請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/92897完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 孫紹華 | zh_TW |
| dc.contributor.advisor | Shao-Hua Sun | en |
| dc.contributor.author | 李威緒 | zh_TW |
| dc.contributor.author | Wei-Hsu Lee | en |
| dc.date.accessioned | 2024-07-03T16:10:32Z | - |
| dc.date.available | 2024-09-24 | - |
| dc.date.copyright | 2024-07-03 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-06-28 | - |
| dc.identifier.citation | [1] Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. Gpt-4 technical report. arXiv preprint arXiv:2303.08774, 2023.
[2] Matej Balog, Alexander L Gaunt, Marc Brockschmidt, Sebastian Nowozin, and Daniel Tarlow. Deepcoder: Learning to write programs. In International Conference on Learning Representations, 2017. [3] Rudy R Bunel, Matthew Hausknecht, Jacob Devlin, Rishabh Singh, and Pushmeet Kohli. Leveraging grammar and reinforcement learning for neural program synthesis. In International Conference on Learning Representations, 2018. [4] Natasha Butt, Blazej Manczak, Auke Wiggers, Corrado Rainone, David Zhang, Michaël Defferrard, and Taco Cohen. Codeit: Self-improving language models with prioritized hindsight replay. In International Conference on Machine Learning, 2024. [5] Tales Henrique Carvalho, Kenneth Tjhia, and Levi Lelis. Reclaiming the source of programmatic policies: Programmatic versus latent spaces. In International Conference on Learning Representations, 2023. [6] Xinyun Chen, Chang Liu, and Dawn Song. Execution-guided neural program synthesis. In International Conference on Learning Representations, 2018. [7] Raphaël Dang-Nhu. Plans: Neuro-symbolic program learning from videos. In Neural Information Processing Systems, 2020. [8] Aditya Desai, Sumit Gulwani, Vineet Hingorani, Nidhi Jain, Amey Karkare, Mark Marron, Subhajit Roy, et al. Program synthesis using natural language. In International Conference on Software Engineering, 2016. [9] Jacob Devlin, Jonathan Uesato, Surya Bhupatiraju, Rishabh Singh, Abdel-rahman Mohamed, and Pushmeet Kohli. Robustfill: Neural program learning under noisy i/ o. In International Conference on Machine Learning, 2017. [10] Xuguang Duan, Qi Wu, Chuang Gan, Yiwei Zhang, Wenbing Huang, Anton Van Den Hengel, and Wenwu Zhu. Watch, reason and code: Learning to represent videos using program. In Proceedings of the 27th ACM International Conference on Multimedia, 2019. [11] Abhay Garg, Anand Sriraman, Kunal Pagarey, and Shirish Karande. Are transformers all that karel needs? In Advances in Programming Languages and Neurosymbolic Systems Workshop, 2021. [12] Kavi Gupta, Peter Ebert Christensen, Xinyun Chen, and Dawn Song. Synthesize, execute and debug: Learning to repair for neural program synthesis. In Neural Information Processing Systems, 2020. [13] Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685, 2021. [14] Cheng-Wei Hung. Investigating the impact of program execution on neural program synthesis. Master’s thesis, National Taiwan University, 2024. [15] Leslie Pack Kaelbling, Michael L Littman, and Anthony R Cassandra. Planning and acting in partially observable stochastic domains. 101(1-2), 1998. [16] Hung Le, Yue Wang, Akhilesh Deepak Gotmare, Silvio Savarese, and Steven Chu Hong Hoi. Coderl: Mastering code generation through pretrained models and deep reinforcement learning. In Neural Information Processing Systems, 2022. [17] Brian Lester, Rami Al-Rfou, and Noah Constant. The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691, 2021. [18] Xiang Lisa Li and Percy Liang. Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190, 2021. [19] Xi Victoria Lin, Chenglong Wang, Luke Zettlemoyer, and Michael D Ernst. Nl2bash: A corpus and semantic parser for natural language interface to the linux operating system. In International Conference on Language Resources and Evaluation, 2018. [20] Guan-Ting Liu, En-Pei Hu, Pu-Jen Cheng, Hung-Yi Lee, and Shao-Hua Sun. Hierarchical programmatic reinforcement learning via learning to compose programs. In International Conference on Machine Learning, 2023. [21] Max Liu, Chan-Hung Yu, Wei-Hsu Lee, Cheng-Wei Hung, Yen-Chun Chen, and Shao-Hua Sun. Synthesizing programmatic reinforcement learning policies with large language model guided search. arXiv preprint arXiv:2405.16450, 2024. [22] Anthony Manchin, Jamie Sherrah, Qi Wu, and Anton van den Hengel. Program generation from diverse video demonstrations. arXiv preprint arXiv:2302.00178, 2023. [23] Sourab Mangrulkar, Sylvain Gugger, Lysandre Debut, Younes Belkada, Sayak Paul, and Benjamin Bossan. Peft: State-of-the-art parameter-efficient fine-tuning methods, 2022. [24] Richard E Pattis. Karel the robot: a gentle introduction to the art of programming. John Wiley & Sons, Inc., 1981. [25] Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning, 2021. [26] Mohammad Raza, Sumit Gulwani, and Natasa Milic-Frayling. Compositional program synthesis from natural language and examples. In International Joint Conference on Artificial Intelligence, 2015. [27] Baptiste Roziere, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Tal Remez, Jérémy Rapin, et al. Code llama: Open foundation models for code. arXiv preprint arXiv:2308.12950, 2023. [28] Noam Shazeer and Mitchell Stern. Adafactor: Adaptive learning rates with sublinear memory cost. In International Conference on Machine Learning, 2018. [29] Kensen Shi, Joey Hong, Yinlin Deng, Pengcheng Yin, Manzil Zaheer, and Charles Sutton. Exedec: Execution decomposition for compositional generalization in neural program synthesis. In International Conference on Learning Representations, 2023. [30] Eui Chul Shin, Illia Polosukhin, and Dawn Song. Improving neural program synthesis with inferred execution traces. 2018. [31] Shao-Hua Sun, Hyeonwoo Noh, Sriram Somasundaram, and Joseph Lim. Neural program synthesis from diverse demonstration videos. In International Conference on Machine Learning, 2018. [32] Yonglong Tian, Andrew Luo, Xingyuan Sun, Kevin Ellis, William T Freeman, Joshua B Tenenbaum, and Jiajun Wu. Learning to infer and execute 3d shape programs. In International Conference on Learning Representations, 2018. [33] Dweep Trivedi, Jesse Zhang, Shao-Hua Sun, and Joseph J Lim. Learning to synthesize programs as interpretable and generalizable policies. In Neural Information Processing Systems, 2021. [34] Bailin Wang, Zi Wang, Xuezhi Wang, Yuan Cao, Rif A. Saurous, and Yoon Kim. Grammar prompting for domain-specific language generation with large language models. In Neural Information Processing Systems, 2023. [35] Yue Wang, Weishi Wang, Shafiq Joty, and Steven CH Hoi. Codet5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. In Empirical Methods in Natural Language Processing, 2021. [36] Yue Wang, Hung Le, Akhilesh Deepak Gotmare, Nghi DQ Bui, Junnan Li, and Steven CH Hoi. Codet5+: Open code large language models for code understanding and generation. arXiv preprint arXiv:2305.07922, 2023. [37] Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoest, and Alexander M. Rush. Transformers: State-of-the-art natural language processing. In Empirical Methods in Natural Language Processing, 2020. [38] Jiajun Wu, Joshua B Tenenbaum, and Pushmeet Kohli. Neural scene de-rendering. In IEEE Conference on Computer Vision and Pattern Recognition, 2017. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/92897 | - |
| dc.description.abstract | 程式合成基於特定的規格來創建程式，這些規格可以有各種形式。大型語言模型（LLM）由於缺乏訓練資料，在處理領域特定語言（DSL）時存在困難。了解DSL與一般程式語言之間的差異至關重要。我們開發了兩個框架來改進模型對DSL執行和邊緣情況的理解。此外，添加新的神經模塊也可能有幫助。我們利用參數高效微調（PEFT）和CLIP開發了具有增強泛化能力的兩個框架。在某些情況下，設計評估指標可能是必要的。我們的貢獻在於找出最有效的方法來彌合DSL與LLM之間的鴻溝，並通過使用新的評估指標，提供對神經程式合成的新視角。 | zh_TW |
