{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:01:27Z","timestamp":1782846087296,"version":"3.54.5"},"reference-count":82,"publisher":"Association for Computing Machinery (ACM)","issue":"FSE","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Softw. Eng."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>Large language models (LLMs) have achieved remarkable performance in software engineering (SE), and fine-tuning LLM for specific SE tasks has gradually become a new paradigm. However, storing fine-tuned checkpoints for multiple tasks incurs heavy storage and deployment complexity. Model fusion, which operates on fine-tuned parameters, offers excellent parameter compression and scalability, yet its effectiveness in the SE domain remains underexplored, making such an investigation essential for guiding the development of customized fusion techniques for the SE domain. To bridge this gap, we conduct a systematic study of model fusion in the SE contexts and reveal the following major findings: (1) when fusing programming languages (PLs) within the same task, model fusion usually works well and can enhance the performance of PLs with fewer data when PLs share similar features. (2) when fusing SE tasks of the same category within a same PL, all methods except TALL-Masks generally suffer substantial performance degradation on specific tasks; (3) when fusing SE tasks of different categories across different PLs, all existing model fusion methods exhibit significant performance degradation on certain tasks. In our evaluation results, TALL-Masks, which introduces a mask for each task to extract the most relevant dimensions from the fusion parameters, achieves promising performance. However, during parameters fusion, weak features (i.e., small variation in fine-tuned parameters) are easily overshadowed by strong ones (i.e., large variation in fine-tuned parameters) during parameter fusion, causing the constructed masks to fail to extract the most relevant parameters. To overcome this situation, we propose an improved version of TALL-Masks, called Scaling-Masks. The key idea is to amplify weak features to prevent them from being overshadowed by strong ones, which is achieved by scaling the value range of weak features to match that of strong features. Experimental results demonstrate that Scaling-Masks can significantly improve fusion performance for tasks with extremely weak features without affecting other tasks, with normalized accuracy improved by 63.49% for vulnerability detection when fusing SE tasks of different categories and 24.02% for PHP when fusing PLs in the code repair task.<\/jats:p>","DOI":"10.1145\/3808198","type":"journal-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:06:14Z","timestamp":1782839174000},"page":"4347-4370","source":"Crossref","is-referenced-by-count":0,"title":["One Size Does Fit All: Exploring Model Fusion for Software Engineering Tasks"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0386-3338","authenticated-orcid":false,"given":"Yinggang","family":"Qiu","sequence":"first","affiliation":[{"name":"National University of Defense Technology, College of Computer Science and Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3440-9520","authenticated-orcid":false,"given":"Yihao","family":"Qin","sequence":"additional","affiliation":[{"name":"Information Support Force Engineering University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7239-1819","authenticated-orcid":false,"given":"Mingyang","family":"Geng","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, College of Computer Science and Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1469-2063","authenticated-orcid":false,"given":"Shangwen","family":"Wang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, College of Computer Science and Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6243-8479","authenticated-orcid":false,"given":"Dezun","family":"Dong","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, College of Computer Science and Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Resource-Efficient & Effective Code Summarization. In 2025 IEEE\/ACM Second International Conference on AI Foundation Models and Software Engineering (Forge). IEEE, 224-235","author":"Afrin Saima","year":"2025","unstructured":"Saima Afrin, Joseph Call, Khai-Nguyen Nguyen, Oscar Chaparro, and Antonio Mastropaolo. 