記得每一個細節，因此提供一個可以主動地去提醒人們是否有細節被遺忘或錯置的系統便相當重要。在此研究中，我們著重於兩個目標：如何透過大型語言模型來進行主動式的資訊召回和如何將個人化的知識圖譜運用於提升原始模型的能力。
我們在架構中導入了一個用於修正原始答案的模組，此模組會分析來自於知識圖譜模組的資訊，藉此來改善原始模型預測的結果。在實驗結果中表明，我們的架構不僅能夠提升ChatGPT和Llama3等大型語言模型的性能，也能運用在不同的SOTA模型。 整體來說，我們的研究提出了一個新架構，不僅可以用於加強原始模型的準確率，且在彈性高的特性下，我們可以替換不同的原始模型及搜索知識圖譜的方式，讓模型的成效有更進一步的提升。這個架構不僅在主動式資訊召回這個任務下取得不錯的結果，同時也為其他領域的研究提供了如何利用知識圖譜來運用大型語言模型的方法。 | zh_TW |
| dc.description.abstract | Several studies have focused on developing information recall systems to help individuals remember their personal life experiences. This is due to the fact that people cannot recall every detail of their life events and may sometimes confuse different events. Providing a system that can proactively remind individuals of forgotten or confused details is therefore essential. Recent advancements in large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation. Many works are also exploring how to integrate LLMs into personalized applications. This thesis focuses on two objectives: (1) leveraging LLMs for proactive information recall and (2) introducing personal knowledge graphs to augment the capabilities of detecting information recall needs by refining the decision. We construct a framework that incorporates a refinement module to consult structure information from personal knowledge graph, thereby achieving precise recall support. This framework offers high flexibility, allowing for the replacement of different base models and modification of fact retrieval methods to further improve robustness. Experimental results show that our framework more effectively aids in detecting forgotten events, achieving the goal of helping users recall past experiences. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-07-23T16:39:46Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-07-23T16:39:46Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | Acknowledgements i
摘要 ii Abstract iii Contents v List of Figures viii List of Tables ix Chapter 1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 Thesis Organization . . . . . . . . . . . . . . . . . . . . . . . . . . 4 Chapter 2 Related Work . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 2.1 Lifelogging . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 2.2 Proactive Information Recall . . . . . . . . . . . . . . . . . . . . . . 6 2.3 Large Language Model with Knowledge Graph . . . . . . . . . . . . 7 2.3.1 Large Language Model . . . . . . . . . . . . . . . . . . . . . . . . 7 2.3.2 Knowledge Graph . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.3.3 Cooperation between LLMs and KG . . . . . . . . . . . . . . . . . 8 2.4 Refinement for LLMs . . . . . . . . . . . . . . . . . . . . . . . . . 9 Chapter 3 Methodology . . . . . . . . . . . . . . . . . . . . . . . . . 12 3.1 Task Definition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 3.2 Graph-Empowered Refinement Framework . . . . . . . . . . . . . . 14 3.2.1 Overall Framework . . . . . . . . . . . . . . . . . . . . . . . . . . 14 3.2.2 Base Module–Direct Prediction . . . . . . . . . . . . . . . . . . . . 15 3.2.3 Support Module–Event Prediction . . . . . . . . . . . . . . . . . . 17 3.2.3.1 Knowledge Graph-based Prediction . . . . . . . . . . . 18 3.2.3.2 LLM-based Prediction . . . . . . . . . . . . . . . . . . 20 3.2.4 Correction Module–Correction Prediction . . . . . . . . . . . . . . 21 3.3 Label Mapper Algorithm . . . . . . . . . . . . . . . . . . . . . . . . 24 Chapter 4 Experiments . . . . . . . . . . . . . . . . . . . . . . . . . 27 4.1 Baseline Models . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27 4.2 Experiment Setup . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 4.3 Experimental Results . . . . . . . . . . . . . . . . . . . . . . . . . . 29 4.3.1 Main Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29 4.3.2 Results with Different Base Module . . . . . . . . . . . . . . . . . 31 4.3.2.1 GPT3.5 as the Base module . . . . . . . . . . . . . . . 32 4.3.2.2 Llama3 70B as the Base module . . . . . . . . . . . . 32 4.3.2.3 SEEN (Longformer-base) as the Base Module . . . . . 33 4.3.2.4 SEEN (Longformer-large) as the Base module . . . . . 34 Chapter 5 Analysis and Discussion . . . . . . . . . . . . . . . . . . . . . . . . . 35 5.1 The Impact of Support Module . . . . . . . . . . . . . . . . . . . . . 35 5.2 The Importance of Each Module . . . . . . . . . . . . . . . . . . . . 37 5.3 The Impact of Story Length . . . . . . . . . . . . . . . . . . . . . . 39 5.4 Error Analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40 5.5 The Limitation of Large Language Models for Proactive Information Recall . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 43 Chapter 6 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 46 References . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48 | - |
| dc.language.iso | en | - |
| dc.subject | 生活日誌 | zh_TW |
| dc.subject | 主動資訊召回 | zh_TW |
| dc.subject | 大型語言模型 | zh_TW |
| dc.subject | 個人知識圖譜 | zh_TW |
| dc.subject | 答案精煉 | zh_TW |
| dc.subject | Large Language Model | en |
| dc.subject | Lifelogging | en |
| dc.subject | Answer Refinement | en |
| dc.subject | Personal Knowledge Graph | en |
| dc.subject | Proactive Information Recall | en |
| dc.title | 基於個人化圖譜增強大型語言模型於主動式資訊召回之研究 | zh_TW |
| dc.title | Personalized Graph-Empowered Large Language Model with Correction for Proactive Information Recall | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 陳建錦;蔡宗翰;陳柏琳 | zh_TW |
| dc.contributor.oralexamcommittee | Chien-Chin Chen;Tzong-Han Tsai;Berlin Chen | en |
| dc.subject.keyword | 生活日誌,主動資訊召回,大型語言模型,個人知識圖譜,答案精煉, | zh_TW |
| dc.subject.keyword | Lifelogging,Proactive Information Recall,Large Language Model,Personal Knowledge Graph,Answer Refinement, | en |
| dc.relation.page | 55 | - |
| dc.identifier.doi | 10.6342/NTU202402006 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2024-07-23 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 資訊工程學系 | - |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-112-2.pdf 未授權公開取用 | 1.69 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。