請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/94836完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 傅立成 | zh_TW |
| dc.contributor.advisor | Li-Chen Fu | en |
| dc.contributor.author | 廖政華 | zh_TW |
| dc.contributor.author | Cheng-Hua Liao | en |
| dc.date.accessioned | 2024-08-19T17:20:47Z | - |
| dc.date.available | 2024-08-20 | - |
| dc.date.copyright | 2024-08-19 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-08-06 | - |
| dc.identifier.citation | [1] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. u.Kaiser, and I. Polosukhin, “Attention is all you need,” in Advances in NeuralInformation Processing Systems, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach,R. Fergus, S. Vishwanathan, and R. Garnett, Eds., vol. 30. Curran Associates,Inc., 2017. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf
[2] S. Yao, D. Yu, J. Zhao, I. Shafran, T. L. Griffiths, Y. Cao, and K. Narasimhan, “Treeof Thoughts: Deliberate problem solving with large language models,” 2023. [3] E. Bohlmeijer, M. Roemer, P. Cuijpers, and F. Smit, “The effects of reminiscenceon psychological well-being in older adults: A meta-analysis,” Aging and MentalHealth, vol. 11, no. 3, pp. 291–300, 2007. [4] Y.-H. Park, H. K. Chang, M. H. Lee, and S. H. Lee, “Community-dwelling olderadults＇needs and acceptance regarding the use of robot technology to assist withdaily living performance,” BMC geriatrics, vol. 19, pp. 1–9, 2019. [5] A. S. Tulshan and S. N. Dhage, “Survey on virtual assistant: Google assistant, siri,cortana, alexa,” in Advances in Signal Processing and Intelligent Recognition Sys-tems, S. M. Thampi, O. Marques, S. Krishnan, K.-C. Li, D. Ciuonzo, and M. H.Kolekar, Eds. Singapore: Springer Singapore, 2019, pp. 190–201. [6] W. X. Zhao, K. Zhou, J. Li, T. Tang, X. Wang, Y. Hou, Y. Min, B. Zhang, J. Zhang,Z. Dong, Y. Du, C. Yang, Y. Chen, Z. Chen, J. Jiang, R. Ren, Y. Li, X. Tang, Z. Liu,P. Liu, J.-Y. Nie, and J.-R. Wen, “A survey of large language models,” arXiv preprintarXiv:2303.18223, 2023. [Online]. Available: http://arxiv.org/abs/2303.18223 [7] V. Karpukhin, B. Oguz, S. Min, P. Lewis, L. Wu, S. Edunov, D. Chen, and W.-t.Yih, “Dense passage retrieval for open-domain question answering,” in Proceedingsof the 2020 Conference on Empirical Methods in Natural Language Processing(EMNLP), B. Webber, T. Cohn, Y. He, and Y. Liu, Eds. Online: Associationfor Computational Linguistics, Nov. 2020, pp. 6769–6781. [Online]. Available:https://aclanthology.org/2020.emnlp-main.550 [8] Y. Zhu, H. Yuan, S. Wang, J. Liu, W. Liu, C. Deng, H. Chen, Z. Dou, and J.-R. Wen,“Large language models for information retrieval: A survey,” 2024. [9] M. Lewis, Y. Liu, N. Goyal, M. Ghazvininejad, A. Mohamed, O. Levy, V. Stoyanov,and L. Zettlemoyer, “BART: Denoising sequence-to-sequence pre-training fornatural language generation, translation, and comprehension,” in Proceedingsof the 58th Annual Meeting of the Association for Computational Linguistics,D. Jurafsky, J. Chai, N. Schluter, and J. Tetreault, Eds. Online: Associationfor Computational Linguistics, Jul. 2020, pp. 7871–7880. [Online]. Available:https://aclanthology.org/2020.acl-main.703 [10] T. Zhang, F. Ladhak, E. Durmus, P. Liang, K. McKeown, and T. B. Hashimoto,“Benchmarking Large Language Models for News Summarization,” Transactionsof the Association for Computational Linguistics, vol. 12, pp. 39–57, 01 2024.