2025. Resource-Efficient & Effective Code Summarization. In 2025 IEEE\/ACM Second International Conference on AI Foundation Models and Software Engineering (Forge). IEEE, 224-235."},{"key":"e_1_2_1_2_1","volume-title":"Feature normalization and likelihood-based similarity measures for image retrieval. Pattern recognition letters 22, 5","author":"Aksoy Selim","year":"2001","unstructured":"Selim Aksoy and Robert M Haralick. 2001. Feature normalization and likelihood-based similarity measures for image retrieval. Pattern recognition letters 22, 5 (2001), 563-582."},{"key":"e_1_2_1_3_1","first-page":"1","article-title":"Data normalization and standardization: a technical report","volume":"1","author":"Muhammad Ali Peshawa Jamal","year":"2014","unstructured":"Peshawa Jamal Muhammad Ali, Rezhna Hassan Faraj, Erbil Koya, Peshawa J Muhammad Ali, and Rezhna H Faraj. 2014. Data normalization and standardization: a technical report. Mach Learn Tech Rep 1, 1 (2014), 1-6.","journal-title":"Mach Learn Tech Rep"},{"key":"e_1_2_1_4_1","volume-title":"Proceedings of the XXI Brazilian Symposium on Software Quality. 1-10","author":"Andrade Vin\u00edcius Camargo","year":"2022","unstructured":"Vin\u00edcius Camargo Andrade, Rhodrigo Deda Gomes, Sheila Reinehr, Cinthia Obladen De Almendra Freitas, and Andreia Malucelli. 2022. Privacy by design and software engineering: A systematic literature review. In Proceedings of the XXI Brazilian Symposium on Software Quality. 1-10."},{"key":"e_1_2_1_5_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_2_1_6_1","unstructured":"BigCode. 2023. Self-OSS-Instruct-SC2-ExecFilter-50K. https:\/\/huggingface.co\/datasets\/bigcode\/self-oss-instruct-sc2- exec-filter-50k."},{"key":"e_1_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Yupeng Chang Xu Wang Jindong Wang Yuan Wu Linyi Yang Kaijie Zhu Hao Chen Xiaoyuan Yi Cunxiang Wang Yidong Wang et al. 2024. A survey on evaluation of large language models. ACM transactions on intelligent systems and technology 15 3 (2024) 1-45.","DOI":"10.1145\/3641289"},{"key":"e_1_2_1_8_1","volume-title":"LoRACode: LoRA Adapters for Code Embeddings. arXiv preprint arXiv:2503.05315","author":"Chaturvedi Saumya","year":"2025","unstructured":"Saumya Chaturvedi, Aman Chadha, and Laurent Bindschaedler. 2025. LoRACode: LoRA Adapters for Code Embeddings. arXiv preprint arXiv:2503.05315 (2025)."},{"key":"e_1_2_1_9_1","volume-title":"Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al.","author":"Chen Mark","year":"2021","unstructured":"Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde De Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. 2021. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)."},{"key":"e_1_2_1_10_1","volume-title":"Are Decoder-Only Large Language Models the Silver Bullet for Code Search? arXiv preprint arXiv:2410.22240","author":"Chen Yuxuan","year":"2024","unstructured":"Yuxuan Chen, Guangsheng Ou, Mingwei Liu, Yanlin Wang, and Zibin Zheng. 2024. Are Decoder-Only Large Language Models the Silver Bullet for Code Search? arXiv preprint arXiv:2410.22240 (2024)."},{"key":"e_1_2_1_11_1","volume-title":"An Empirical Study. arXiv preprint arXiv:2411.08388","author":"Cherny-Shahar Tsvi","year":"2024","unstructured":"Tsvi Cherny-Shahar and Amiram Yehudai. 2024. Multi-Lingual Development & Programming Languages Interoperability: An Empirical Study. arXiv preprint arXiv:2411.08388 (2024)."},{"key":"e_1_2_1_12_1","volume-title":"Fatemeh H Fard, and Ali Ouni.","author":"Dehghan Meghdad","year":"2024","unstructured":"Meghdad Dehghan, Jie JW Wu, Fatemeh H Fard, and Ali Ouni. 2024. Mergerepair: An exploratory study on merging task-specific adapters in code llms for automated program repair. arXiv preprint arXiv:2408.09568 (2024)."