請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/95718完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 陳祝嵩 | zh_TW |
| dc.contributor.advisor | Chu-Song Chen | en |
| dc.contributor.author | 陳姵如 | zh_TW |
| dc.contributor.author | Pei-Ju Chen | en |
| dc.date.accessioned | 2024-09-15T16:57:41Z | - |
| dc.date.available | 2024-09-16 | - |
| dc.date.copyright | 2024-09-15 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-08-13 | - |
| dc.identifier.citation | [1] J. Achiam, S. Adler, S. Agarwal, L. Ahmad, I. Akkaya, F. L. Aleman, D. Almeida, J. Altenschmidt, S. Altman, S. Anadkat, et al. Gpt-4 technical report. arXiv preprint arXiv:2303.08774, 2023.
[2] T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, et al. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901, 2020. [3] F.-T. L. P.-C. H. Y.-C. C. D.-S. S. Chan-Jan Hsu, Chang-Le Liu. Breeze-7b-instruct-v01.Accessed : 2024 − 01 − 25. [4] T. Chen, H. Wang, S. Chen, W. Yu, K. Ma, X. Zhao, D. Yu, and H. Zhang. Dense x retrieval: What retrieval granularity should we use? arXiv preprint arXiv:2312.06648, 2023. [5] S. Es, J. James, L. Espinosa-Anke, and S. Schockaert. Ragas: Automated evaluation of retrieval augmented generation. arXiv preprint arXiv:2309.15217, 2023. [6] P.Finardi,L.Avila,R.Castaldoni,P.Gengo,C.Larcher,M.Piau,P.Costa,andV.Caridá. The chronicles of rag: The retriever, the chunk and the generator. arXiv preprint arXiv:2401.07883, 2024. [7] Y. Gao, Y. Xiong, X. Gao, K. Jia, J. Pan, Y. Bi, Y. Dai, J. Sun, and H. Wang. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997, 2023. [8] K.Guu,K.Lee,Z.Tung,P.Pasupat,andM.Chang.Retrievalaugmentedlanguagemodel pre-training. In International conference on machine learning, pages 3929–3938. PMLR, 2020. [9] D. Hendrycks, C. Burns, S. Basart, A. Zou, M. Mazeika, D. Song, and J. Steinhardt. Measuring massive multitask language understanding, 2021. [10] H. Huang, T. Tang, D. Zhang, W. X. Zhao, T. Song, Y. Xia, and F. Wei. Not all lan- guages are created equal in llms: Improving multilingual capability by cross-lingual-thought prompting, 2023. [11] infgrad. stella-base-zh. Accessed: 2024-01-25. [12] infgrad. stella-large-zh. Sep 11, 2023. [13] G. Izacard, M. Caron, L. Hosseini, S. Riedel, P. Bojanowski, A. Joulin, and E. Grave. Unsupervised dense information retrieval with contrastive learning. arXiv preprint arXiv:2112.09118, 2021. [14] A. Q. Jiang, A. Sablayrolles, A. Roux, A. Mensch, B. Savary, C. Bamford, D. S. Chaplot, D. de las Casas, E. B. Hanna, F. Bressand, G. Lengyel, G. Bour, G. Lample, L. R. Lavaud, L. Saulnier, M.-A. Lachaux, P. Stock, S. Subramanian, S. Yang, S. Antoniak, T. L. Scao, T. Gervet, T. Lavril, T. Wang, T. Lacroix, and W. E. Sayed. Mixtral of experts, 2024. [15] N. Kandpal, H. Deng, A. Roberts, E. Wallace, and C. Raffel. Large language models struggle to learn long-tail knowledge, 2023. [16] V.Karpukhin,B.Oğuz,S.Min,P.Lewis,L.Wu,S.Edunov,D.Chen,andW.-t.Yih.Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906, 2020. [17] P. Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, H. Küttler, M. Lewis, W.-t. Yih, T. Rocktäschel, et al. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems, 33:9459–9474, 2020. [18] X. Li, E. Nie, and S. Liang. From classification to generation: Insights into crosslingual retrieval augmented icl. arXiv preprint arXiv:2311.06595, 2023. [19] Z. Li, X. Zhang, Y. Zhang, D. Long, P. Xie, and M. Zhang. Towards general text embed- dings with multi-stage contrastive learning. arXiv preprint arXiv:2308.03281, 2023. [20] Z. Li, X. Zhang, Y. Zhang, D. Long, P. Xie, and M. Zhang. Towards general text embed- dings with multi-stage contrastive learning, 2023. [21] Y.-T. Lin and Y.-N. Chen. Taiwan llm: Bridging the linguistic divide with a culturally aligned language model, 2023. [22] O. Ram, Y. Levine, I. Dalmedigos, D. Muhlgay, A. Shashua, K. Leyton-Brown, and Y. Shoham. In-context retrieval-augmented language models. arXiv preprint arXiv:2302.00083, 2023. [23] S. . T. P. Research and I. C. (NARLabs). taide/taide-lx-7b-chat. Accessed: 2024-07-30. [24] S. Robertson and H. Zaragoza.The Probabilistic Relevance Framework: BM25 and Beyond. Foundations and Trends® in Information Retrieval, 3(4):333–389, 2009. [25] J. Saad-Falcon, O. Khattab, C. Potts, and M. Zaharia. Ares: An automated evaluation framework for retrieval-augmented generation systems. arXiv preprint arXiv:2311.09476, 2023. [26] A. Srivastava, A. Rastogi, A. Rao, A. A. M. Shoeb, A. Abid, A. Fisch, A. R. Brown, A. Santoro, A. Gupta, A. Garriga-Alonso, A. Kluska, A. Lewkowycz, A. Agarwal, A. Power, A. Ray, A. Warstadt, A. W. Kocurek, A. Safaya, A. Tazarv, A. Xiang, A. Parrish, A. Nie, A. Hussain, A. Askell, A. Dsouza, A. Slone, A. Rahane, A. S. Iyer, A. Andreassen, A. Madotto, A. Santilli, A. Stuhlmüller, A. Dai, A. La, A. Lampinen, A. Zou, A. Jiang, A. Chen, A. Vuong, A. Gupta, A. Gottardi, A. Norelli, A. Venkatesh, A. Gholamidavoodi, A. Tabassum, A. Menezes, A. Kirubarajan, A. Mullokandov, A. Sabharwal, A. Herrick, A. Efrat, A. Erdem, A. Karakaş, B. R. Roberts, B. S. Loe, B. Zoph, B. Bojanowski, B. Özyurt, B. Hedayatnia, B. Neyshabur, B. Inden, B. Stein, B. Ekmekci, B. Y. Lin, B. Howald, B. Orinion, C. Diao, C. Dour, C. Stinson, C. Argueta, C. F. Ramírez, C. Singh, C. Rathkopf, C. Meng, C. Baral, C. Wu, C. Callison-Burch, C. Waites, C. Voigt, C. D. Manning, C. Potts, C. Ramirez, C. E. Rivera, C. Siro, C. Raffel, C. Ashcraft, C. Gar- bacea, D. Sileo, D. Garrette, D. Hendrycks, D. Kilman, D. Roth, D. Freeman, D. Khashabi, D. Levy, D. M. González, D. Perszyk, D. Hernandez, D. Chen, D. Ippolito, D. Gilboa, D. Dohan, D. Drakard, D. Jurgens, D. Datta, D. Ganguli, D. Emelin, D. Kleyko, D. Yuret, D. Chen, D. Tam, D. Hupkes, D. Misra, D. Buzan, D. C. Mollo, D. Yang, D.-H. Lee, D. Schrader, E. Shutova, E. D. Cubuk, E. Segal, E. Hagerman, E. Barnes, E. Donoway, E. Pavlick, E. Rodola, E. Lam, E. Chu, E. Tang, E. Erdem, E. Chang, E. A. Chi, E. Dyer, E. Jerzak, E. Kim, E. E. Manyasi, E. Zheltonozhskii, F. Xia, F. Siar, F. Martínez-Plumed, F. Happé, F. Chollet, F. Rong, G. Mishra, G. I. Winata, G. de