| dc.description.abstract | Program synthesis creates programs based on specific specifications in various modalities. Large language models~(LLMs) struggle with domain-specific language~(DSL) due to a lack of training data. Understanding the differences between DSL and general programming languages is important. Two frameworks have been developed to improve the model''s understanding of DSL execution and corner cases. Adding new neural modules may also help. Two frameworks with enhanced generalization abilities have been developed using parameter-efficient fine-tuning (PEFT) and CLIP. In some cases, designing an evaluation metric may be necessary. Our contribution involves identifying the most effective method for bridging the gap between DSL and LLM and offering a fresh perspective on neural program synthesis through the use of new evaluation metrics. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-07-03T16:10:32Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-07-03T16:10:32Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | Contents
Acknowledgements i 摘要 iii Abstract v Contents vii List of Figures xi List of Tables xiii Chapter 1 Introduction 1 Chapter 2 Related Work 3 2.1 Neural Program Synthesis 3 2.2 Contrastive Learning 4 2.3 Programmatic Reinforcement Learning 4 2.4 Parameter Efficient Fine-Tuning 5 Chapter 3 Preliminaries 7 3.1 Domain-Specific Languages (DSL) 7 3.2 Pretrained Code Models 8 3.3 Synthetic Dataset 9 Chapter 4 PEFT 11 4.1 Problem Formulation 12 4.2 Method 13 4.2.1 Execution Result Encoder 13 4.2.2 Parameter-Efficient Fine-tuning techniques for Encoder-Decoder models 14 4.3 Experiment 14 4.3.1 Comparison between fine-tuning and parameter-efficient fine-tuning 15 4.3.2 The Execution Results for Different Demonstrations 16 4.4 Conclusion 16 Chapter 5 Execution and Synthesis 19 5.1 Problem Formulation 20 5.2 Method 20 5.2.1 Neural Program Synthesizer Model 21 5.2.2 Neural Program Executor Model 21 5.3 Experiment 22 5.4 Comparison of Synthesis Without Augmentation, Synthesis Only, and Synthesis with Execution Aid 23 5.5 Conclusion 23 Chapter 6 Contrastive Pre-training 25 6.1 Problem Formulation 25 6.2 Method 26 6.3 Experiment 26 6.3.1 With or Without the Contrastive Model 27 6.3.2 Improving the CPEP Model 28 6.3.3 Longer Dataset 29 6.4 Conclusion 31 Chapter 7 Negative Samples 33 7.1 Problem Formulation 33 7.2 Method 34 7.3 Experiment 34 7.3.1 Optimize Program Synthesis with Positive and Negative Sample 34 7.4 Conclusion 35 Chapter 8 PRL Evaluation 37 8.1 Problem Formulation 37 8.2 Method 38 8.3 Experiment 39 8.4 The Evaluation Results 39 8.5 Model Visualization 40 8.6 Conclusion 42 Chapter 9 Conclusion and Discussion 43 References 45 | - |
| dc.language.iso | en | - |
| dc.title | 透過微調技術、對比學習、全面訓練策略和實際評估增進程式合成 | zh_TW |
| dc.title | Enhancing Program Synthesis through Fine-Tuning Techniques, Contrastive Learning, Comprehensive Training Strategies, and Real-World Evaluation Scenarios | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 謝秉均;陳縕儂 | zh_TW |
| dc.contributor.oralexamcommittee | Ping-Chun Hsieh;Yun-Nung Chen | en |
| dc.subject.keyword | 程式合成,程式預訓練模型,參數微調,對比學習,正反樣本,可程式化強化學習, | zh_TW |
| dc.subject.keyword | Program Synthesis,Pretrained Code Models,Fine-tuning,Contrastive Learning,Positive and Negative Samples,Programmatic Reinforcement Learning, | en |
| dc.relation.page | 50 | - |
| dc.identifier.doi | 10.6342/NTU202401351 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2024-06-28 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 電信工程學研究所 | - |
| 顯示於系所單位： | 電信工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-112-2.pdf | 814.13 kB | 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。