},{"key":"e_1_2_1_13_1","first-page":"1564","volume-title":"Proceedings of the ACM on Software Engineering 1, FSE","author":"Dou Shihan","year":"2024","unstructured":"Shihan Dou, Yueming Wu, Haoxiang Jia, Yuhao Zhou, Yan Liu, and Yang Liu. 2024. Cc2vec: Combining typed tokens with contrastive learning for effective code clone detection. Proceedings of the ACM on Software Engineering 1, FSE (2024), 1564-1584."},{"key":"e_1_2_1_14_1","volume-title":"Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering. 1907-","author":"Du Yali","year":"2024","unstructured":"Yali Du, Hui Sun, and Ming Li. 2024. A Joint Learning Model with Variational Interaction for Multilingual Program Translation. In Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering. 1907- 1918."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3709358"},{"key":"e_1_2_1_16_1","volume-title":"Codebert: A pre-trained model for programming and natural languages. arXiv preprint arXiv:2002.08155","author":"Feng Zhangyin","year":"2020","unstructured":"Zhangyin Feng, Daya Guo, Duyu Tang, Nan Duan, Xiaocheng Feng, Ming Gong, Linjun Shou, Bing Qin, Ting Liu, Daxin Jiang, et al. 2020. Codebert: A pre-trained model for programming and natural languages. arXiv preprint arXiv:2002.08155 (2020)."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-023-10346-3"},{"key":"e_1_2_1_18_1","volume-title":"Enhanced Continual Learning of Vision-Language Models with Model Fusion. arXiv preprint arXiv:2503.10705","author":"Gao Haoyuan","year":"2025","unstructured":"Haoyuan Gao, Zicong Zhang, Yuqi Wei, Linglan Zhao, Guilin Li, Yexin Li, Linghe Kong, and Weiran Huang. 2025. Enhanced Continual Learning of Vision-Language Models with Model Fusion. arXiv preprint arXiv:2503.10705 (2025)."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3608134"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180167"},{"key":"e_1_2_1_21_1","volume-title":"Graphcodebert: Pre-training code representations with data flow. arXiv preprint arXiv:2009.08366","author":"Guo Daya","year":"2020","unstructured":"Daya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, Shujie Liu, Long Zhou, Nan Duan, Alexey Svyatkovskiy, Shengyu Fu, et al. 2020. Graphcodebert: Pre-training code representations with data flow. arXiv preprint arXiv:2009.08366 (2020)."},{"key":"e_1_2_1_22_1","volume-title":"Parameter-efficient fine-tuning for large models: A comprehensive survey. arXiv preprint arXiv:2403.14608","author":"Han Zeyu","year":"2024","unstructured":"Zeyu Han, Chao Gao, Jinyang Liu, Jeff Zhang, and Sai Qian Zhang. 2024. Parameter-efficient fine-tuning for large models: A comprehensive survey. arXiv preprint arXiv:2403.14608 (2024)."},{"key":"e_1_2_1_23_1","volume-title":"Mera: Merging pretrained adapters for few-shot learning. arXiv preprint arXiv:2308.15982","author":"He Shwai","year":"2023","unstructured":"Shwai He, Run-Ze Fan, Liang Ding, Li Shen, Tianyi Zhou, and Dacheng Tao. 2023. Mera: Merging pretrained adapters for few-shot learning. arXiv preprint arXiv:2308.15982 (2023)."},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3695988"},{"key":"e_1_2_1_25_1","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2022. Lora: Low-rank adaptation of large language models. ICLR 1, 2 (2022), 3.","journal-title":"ICLR"},{"key":"e_1_2_1_26_1","volume-title":"Tianyu Pang, Chao Du, and Min Lin.","author":"Huang Chengsong","year":"2023","unstructured":"Chengsong Huang, Qian Liu, Bill Yuchen Lin, Tianyu Pang, Chao Du, and Min Lin. 2023. Lorahub: Efficient cross-task generalization via dynamic lora composition. arXiv preprint arXiv:2307.13269 (2023)."},{"key":"e_1_2_1_27_1","doi-asserted-by":"crossref","first-page":"122741","DOI":"10.52202\/079017-3900","article-title":"Emr-merging: Tuning-free high-performance model merging","volume":"37","author":"Huang Chenyu","year":"2024","unstructured":"Chenyu Huang, Peng Ye, Tao Chen, Tong He, Xiangyu Yue, and Wanli Ouyang. 2024. Emr-merging: Tuning-free high-performance model merging. Advances in Neural Information Processing Systems 37 (2024), 122741-122769.