Melo, G. Kruszewski, G. Parascandolo, G. Mariani, G. Wang, G. Jaimovitch-López, G. Betz, G. Gur-Ari, H. Galijasevic, H. Kim, H. Rashkin, H. Hajishirzi, H. Mehta, H. Bogar, H. Shevlin, H. Schütze, H. Yakura, H. Zhang, H. M. Wong, I. Ng, I. Noble, J. Jumelet, J. Geissinger, J. Kernion, J. Hilton, J. Lee, J. F. Fisac, J. B. Simon, J. Koppel, J. Zheng, J. Zou, J. Kocoń, J. Thompson, J. Wingfield, J. Kaplan, J. Radom, J. Sohl-Dickstein, J. Phang, J. Wei, J. Yosinski, J. Novikova, J. Bosscher, J. Marsh, J. Kim, J. Taal, J. Engel, J. Alabi, J. Xu, J. Song, J. Tang, J. Waweru, J. Burden, J. Miller, J. U. Balis, J. Batchelder, J. Berant, J. Frohberg, J. Rozen, J. Hernandez-Orallo, J. Boudeman, J. Guerr, J. Jones, J. B. Tenenbaum, J. S. Rule, J. Chua, K. Kanclerz, K. Livescu, K. Krauth, K. Gopalakrishnan, K. Ignatyeva, K. Markert, K. D. Dhole, K. Gimpel, K. Omondi, K. Mathewson, K. Chiafullo, K. Shkaruta, K. Shridhar, K. McDonell, K. Richardson, L. Reynolds, L. Gao, L. Zhang, L. Dugan, L. Qin, L. Contreras-Ochando, L.-P. Morency, L. Moschella, L. Lam, L. No- ble, L. Schmidt, L. He, L. O. Colón, L. Metz, L. K. Şenel, M. Bosma, M. Sap, M. ter Hoeve, M. Farooqi, M. Faruqui, M. Mazeika, M. Baturan, M. Marelli, M. Maru, M. J. R. Quintana, M. Tolkiehn, M. Giulianelli, M. Lewis, M. Potthast, M. L. Leavitt, M. Hagen, M. Schubert, M. O. Baitemirova, M. Arnaud, M. McElrath, M. A. Yee, M. Cohen, M. Gu, M. Ivanitskiy, M. Starritt, M. Strube, M. Swędrowski, M. Bevilacqua, M. Yasunaga, M. Kale, M. Cain, M. Xu, M. Suzgun, M. Walker, M. Tiwari, M. Bansal, M. Aminnaseri, M. Geva, M. Gheini, M. V. T, N. Peng, N. A. Chi, N. Lee, N. G.-A. Krakover, N. Cameron, N. Roberts, N. Doiron, N. Martinez, N. Nangia, N. Deckers, N. Muennighoff, N. S. Keskar, N. S. Iyer, N. Constant, N. Fiedel, N. Wen, O. Zhang, O. Agha, O. Elbaghdadi, O. Levy, O. Evans, P. A. M. Casares, P. Doshi, P. Fung, P. P. Liang, P. Vicol, P. Alipoormolabashi, P. Liao, P. Liang, P. Chang, P. Eckersley, P. M. Htut, P. Hwang, P. Miłkowski, P. Patil, P. Pezeshkpour, P. Oli, Q. Mei, Q. Lyu, Q. Chen, R. Banjade, R. E. Rudolph, R. Gabriel, R. Habacker, R. Risco, R. Millière, R. Garg, R. Barnes, R. A. Saurous, R. Arakawa, R. Raymaekers, R. Frank, R. Sikand, R. Novak, R. Sitelew, R. LeBras, R. Liu, R. Jacobs, R. Zhang, R. Salakhutdinov, R. Chi, R. Lee, R. Stovall, R. Teehan, R. Yang, S. Singh, S. M. Mohammad, S. Anand, S. Dillavou, S. Shleifer, S. Wiseman, S. Gruetter, S. R. Bowman, S. S. Schoenholz, S. Han, S. Kwatra, S. A. Rous, S. Ghazarian, S. Ghosh, S. Casey, S. Bischoff, S. Gehrmann, S. Schuster, S. Sadeghi, S. Hamdan, S. Zhou, S. Srivastava, S. Shi, S. Singh, S. Asaadi, S. S. Gu, S. Pachchigar, S. Toshniwal, S. Upadhyay, Shyamolima, Debnath, S. Shakeri, S. Thormeyer, S. Melzi, S. Reddy, S. P. Makini, S.-H. Lee, S. Torene, S. Hatwar, S. Dehaene, S. Divic, S. Ermon, S. Bi- derman, S. Lin, S. Prasad, S. T. Piantadosi, S. M. Shieber, S. Misherghi, S. Kiritchenko, S. Mishra, T. Linzen, T. Schuster, T. Li, T. Yu, T. Ali, T. Hashimoto, T.