[Online]. Available: https://doi.org/10.1162/tacl_a_00632 [11] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deepbidirectional transformers for language understanding,” in Proceedings of the 2019Conference of the North American Chapter of the Association for ComputationalLinguistics: Human Language Technologies, Volume 1 (Long and Short Papers),J. Burstein, C. Doran, and T. Solorio, Eds. Minneapolis, Minnesota: Associationfor Computational Linguistics, Jun. 2019, pp. 4171–4186. [Online]. Available:https://aclanthology.org/N19-1423 [12] Z. Liu, I. Lee, Y. Du, S. Sanyal, and J. Zhao, “Self-contradictory reasoning evaluationand detection,” 2024. [13] S. Min, E. Wallace, S. Singh, M. Gardner, H. Hajishirzi, and L. Zettlemoyer,“Compositional questions do not necessitate multi-hop reasoning,” in Proceedingsof the 57th Annual Meeting of the Association for Computational Linguistics,A. Korhonen, D. Traum, and L. Màrquez, Eds. Florence, Italy: Associationfor Computational Linguistics, Jul. 2019, pp. 4249–4257. [Online]. Available:https://aclanthology.org/P19-1416 [14] 宋豐裕., “基於記憶庫問答的記憶輔助機器人 / 宋豐裕 [撰] = memory assistancerobot based on memory bank question answering / feng-yu sung,” 2023. [15] Z. Ma, Z. Dou, Y. Zhu, H. Zhong, and J.-R. Wen, “One chatbot per person: Creatingpersonalized chatbots based on implicit user profiles,” in Proceedings of the 44thinternational ACM SIGIR conference on research and development in informationretrieval, 2021, pp. 555–564. [16] J. Xu, A. Szlam, and J. Weston, “Beyond goldfish memory: Long-term open-domainconversation,” arXiv preprint arXiv:2107.07567, 2021. [17] X. Xu, Z. Gou, W. Wu, Z.-Y. Niu, H. Wu, H. Wang, and S. Wang, “Long time nosee! open-domain conversation with long-term persona memory,” arXiv preprintarXiv:2203.05797, 2022. [18] H. Trivedi, N. Balasubramanian, T. Khot, and A. Sabharwal, “Interleaving retrievalwith chain-of-thought reasoning for knowledge-intensive multi-step questions,” inProceedings of the 61st Annual Meeting of the Association for ComputationalLinguistics (Volume 1: Long Papers), A. Rogers, J. Boyd-Graber, and N. Okazaki,Eds. Toronto, Canada: Association for Computational Linguistics, Jul. 2023, pp.10 014–10 037. [Online]. Available: https://aclanthology.org/2023.acl-long.557 [19] S. Yao, J. Zhao, D. Yu, N. Du, I. Shafran, K. Narasimhan, and Y. Cao, “React: Synergizing reasoning and acting in language models,” arXiv preprint arXiv:2210.03629,2022. [20] O. Press, M. Zhang, S. Min, L. Schmidt, N. Smith, and M. Lewis, “Measuringand narrowing the compositionality gap in language models,” in Findings of theAssociation for Computational Linguistics: EMNLP 2023, H. Bouamor, J. Pino, andK. Bali, Eds. Singapore: Association for Computational Linguistics, Dec. 2023, pp.5687–5711. [Online]. Available: https://aclanthology.org/2023.findings-emnlp.378 [21] J. Zhang, S. Cao, T. Zhang, X. Lv, J. Li, L. Hou, J. Shi, and Q. Tian, “Reasoningover hierarchical question decomposition tree for explainable question answering,”in Proceedings of the 61st Annual Meeting of the Association for ComputationalLinguistics (Volume 1: Long Papers), A. Rogers, J. Boyd-Graber, and N. Okazaki,Eds. Toronto, Canada: Association for Computational Linguistics, Jul. 2023, pp.14 556–14 570. [Online]. Available: https://aclanthology.org/2023.acl-long.814 [22] Y. Zhu, Z. Luo, and G. Cheng, “Furthest reasoning with plan assessment: Stablereasoning path with retrieval-augmented large language models,” 2023. [23] 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,” arXivpreprint arXiv:2312.10997, 2023. [24] T. Mikolov, M. Karafiát, L. Burget, J. Černocký, and S. Khudanpur, “Recurrentneural network based language model,” in Proc. Interspeech 2010, 2010, pp. 1045–1048. [25] M. Sundermeyer, R. Schlüter, and H. Ney, “Lstm neural networks for language mod-eling.” in Interspeech, vol. 2012, 2012, pp. 194–197. [26] A. Radford, K. Narasimhan, T. Salimans, I. Sutskever et al., “Improving languageunderstanding by generative pre-training,” 2018. [27] C. Raffel, N. Shazeer, A. Roberts, K. Lee, S. Narang, M. Matena, Y. Zhou, W. Li,and P. J. Liu, “Exploring the limits of transfer learning with a unified text-to-texttransformer,” Journal of machine learning research, vol. 21, no. 140, pp. 1–67, 2020. [28] J. Wei, Y. Tay, R. Bommasani, C. Raffel, B. Zoph, S. Borgeaud, D. Yogatama,M. Bosma, D. Zhou, D. Metzler, E. H. Chi, T. Hashimoto, O. Vinyals, P. Liang,J. Dean, and W. Fedus, “Emergent abilities of large language models,” Transactionson Machine Learning Research, 2022, survey Certification. [Online]. Available:https://openreview.net/forum?id=yzkSU5zdwD [29] T. B. Brown, B. Mann, N. Ryder, M. Subbiah, J. Kaplan, P. Dhariwal, A. Nee-lakantan, P. Shyam, G. Sastry, A. Askell, S. Agarwal, A. Herbert-Voss, G. Krueger,T. Henighan, R. Child, A. Ramesh, D. M. Ziegler, J. Wu, C. Winter, C. Hesse,M. Chen, E. Sigler, M. Litwin, S. Gray, B. Chess, J. Clark, C. Berner, S. McCandlish,A. Radford, I. Sutskever, and D. Amodei, “Language models are few-shot learners,”2020. [30] Q. Dong, L. Li, D. Dai, C. Zheng, Z. Wu, B. Chang, X. Sun, J. Xu, and Z. Sui, “Asurvey on in-context learning,” arXiv preprint arXiv:2301.00234, 2022. [31] J. Wei, X. Wang, D. Schuurmans, M. Bosma, B. Ichter, F. Xia, E. Chi, Q. Le, andD. Zhou, “Chain-of-thought prompting elicits reasoning in large language models,”2023. [32] X. Wang, J. Wei, D. Schuurmans, Q. V. Le, E. H. Chi, S. Narang, A. Chowdhery,and D. Zhou, “Self-consistency improves chain of thought reasoning in languagemodels,” in The Eleventh International Conference on Learning Representations,2023. [Online]. Available: https://openreview.net/forum?id=1PL1NIMMrw [33] A. Parisi, Y. Zhao, and N. Fiedel, “Talm: Tool augmented language models,” arXivpreprint arXiv:2205.12255, 2022. [34] T. Schick, J. Dwivedi-Yu, R. Dessì, R. Raileanu, M. Lomeli, E. Hambro, L. Zettle-moyer, N. Cancedda, and T. Scialom, “Toolformer: Language models can teachthemselves to use tools,” Advances in Neural Information Processing Systems,vol. 36, 2024. [35] P. Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, H. Küttler,M. Lewis, W. tau Yih, T. Rocktäschel, S. Riedel, and D. Kiela, “Retrieval-augmentedgeneration for knowledge-intensive nlp tasks,” 2021. [36] S. E. Robertson and K. S. Jones, “Relevance weighting of search terms,” Journal ofthe American Society for Information science, vol. 27, no. 3, pp. 129–146, 1976. [37] R. Nogueira and K. Cho, “Passage re-ranking with bert,” 2020. [38] R. Jagerman, H. Zhuang, Z. Qin, X. Wang, and M. Bendersky, “Query expansion byprompting large language models,” arXiv preprint arXiv:2305.03653, 2023. [39] X. Ma, Y. Gong, P. He, H. Zhao, and N. Duan, “Query rewriting in retrieval-augmented large language models,” in Proceedings of the 2023 Conference onEmpirical Methods in Natural Language Processing, H. Bouamor, J. Pino, andK. Bali, Eds. Singapore: Association for Computational Linguistics, Dec. 2023,pp. 5303–5315. [Online]. Available: https://aclanthology.org/2023.emnlp-main.322 [40] W. Sun, L. Yan, X. Ma, P. Ren, D. Yin, and Z. Ren, “Is chatgpt good at search? in-vestigating large language models as re-ranking agent,” ArXiv, vol. abs/2304.09542,2023. [41] L. Wang, N. Yang, X. Huang, L. Yang, R. Majumder, and F. Wei, “Improving textembeddings with large language models,” 2024. [42] A. Asai, T. Schick, P. Lewis, X. Chen, G. Izacard, S. Riedel, H. Hajishirzi, and W.-t.Yih, “Task-aware retrieval with instructions,” in Findings of the Association forComputational Linguistics: ACL 2023, A. Rogers, J. Boyd-Graber, and N. Okazaki,Eds. Toronto, Canada: Association for Computational Linguistics, Jul. 2023, pp.3650–3675. [Online]. Available: https://aclanthology.org/2023.findings-acl.225 [43] L. Huang, W. Yu, W. Ma, W. Zhong, Z. Feng, H. Wang, Q. Chen, W. Peng, X. Feng,B. Qin, and T. Liu, “A survey on hallucination in large language models: Principles,taxonomy, challenges, and open questions,” 2023. [44] O. Shaikh, K. Gligoric, A. Khetan, M. Gerstgrasser, D. Yang, and D. Jurafsky,“Grounding gaps in language model generations,” in Proceedings of the 2024Conference of the North American Chapter of the Association for ComputationalLinguistics: Human Language Technologies (Volume 1: Long Papers), K. Duh,H. Gomez, and S. Bethard, Eds. Mexico City, Mexico: Association forComputational Linguistics, Jun. 2024, pp. 6279–6296. [Online]. Available:https://aclanthology.org/2024.naacl-long.348 [45] A. Ushio and J. Camacho-Collados, “T-NER: An all-round python library fortransformer-based named entity recognition,” in Proceedings of the 16th Conferenceof the European Chapter of the Association for Computational Linguistics: SystemDemonstrations. Online: Association for Computational Linguistics, Apr. 2021,pp. 53–62. [Online]. Available: https://aclanthology.org/2021.eacl-demos.7 [46] P.