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_28_1","volume-title":"Comprehensive Fine-Tuning Large Language Models of Code for Automated Program Repair","author":"Huang Kai","year":"2025","unstructured":"Kai Huang, Jian Zhang, Xinlei Bao, Xu Wang, and Yang Liu. 2025. Comprehensive Fine-Tuning Large Language Models of Code for Automated Program Repair. IEEE Transactions on Software Engineering (2025)."},{"key":"e_1_2_1_29_1","volume-title":"Codesearchnet challenge: Evaluating the state of semantic code search. arXiv preprint arXiv:1909.09436","author":"Husain Hamel","year":"2019","unstructured":"Hamel Husain, Ho-Hsiang Wu, Tiferet Gazit, Miltiadis Allamanis, and Marc Brockschmidt. 2019. Codesearchnet challenge: Evaluating the state of semantic code search. arXiv preprint arXiv:1909.09436 (2019)."},{"key":"e_1_2_1_30_1","volume-title":"Mitchell Wortsman, Suchin Gururangan, Ludwig Schmidt, Hannaneh Hajishirzi, and Ali Farhadi.","author":"Ilharco Gabriel","year":"2022","unstructured":"Gabriel Ilharco, Marco Tulio Ribeiro, Mitchell Wortsman, Suchin Gururangan, Ludwig Schmidt, Hannaneh Hajishirzi, and Ali Farhadi. 2022. Editing models with task arithmetic. arXiv preprint arXiv:2212.04089 (2022)."},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.824819"},{"key":"e_1_2_1_32_1","volume-title":"2017 IEEE\/ACM 12th International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS). IEEE, 31-41","author":"Jamshidi Pooyan","year":"2017","unstructured":"Pooyan Jamshidi, Miguel Velez, Christian K\u00e4stner, Norbert Siegmund, and Prasad Kawthekar. 2017. Transfer learning for improving model predictions in highly configurable software. In 2017 IEEE\/ACM 12th International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS). IEEE, 31-41."},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3672456"},{"key":"e_1_2_1_34_1","volume-title":"Investigating large language models for code vulnerability detection: An experimental study. arXiv preprint arXiv:2412.18260","author":"Jiang Xuefeng","year":"2024","unstructured":"Xuefeng Jiang, Lvhua Wu, Sheng Sun, Jia Li, Jingjing Xue, Yuwei Wang, Tingting Wu, and Min Liu. 2024. Investigating large language models for code vulnerability detection: An experimental study. arXiv preprint arXiv:2412.18260 (2024)."},{"key":"e_1_2_1_35_1","volume-title":"From llms to llm-based agents for software engineering: A survey of current, challenges and future. arXiv preprint arXiv:2408.02479","author":"Jin Haolin","year":"2024","unstructured":"Haolin Jin, Linghan Huang, Haipeng Cai, Jun Yan, Bo Li, and Huaming Chen. 2024. From llms to llm-based agents for software engineering: A survey of current, challenges and future. arXiv preprint arXiv:2408.02479 (2024)."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.367"},{"key":"e_1_2_1_37_1","doi-asserted-by":"crossref","first-page":"2956","DOI":"10.1109\/TSE.2020.2983927","article-title":"Whence to learn? transferring knowledge in configurable systems using beetle","volume":"47","author":"Krishna Rahul","year":"2020","unstructured":"Rahul Krishna, Vivek Nair, Pooyan Jamshidi, and Tim Menzies. 2020. Whence to learn? transferring knowledge in configurable systems using beetle. IEEE Transactions on Software Engineering 47, 12 (2020), 2956-2972.","journal-title":"IEEE Transactions on Software Engineering"},{"key":"e_1_2_1_38_1","volume-title":"2021 36th IEEE\/ACM International Conference on Automated Software Engineering (ASE). IEEE, 717-729","author":"Minh Le Triet Huynh","year":"2021","unstructured":"Triet Huynh Minh Le, David Hin, Roland Croft, and M Ali Babar. 2021. Deepcva: Automated commit-level vulnerability assessment with deep multi-task learning. In 2021 36th IEEE\/ACM International Conference on Automated Software Engineering (ASE). IEEE, 717-729."},{"key":"e_1_2_1_39_1","volume-title":"Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, et al.","author":"Li Raymond","year":"2023","unstructured":"Raymond Li, Loubna Ben Allal, Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, et al. 2023. Starcoder: may the source be with you! arXiv preprint arXiv:2305.06161 (2023)."