-L. Wu, T. Desbordes, T. Rothschild, T. Phan, T. Wang, T. Nkinyili, T. Schick, T. Kornev, T. Tunduny, T. Gerstenberg, T. Chang, T. Neeraj, T. Khot, T. Shultz, U. Shaham, V. Misra, V. Dem- berg, V. Nyamai, V. Raunak, V. Ramasesh, V. U. Prabhu, V. Padmakumar, V. Srikumar, W. Fedus, W. Saunders, W. Zhang, W. Vossen, X. Ren, X. Tong, X. Zhao, X. Wu, X. Shen, Y. Yaghoobzadeh, Y. Lakretz, Y. Song, Y. Bahri, Y. Choi, Y. Yang, Y. Hao, Y. Chen, Y. Belinkov, Y. Hou, Y. Hou, Y. Bai, Z. Seid, Z. Zhao, Z. Wang, Z. J. Wang, Z. Wang, and Z. Wu. Beyond the imitation game: Quantifying and extrapolating the capabilities of language models, 2023. [27] Z.-R. Tam and Y.-T. Pai. An improved traditional chinese evaluation suite for foundation model. arXiv, 2023. [28] H.Touvron,L.Martin,K.Stone,P.Albert,A.Almahairi,Y.Babaei,N.Bashlykov,S.Batra, P. Bhargava, S. Bhosale, et al. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288, 2023. [29] H. Trivedi, N. Balasubramanian, T. Khot, and A. Sabharwal. Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions. arXiv preprint arXiv:2212.10509, 2022. [30] A. Wang, Y. Pruksachatkun, N. Nangia, A. Singh, J. Michael, F. Hill, O. Levy, and S. Bowman. Superglue: A stickier benchmark for general-purpose language understanding systems. Advances in neural information processing systems, 32, 2019. [31] L. Wang, N. Yang, X. Huang, L. Yang, R. Majumder, and F. Wei. Improving text embed- dings with large language models. arXiv preprint arXiv:2401.00368, 2023. [32] T. Wu, Y. Qin, E. Zhang, Z. Xu, Y. Gao, K. Li, and X. Sun. Towards robust text retrieval with progressive learning, 2023. [33] S. Xiao, Z. Liu, P. Zhang, and N. Muennighoff. C-pack: Packaged resources to advance general chinese embedding, 2023. [34] yentinglin. bert-base-zhtw. Accessed: 2024-01-25. [35] W.Yu,D.Iter,S.Wang,Y.Xu,M.Ju,S.Sanyal,C.Zhu,M.Zeng,andM.Jiang.Generate rather than retrieve: Large language models are strong context generators, 2023. [36] Y. Zhang, Y. Li, L. Cui, D. Cai, L. Liu, T. Fu, X. Huang, E. Zhao, Y. Zhang, Y. Chen, L. Wang, A. T. Luu, W. Bi, F. Shi, and S. Shi. Siren’s song in the ai ocean: A survey on hallucination in large language models, 2023. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/95718 | - |
| dc.description.abstract | 大型語言模型(LLM)可謂是 2023 年人工智慧領域中最為熱門的名詞之一，而其在各種場景中的應用方法之一即為檢索增強生成(RAG)，因此受到廣泛關注。雖然在學術界受到高度重視，但目前在實際生活中的應用仍相對有限。為此，本論文特別選擇了一個與我身為學生緊密相關的場域 ── 學校，成功地將檢索增 強生成的大型語言模型應用於實際生活中。在語言模型資源相對較為匱乏的繁體 中文情境中，這篇作品整合了多項技術包含網頁爬蟲及網頁資料清理、嵌入檢索(embedding retrieval)、文檔切分最佳化、前後端、line 聊天機器人 UI 整合，最終取得了成功的應用。實現將技術應用到實際情境中的重要里程碑，檢索增強生成 的大語言模型朝著實現高品質、個人化支持及普及化的目標邁進。 | zh_TW |
| dc.description.abstract | Large Language Models (LLMs) can be considered one of the hottest terms in the field of artificial intelligence in 2023, and one of their application methods among various scenarios is Retrieval-Augmented Generation (RAG), which attracts widespread attention. Although highly regarded in the academia, their practical applications in real life are relatively limited. Therefore, this paper specifically chooses a field closely related to me as a student—school—and successfully applied the Retrieval-Augmented Generation of LLMs to real-life situations. In the context of Traditional Chinese where language model resources are relatively scarce, this work integrates multiple technologies, including web crawling and data cleaning, embedding retrieval, chunk optimization, front-end and back-end development, and Line chatbot UI integration, ultimately achieving successful application. This milestone in applying technology to real-world scenarios propels LLMs in Retrieval-Augmented Generation towards the goals of achieving high-quality, personalized support, and widespread use. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-09-15T16:57:41Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-09-15T16:57:41Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | Acknowledgements i
摘要 ii Abstract iii Contents v List of Figures vii List of Tables viii Chapter 1 Introduction 1 1.1 Motivation ............................... 1 Chapter 2 Related Works 4 2.1 RetrievalAugmentedGeneration ................... 4 2.2 Retrieval ................................ 5 2.2.1 Chunk optimization.......................... 5 2.2.2 EmbeddingModels .......................... 6 2.3 Generation ............................... 7 2.4 RAGEvaluation ............................ 7 Chapter 3 Method 9 3.1 Problem Definition........................... 9 3.2 Database Construction ......................... 9 3.3 TestDatasetConstruction ....................... 10 3.3.1 FAQs sourced from web pages .................... 10 3.3.2 Synthetic dataset generated using ChatGPT . . . . . . . . . . . . . 11 3.4 Retrieval ................................ 12 3.4.1 Chunking and Pre-processing..................... 12 3.4.2 Vectorize ............................... 13 3.5 Generation ............................... 14 Chapter 4 Experiments 15 4.1 Automated Evaluation ......................... 15 4.1.1 Evaluation of Answer Quality .................... 17 4.1.2 Evaluation of Retrieval Quality and LLM Comprehension . . . . . . 18 4.2 Human Evaluation ........................... 19 4.2.1 Answer Similarity........................... 21 4.2.2 Answer Precision ........................... 21 4.2.3 Model Preferences .......................... 22 4.3 Ablation Study ............................. 23 4.4 Implementation Detail ......................... 25 Chapter 5 Conclusion 26 References 27 | - |
| dc.language.iso | en | - |
| dc.title | 改變校園對話：基於具檢索增強生成的大語言模型聊天機器人 | zh_TW |
| dc.title | Revolutionizing Campus Conversation: LLM-Powered Chatbot with Retrieval-Augmented Generation | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.coadvisor | 陳駿丞 | zh_TW |
| dc.contributor.coadvisor | Jun-Cheng Chen | en |
| dc.contributor.oralexamcommittee | 陳光華;楊惠芳 | zh_TW |
| dc.contributor.oralexamcommittee | Kuang-Hua Chen;Huei-Fang Yang | en |
| dc.subject.keyword | 大語言模型,檢索增強生成,校園個人助理, | zh_TW |
| dc.subject.keyword | Large Language Models,Retrieval-Augmented Generation,Campus Personal Assistant, | en |
| dc.relation.page | 33 | - |
| dc.identifier.doi | 10.6342/NTU202400247 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2024-08-14 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 資料科學學位學程 | - |
| 顯示於系所單位： | 資料科學學位學程 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-112-2.pdf | 1.16 MB | Adobe PDF | 檢視/開啟 |
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。