-L. Huguet Cabot and R. Navigli, “REBEL: Relation extraction by end-to-endlanguage generation,” in Findings of the Association for Computational Linguistics:EMNLP 2021, M.-F. Moens, X. Huang, L. Specia, and S. W.-t. Yih, Eds. PuntaCana, Dominican Republic: Association for Computational Linguistics, Nov. 2021,pp. 2370–2381. [Online]. Available: https://aclanthology.org/2021.findings-emnlp.204 [47] S. Wadhwa, S. Amir, and B. Wallace, “Revisiting relation extraction in the eraof large language models,” in Proceedings of the 61st Annual Meeting of theAssociation for Computational Linguistics (Volume 1: Long Papers), A. Rogers,J. Boyd-Graber, and N. Okazaki, Eds. Toronto, Canada: Association forComputational Linguistics, Jul. 2023, pp. 15 566–15 589. [Online]. Available:https://aclanthology.org/2023.acl-long.868 [48] D. Edge, H. Trinh, N. Cheng, J. Bradley, A. Chao, A. Mody, S. Truitt, and J. Larson,“From local to global: A graph rag approach to query-focused summarization,” arXivpreprint arXiv:2404.16130, 2024. [49] P. Rajpurkar, R. Jia, and P. Liang, “Know what you don’t know: Unanswerablequestions for SQuAD,” in Proceedings of the 56th Annual Meeting of the Associationfor Computational Linguistics (Volume 2: Short Papers), I. Gurevych and Y. Miyao,Eds. Melbourne, Australia: Association for Computational Linguistics, Jul. 2018,pp. 784–789. [Online]. Available: https://aclanthology.org/P18-2124 [50] V. Raina and M. Gales, “Answer uncertainty and unanswerability in multiple-choicemachine reading comprehension,” in Findings of the Association for ComputationalLinguistics: ACL 2022, S. Muresan, P. Nakov, and A. Villavicencio, Eds. Dublin,Ireland: Association for Computational Linguistics, May 2022, pp. 1020–1034.[Online]. Available: https://aclanthology.org/2022.findings-acl.82 [51] N. M. Guerreiro, E. Voita, and A. Martins, “Looking for a needle in a haystack:A comprehensive study of hallucinations in neural machine translation,” inProceedings of the 17th Conference of the European Chapter of the Associationfor Computational Linguistics, A. Vlachos and I. Augenstein, Eds. Dubrovnik,Croatia: Association for Computational Linguistics, May 2023, pp. 1059–1075.[Online]. Available: https://aclanthology.org/2023.eacl-main.75 [52] R. Nogueira, Z. Jiang, R. Pradeep, and J. Lin, “Document ranking with a pretrainedsequence-to-sequence model,” in Findings of the Association for ComputationalLinguistics: EMNLP 2020, T. Cohn, Y. He, and Y. Liu, Eds. Online: Associationfor Computational Linguistics, Nov. 2020, pp. 708–718. [Online]. Available:https://aclanthology.org/2020.findings-emnlp.63 [53] A. Anand, V. V, V. Setty, and A. Anand, “Context aware query rewriting for textrankers using llm,” 2023. [54] Z. Yang, P. Qi, S. Zhang, Y. Bengio, W. W. Cohen, R. Salakhutdinov, and C. D.Manning, “HotpotQA: A dataset for diverse, explainable multi-hop question an-swering,” in Conference on Empirical Methods in Natural Language Processing(EMNLP), 2018. [55] X. Ho, A.