},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3650212.3680381"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671609"},{"key":"e_1_2_1_42_1","volume-title":"2023 38th IEEE\/ACM International Conference on Automated Software Engineering (ASE). IEEE, 397-408","author":"Liu Jiaxing","year":"2023","unstructured":"Jiaxing Liu, Chaofeng Sha, and Xin Peng. 2023. An empirical study of parameter-efficient fine-tuning methods for pre-trained code models. In 2023 38th IEEE\/ACM International Conference on Automated Software Engineering (ASE). IEEE, 397-408."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.proenv.2011.12.040"},{"key":"e_1_2_1_44_1","volume-title":"Codexglue: A machine learning benchmark dataset for code understanding and generation. arXiv preprint arXiv:2102.04664","author":"Lu Shuai","year":"2021","unstructured":"Shuai Lu, Daya Guo, Shuo Ren, Junjie Huang, Alexey Svyatkovskiy, Ambrosio Blanco, Colin Clement, Dawn Drain, Daxin Jiang, Duyu Tang, et al. 2021. Codexglue: A machine learning benchmark dataset for code understanding and generation. arXiv preprint arXiv:2102.04664 (2021)."},{"key":"e_1_2_1_45_1","volume-title":"Tegawende F Bissyande, Haoye Tian, and Xuan Bach D Le.","author":"Luo Wenqiang","year":"2024","unstructured":"Wenqiang Luo, Jacky Keung, Boyang Yang, He Ye, Claire Le Goues, Tegawende F Bissyande, Haoye Tian, and Xuan Bach D Le. 2024. When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair. ACM Transactions on Software Engineering and Methodology (2024)."},{"key":"e_1_2_1_46_1","volume-title":"He Hu, and Yaliang Li.","author":"Min Yingqian","year":"2024","unstructured":"Yingqian Min, Kun Zhou, Dawei Gao, Wayne Xin Zhao, He Hu, and Yaliang Li. 2024. Data-cube: Data curriculum for instruction-based sentence representation learning. arXiv preprint arXiv:2401.03563 (2024)."},{"key":"e_1_2_1_47_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_2_1_48_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311-318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311-318."},{"key":"e_1_2_1_49_1","volume-title":"Keep It Simple: Self-Adaptive Code Graph Simplification for Accurate Vulnerability Detection","author":"Peng Xin","year":"2025","unstructured":"Xin Peng, Shangwen Wang, Yihao Qin, Bo Lin, Liqian Chen, Jieren Cheng, and Xiaoguang Mao. 2025. Keep It Simple: Self-Adaptive Code Graph Simplification for Accurate Vulnerability Detection. IEEE Transactions on Software Engineering (2025)."},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3757915"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE63991.2025.00072"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2025.3543187"},{"key":"e_1_2_1_53_1","first-page":"2594","volume-title":"Proceedings of the ACM on Software Engineering 2, FSE","author":"Ran Dezhi","year":"2025","unstructured":"Dezhi Ran, Yuan Cao, Yuzhe Guo, Yuetong Li, Mengzhou Wu, Simin Chen, Wei Yang, and Tao Xie. 2025. Medusa: A Framework for Collaborative Development of Foundation Models with Automated Parameter Ownership Assignment. Proceedings of the ACM on Software Engineering 2, FSE (2025), 2594-2617."},{"key":"e_1_2_1_54_1","volume-title":"Code generation with alphacodium: From prompt engineering to flow engineering. arXiv preprint arXiv:2401.08500","author":"Ridnik Tal","year":"2024","unstructured":"Tal Ridnik, Dedy Kredo, and Itamar Friedman. 2024. Code generation with alphacodium: From prompt engineering to flow engineering. arXiv preprint arXiv:2401.08500 (2024)."},{"key":"e_1_2_1_55_1","volume-title":"Yossi Adi, Jingyu Liu, Romain Sauvestre, Tal Remez, et al.","author":"Roziere Baptiste","year":"2023","unstructured":"Baptiste Roziere, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Romain Sauvestre, Tal Remez, et al. 2023. Code llama: Open foundation models for code. arXiv preprint arXiv:2308.12950 (2023)."},{"key":"e_1_2_1_56_1","volume-title":"European Conference on Computer Vision. Springer, 422-438","author":"Shah Viraj","year":"2024","unstructured":"Viraj Shah, Nataniel Ruiz, Forrester Cole, Erika Lu, Svetlana Lazebnik, Yuanzhen Li, and Varun Jampani. 2024. Ziplora: Any subject in any style by effectively merging loras. In European Conference on Computer Vision. Springer, 422-438."},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3708525"},{"key":"e_1_2_1_58_1","volume-title":"Source code summarization in the era of large language models. arXiv preprint arXiv:2407.07959","author":"Sun Weisong","year":"2024","unstructured":"Weisong Sun, Yun Miao, Yuekang Li, Hongyu Zhang, Chunrong Fang, Yi Liu, Gelei Deng, Yang Liu, and Zhenyu Chen. 2024. Source code summarization in the era of large language models. arXiv preprint arXiv:2407.07959 (2024)."},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2014.77"},{"key":"e_1_2_1_60_1","volume-title":"Alpaca: A strong, replicable instruction-following model","author":"Taori Rohan","year":"2023","unstructured":"Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B Hashimoto. 2023. Alpaca: A strong, replicable instruction-following model. Stanford Center for Research on Foundation Models. https:\/\/crfm. stanford. edu\/2023\/03\/13\/alpaca. html 3, 6 (2023), 7."},{"key":"e_1_2_1_61_1","volume-title":"You Only Train Once: A Flexible Training Framework for Code Vulnerability Detection Driven by Vul-Vector. arXiv preprint arXiv:2506.10988","author":"Tian Bowen","year":"2025","unstructured":"Bowen Tian, Zhengyang Xu, Mingqiang Wu, Songning Lai, and Yutai Yue. 2025. You Only Train Once: A Flexible Training Framework for Code Vulnerability Detection Driven by Vul-Vector. arXiv preprint arXiv:2506.10988 (2025)."},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601248.2601269"},{"key":"e_1_2_1_63_1","first-page":"20","article-title":"Large language models: A comprehensive survey on architectures, applications, and challenges","volume":"7","author":"Veeramachaneni Vinod","year":"2025","unstructured":"Vinod Veeramachaneni. 2025. Large language models: A comprehensive survey on architectures, applications, and challenges. Advanced Innovations in Computer Programming Languages 7, 1 (2025), 20-39.","journal-title":"Advanced Innovations in Computer Programming Languages"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00012"},{"key":"e_1_2_1_65_1","volume-title":"Localizing task information for improved model merging and compression. arXiv preprint arXiv:2405.07813","author":"Wang Ke","year":"2024","unstructured":"Ke Wang, Nikolaos Dimitriadis, Guillermo Ortiz-Jimenez, Fran\u00e7ois Fleuret, and Pascal Frossard. 2024. Localizing task information for improved model merging and compression. arXiv preprint arXiv:2405.07813 (2024)."},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616323"},{"key":"e_1_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2024.3403042"},{"key":"e_1_2_1_68_1","first-page":"486","volume-title":"Proceedings of the ACM on Programming Languages 7, OOPSLA2","author":"Wang Shangwen","year":"2023","unstructured":"Shangwen Wang, Bo Lin, Zhensu Sun, Ming Wen, Yepang Liu, Yan Lei, and Xiaoguang Mao. 2023. Two birds with one stone: Boosting code generation and code search via a generative adversarial network. Proceedings of the ACM on Programming Languages 7, OOPSLA2 (2023), 486-515."},{"key":"e_1_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER48275.2020.9054857"},{"key":"e_1_2_1_70_1","volume-title":"Integrating Task-Specific and Universal Adapters for Pre-Trained Model-based Class-Incremental Learning. arXiv preprint arXiv:2508.08165","author":"Wang Yan","year":"2025","unstructured":"Yan Wang, Da-Wei Zhou, and Han-Jia Ye. 2025. Integrating Task-Specific and Universal Adapters for Pre-Trained Model-based Class-Incremental Learning. arXiv preprint arXiv:2508.08165 (2025)."},{"key":"e_1_2_1_71_1","first-page":"62787","article-title":"Selfcodealign: Self-alignment for code generation","volume":"37","author":"Wei Yuxiang","year":"2024","unstructured":"Yuxiang Wei, Federico Cassano, Jiawei Liu, Yifeng Ding, Naman Jain, Zachary Mueller, Harm de Vries, Leandro Von Werra, Arjun Guha, and Lingming Zhang. 