-K. Duong Nguyen, S. Sugawara, and A. Aizawa, “Constructinga multi-hop QA dataset for comprehensive evaluation of reasoning steps,” inProceedings of the 28th International Conference on Computational Linguistics.Barcelona, Spain (Online): International Committee on Computational Linguistics,Dec. 2020, pp. 6609–6625. [Online]. Available: https://www.aclweb.org/anthology/2020.coling-main.580 [56] OpenAI, “OpenAI GPT-3.5-Turbo API [gpt-3.5-turbo],” https://platform.openai.com/docs/models/gpt-3-5-turbo, 2024. [57] H. W. Chung, L. Hou, S. Longpre, B. Zoph, Y. Tay, W. Fedus, Y. Li, X. Wang,M. Dehghani, S. Brahma, A. Webson, S. S. Gu, Z. Dai, M. Suzgun, X. Chen,A. Chowdhery, A. Castro-Ros, M. Pellat, K. Robinson, D. Valter, S. Narang,G. Mishra, A. Yu, V. Zhao, Y. Huang, A. Dai, H. Yu, S. Petrov, E. H. Chi, J. Dean,J. Devlin, A. Roberts, D. Zhou, Q. V. Le, and J. Wei, “Scaling instruction-finetunedlanguage models,” 2022. [58] J. Chen, S. Xiao, P. Zhang, K. Luo, D. Lian, and Z. Liu, “Bge m3-embedding:Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation,” 2024. [59] P. Rajpurkar, R. Jia, and P. Liang, “Know what you don’t know: Unanswerablequestions for squad,” 2018. [Online]. Available: https://arxiv.org/abs/1806.03822 [60] OpenAI, “OpenAI GPT-4o API [gpt-4o],” https://platform.openai.com/docs/models/gpt-4o, 2024. [61] E. J. Hu, Y. Shen, P. Wallis, Z. Allen-Zhu, Y. Li, S. Wang, L. Wang, and W. Chen,“Lora: Low-rank adaptation of large language models,” 2021. [Online]. Available:https://arxiv.org/abs/2106.09685 [62] S. Borsci, A. Malizia, M. Schmettow, F. van der Velde, G. Tariverdiyeva,D. Balaji, and A. Chamberlain, “The chatbot usability scale: the design and pilotof a usability scale for interaction with ai-based conversational agents,” PersonalUbiquitous Comput., vol. 26, no. 1, p. 95–119, jul 2021. [Online]. Available:https://doi.org/10.1007/s00779-021-01582-9 | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/94836 | - |
| dc.description.abstract | 具備記憶功能的機器人能夠幫助我們回憶過去的個人事件，例如特定的人、事、物等。對於那些記憶力較弱或容易忘事的人來說，這類機器人可以作為一種認知支援工具，幫助他們記住重要資訊。此外，亦有研究指出，社區長者對這種具備記憶輔助功能的機器人有著較高的接受度和偏好，顯示其在提升長者生活自主與關懷方面的潛力。
現實世界使用者的問題可能複雜或表述不清，因而需要多步驟推理或整合多個資訊來解答，這也是當前智慧助理所面臨的挑戰之一。本論文提出了一個具多步推理能力的記憶輔助問答系統。首先，我們從與使用者的對話中提取出事件導向的記憶內容，分析事件中的命名實體及其關係，並儲存在記憶庫中。當使用者提出問題時，系統能迭代地檢索相關資訊並評估檢索結果的信心程度。我們的檢索系統不僅使用文字檢索，還運用圖形檢索以更好地捕捉和利用記憶之間的關係來增強檢索效果。根據信心評估結果，系統可以將問題進一步拆解成子問題或進行改寫，以便更精確地檢索答案。在這個過程中，系統會構建一個樹狀結構來組織解答，最終提供一個合適的答案給使用者。 實驗結果顯示，我們設計的動態樹查詢分解模組與圖搜尋技術相結合，在多跳問答資料集上能夠更有效地針對複雜問題檢索所需的參考資訊並生成答案。此外，這一方法在使用大型語言模型時，所需的token花費顯著低於相關的研究工作。 | zh_TW |
| dc.description.abstract | Robots equipped with memory capabilities can assist individuals in recalling past personal events, including specific people, events, and objects. They can serve as cognitive support tools for those who have difficulty remembering things, helping them to recall important information. Additionally, studies have shown that community-dwelling elders show higher acceptance and preference for such memory assistance features, demonstrating their potential to enhance the autonomy and care of elderly individuals.
In real-world scenarios, users' queries can be complex or poorly expressed, requiring multi-step reasoning or aggregating several pieces of information to provide an answer. This can be challenging for existing intelligent assistants. This thesis proposes a memory-assisted question-answering system with multi-step reasoning capabilities. Firstly, the system can extract event-oriented memory content from the user's conversations, identify the named entities and their relationships within those events, and store them in a memory bank. Given a user's question, the system iteratively retrieves relevant information and evaluates the confidence level of the retrieval results. Our retrieval system uses not only text-based retrieval but also graph-based one to better capture and utilize the relationships between memories to enhance retrieval effectiveness. Based on the confidence assessment, the system can further decompose the question into sub-questions or rewrite it to allow for more precise retrieval of answers. During this process, the system constructs a tree structure to organize the answers, ultimately providing the user with an appropriate response. The experimental results show that our designed dynamic query decomposition tree paradigm, combined with graph search techniques, can more effectively retrieve the necessary reference information and generate answers for complex questions in multi-hop question-answering datasets. Furthermore, this method incurs significantly lower token costs when using large language models compared to related research works. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-08-19T17:20:47Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-08-19T17:20:47Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 致謝 i
摘要 ii Abstract iii Contents v List of Figures ix List of Tables xi Chapter 1 Introduction 1 1.1 Background 1 1.2 Motivation 2 1.3 Related Work 4 1.3.1 User Memory Extraction from Conversation 4 1.3.2 Multi-Hop Question Answering 5 1.3.3 Comparison 6 1.4 Contributions 9 1.5 Thesis Organization 10 Chapter 2 Preliminaries 12 2.1 Large Language Model 12 2.1.1 Transformer-based Language Models 12 2.1.2 Emergent Abilities of Large Language Models 14 2.2 Prompt Engineering 15 2.2.1 Prompt Engineering for Reasoning 15 2.2.2 Prompt Engineering with Tool Use 16 2.3 Retrieval-Augmented Generation 17 2.3.1 Elements of RAG 17 2.3.2 Advanced RAG and Modular RAG 18 2.3.3 Large Language Models and Information Retrieval 19 Chapter 3 Methodology 21 3.1 System Overview 21 3.2 Chat response generation 23 3.3 Memory Bank 24 3.3.1 Document-based Memory Representation 25 3.3.2 Graph-based Memory Representation 25 3.4 Memory Extraction 26 3.4.1 Memory Episode Extraction 26 3.4.2 Memory Entity-Relation Extraction 28 3.5 Query Tree 29 3.5.1 Definition of Query Tree 30 3.5.2 Reasoning with Query Tree 33 3.6 Retrieval System 34 3.6.1 Document Search 36 3.6.2 Graph Search 38 3.7 Answerability Estimation 42 3.8 Query Augmentation 44 Chapter 4 Experiments 47 4.1 Multihop Question Answering 47 4.1.1 Datasets 47 4.1.2 Evaluation Metrics 48 4.1.3 Baselines 49 4.1.4 Implementation Details 49 4.1.5 Main Results 50 4.1.6 Ablation Study 50 4.2 Answerability Estimation 56 4.2.1 Dataset 56 4.2.2 Evaluation metrics 57 4.2.3 Baselines 58 4.2.4 Implementation Details 59 4.2.5 Results 59 4.3 User Study 60 4.3.1 Implementation Details 60 4.3.2 User Interface 61 4.3.3 Questionnaire 62 4.3.4 Procedure 62 4.3.5 Results 63 Chapter 5 Conclusion 66 References 69 | - |
| dc.language.iso | en | - |
| dc.subject | 多跳問答 | zh_TW |
| dc.subject | 檢索增強生成 | zh_TW |
| dc.subject | 大型語言模型 | zh_TW |
| dc.subject | 記憶輔助 | zh_TW |
| dc.subject | 對話資訊擷取 | zh_TW |
| dc.subject | Memory Assistance | en |
| dc.subject | Retrieval-Augmented Generation | en |
| dc.subject | Large Language Model | en |
| dc.subject | Dialogue Information Extraction | en |
| dc.subject | Multi-Hop Question Answering | en |
| dc.title | 具有多步推理能力的個人記憶問答系統 | zh_TW |
| dc.title | Enabling Multi-Step Reasoning in Personal Memory Question Answering System | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 張玉玲;岳修平;黃從仁;李宏毅 | zh_TW |
| dc.contributor.oralexamcommittee | Yu-Ling Chang;Hsiu-Ping Yueh;Tsung-Ren Huang;Hung-Yi Lee | en |
| dc.subject.keyword | 多跳問答,檢索增強生成,大型語言模型,記憶輔助,對話資訊擷取, | zh_TW |
| dc.subject.keyword | Multi-Hop Question Answering,Retrieval-Augmented Generation,Large Language Model,Memory Assistance,Dialogue Information Extraction, | en |
| dc.relation.page | 74 | - |
| dc.identifier.doi | 10.6342/NTU202403395 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2024-08-09 | - |
| 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 | 2.63 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。