2024. Selfcodealign: Self-alignment for code generation. Advances in Neural Information Processing Systems 37 (2024), 62787-62874.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0310"},{"key":"e_1_2_1_73_1","volume-title":"Model merging in llms, mllms, and beyond: Methods, theories, applications and opportunities. arXiv preprint arXiv:2408.07666","author":"Yang Enneng","year":"2024","unstructured":"Enneng Yang, Li Shen, Guibing Guo, Xingwei Wang, Xiaochun Cao, Jie Zhang, and Dacheng Tao. 2024. Model merging in llms, mllms, and beyond: Methods, theories, applications and opportunities. arXiv preprint arXiv:2408.07666 (2024)."},{"key":"e_1_2_1_74_1","volume-title":"Adamerging: Adaptive model merging for multi-task learning. arXiv preprint arXiv:2310.02575","author":"Yang Enneng","year":"2023","unstructured":"Enneng Yang, Zhenyi Wang, Li Shen, Shiwei Liu, Guibing Guo, Xingwei Wang, and Dacheng Tao. 2023. Adamerging: Adaptive model merging for multi-task learning. arXiv preprint arXiv:2310.02575 (2023)."},{"key":"e_1_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2023.3347898"},{"key":"e_1_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3533767.3534390"},{"key":"e_1_2_1_77_1","doi-asserted-by":"crossref","first-page":"67319","DOI":"10.52202\/079017-2149","article-title":"Knowledge composition using task vectors with learned anisotropic scaling","volume":"37","author":"Zhang Frederic Z","year":"2024","unstructured":"Frederic Z Zhang, Paul Albert, Cristian Rodriguez-Opazo, Anton van den Hengel, and Ehsan Abbasnejad. 2024. Knowledge composition using task vectors with learned anisotropic scaling. Advances in Neural Information Processing Systems 37 (2024), 67319-67354.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0552"},{"key":"e_1_2_1_79_1","volume-title":"Lori: Reducing cross-task interference in multi-task low-rank adaptation. arXiv preprint arXiv:2504.07448","author":"Zhang Juzheng","year":"2025","unstructured":"Juzheng Zhang, Jiacheng You, Ashwinee Panda, and Tom Goldstein. 2025. Lori: Reducing cross-task interference in multi-task low-rank adaptation. arXiv preprint arXiv:2504.07448 (2025)."},{"key":"e_1_2_1_80_1","volume-title":"Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:1904.09675","author":"Zhang Tianyi","year":"2019","unstructured":"Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi. 2019. Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:1904.09675 (2019)."},{"key":"e_1_2_1_81_1","volume-title":"Yikun Li, Eng Lieh Ouh, Lwin Khin Shar, et al.","author":"Zhang Ting","year":"2025","unstructured":"Ting Zhang, Chengran Yang, Yindu Su, Martin Weyssow, Hung Nguyen, Tan Bui, Hong Jin Kang, Yikun Li, Eng Lieh Ouh, Lwin Khin Shar, et al. 2025. Benchmarking Large Language Models for Multi-Language Software Vulnerability Detection. arXiv preprint arXiv:2503.01449 (2025)."},{"key":"e_1_2_1_82_1","volume-title":"Experimental Evaluation of Parameter-Efficient Fine-Tuning for Software Engineering Tasks. ACM Transactions on Software Engineering and Methodology","author":"Zou Wentao","year":"2025","unstructured":"Wentao Zou, Zongwen Shen, Qi Li, Jidong Ge, Chuanyi Li, Xiang Chen, Xiaoyu Shen, LiGuo Huang, and Bin Luo. 2025. Experimental Evaluation of Parameter-Efficient Fine-Tuning for Software Engineering Tasks. ACM Transactions on Software Engineering and Methodology (2025)."}],"container-title":["Proceedings of the ACM on Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3808198","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:04:39Z","timestamp":1782842679000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3808198"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":82,"journal-issue":{"issue":"FSE","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1145\/3808198"],"URL":"https:\/\/doi.org\/10.1145\/3808198","relation":{},"ISSN":["2994-970X"],"issn-type":[{"value":"2994-970X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]}}}