{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T07:17:00Z","timestamp":1783408620803,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T00:00:00Z","timestamp":1775952000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,12]]},"DOI":"10.1145\/3786181.3788712","type":"proceedings-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T06:28:24Z","timestamp":1783405704000},"page":"21-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Code vs Serialized AST Inputs for LLM-Based Code Summarization: An Empirical Study"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3360-9295","authenticated-orcid":false,"given":"Shijia","family":"Dong","sequence":"first","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1960-6515","authenticated-orcid":false,"given":"Haoruo","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1243-938X","authenticated-orcid":false,"given":"Paul","family":"Harvey","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,6]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3559555"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639183"},{"key":"e_1_3_3_2_4_2","unstructured":"Miltiadis Allamanis Marc Brockschmidt and Mahmoud Khademi. 2017. Learning to represent programs with graphs. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1711.00740 (2017)."},{"key":"e_1_3_3_2_5_2","unstructured":"Uri Alon Shaked Brody Omer Levy and Eran Yahav. 2018. code2seq: Generating sequences from structured representations of code. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1808.01400 (2018)."},{"key":"e_1_3_3_2_6_2","first-page":"65","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65\u201372."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPC52881.2021.00032"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSM.1998.738528"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3689488.3689990"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Ning Ding Yujia Qin Guang Yang Fuchao Wei Zonghan Yang Yusheng Su Shengding Hu Yulin Chen Chi-Min Chan Weize Chen et\u00a0al. 2023. Parameter-efficient fine-tuning of large-scale pre-trained language models. Nature Machine Intelligence 5 3 (2023) 220\u2013235.","DOI":"10.1038\/s42256-023-00626-4"},{"key":"e_1_3_3_2_11_2","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et\u00a0al. 2024. The llama 3 herd of models. arXiv e-prints (2024) arXiv\u20132407."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPC.2013.6613829"},{"key":"e_1_3_3_2_13_2","unstructured":"Chunrong Fang Weisong Sun Yuchen Chen Xiao Chen Zhao Wei Quanjun Zhang Yudu You Bin Luo Yang Liu and Zhenyu Chen. 2024. Esale: Enhancing code-summary alignment learning for source code summarization. IEEE Transactions on Software Engineering 50 8 (2024) 2077\u20132095."},{"key":"e_1_3_3_2_14_2","unstructured":"Daniel Fried Armen Aghajanyan Jessy Lin Sida Wang Eric Wallace Freda Shi Ruiqi Zhong Wen-tau Yih Luke Zettlemoyer and Mike Lewis. 2022. Incoder: A generative model for code infilling and synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.05999 (2022)."},{"key":"e_1_3_3_2_15_2","unstructured":"Daya Guo Shuo Ren Shuai Lu Zhangyin Feng Duyu Tang Shujie Liu Long Zhou Nan Duan Alexey Svyatkovskiy Shengyu Fu et\u00a0al. 2020. Graphcodebert: Pre-training code representations with data flow. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2009.08366 (2020)."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/1810295.1810335"},{"key":"e_1_3_3_2_17_2","unstructured":"Edward\u00a0J Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang Weizhu Chen et\u00a0al. 2022. Lora: Low-rank adaptation of large language models.ICLR 1 2 (2022) 3."},{"key":"e_1_3_3_2_18_2","unstructured":"Fan Hu Yanlin Wang Lun Du Hongyu Zhang Shi Han Dongmei Zhang and Xirong Li. 2022. Tackling long code search with splitting encoding and aggregating. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2208.11271 (2022)."},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3196321.3196334"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Xing Hu Ge Li Xin Xia David Lo and Zhi Jin. 2020. Deep code comment generation with hybrid lexical and syntactical information. Empirical Software Engineering 25 3 (2020) 2179\u20132217.","DOI":"10.1007\/s10664-019-09730-9"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1195"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2019.00013"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00087"},{"key":"e_1_3_3_2_24_2","unstructured":"Raymond Li Loubna\u00a0Ben Allal Yangtian Zi Niklas Muennighoff Denis Kocetkov Chenghao Mou Marc Marone Christopher Akiki Jia Li Jenny Chim et\u00a0al. 2023. Starcoder: may the source be with you!arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.06161 (2023)."},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPC52881.2021.00026"},{"key":"e_1_3_3_2_26_2","first-page":"74","volume-title":"Text summarization branches out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74\u201381."},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Junhao Lin and Lu Lu. 2021. Semantic feature learning via dual sequences for defect prediction. IEEE Access 9 (2021) 13112\u201313124.","DOI":"10.1109\/ACCESS.2021.3051957"},{"key":"e_1_3_3_2_28_2","first-page":"866","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track","author":"Lomshakov Vadim","year":"2024","unstructured":"Vadim Lomshakov, Andrey Podivilov, Sergey Savin, Oleg Baryshnikov, Alena Lisevych, and Sergey Nikolenko. 2024. Proconsul: Project context for code summarization with llms. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track. 866\u2013880."},{"key":"e_1_3_3_2_29_2","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1711.05101 (2017)."},{"key":"e_1_3_3_2_30_2","unstructured":"Shuai Lu Daya Guo Shuo Ren Junjie Huang Alexey Svyatkovskiy Ambrosio Blanco Colin Clement Dawn Drain Daxin Jiang Duyu Tang et\u00a0al. 2021. Codexglue: A machine learning benchmark dataset for code understanding and generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2102.04664 (2021)."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPC.2013.6613830"},{"key":"e_1_3_3_2_32_2","first-page":"311","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics","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\u2013318."},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACAIT63902.2024.11022067"},{"key":"e_1_3_3_2_34_2","unstructured":"Baptiste Roziere Jonas Gehring Fabian Gloeckle Sten Sootla Itai Gat Xiaoqing\u00a0Ellen Tan Yossi Adi Jingyu Liu Romain Sauvestre Tal Remez et\u00a0al. 2023. Code llama: Open foundation models for code. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.12950 (2023)."},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Chia-Yi Su and Collin McMillan. 2024. Distilled GPT for source code summarization. Automated Software Engineering 31 1 (2024) 22.","DOI":"10.1007\/s10515-024-00460-x"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Weisong Sun Chunrong Fang Yuchen Chen Quanjun Zhang Guanhong Tao Yudu You Tingxu Han Yifei Ge Yuling Hu Bin Luo et\u00a0al. 2024. An extractive-and-abstractive framework for source code summarization. ACM Transactions on Software Engineering and Methodology 33 3 (2024) 1\u201339.","DOI":"10.1145\/3632742"},{"key":"e_1_3_3_2_37_2","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:https:\/\/arXiv.org\/abs\/2407.07959 (2024)."},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510224"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Robert Tarjan. 1972. Depth-first search and linear graph algorithms. SIAM journal on computing 1 2 (1972) 146\u2013160.","DOI":"10.1137\/0201010"},{"key":"e_1_3_3_2_40_2","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238206"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"crossref","unstructured":"Yue Wang Weishi Wang Shafiq Joty and Steven\u00a0CH Hoi. 2021. Codet5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2109.00859 (2021).","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"e_1_3_3_2_43_2","unstructured":"Tong Ye Lingfei Wu Tengfei Ma Xuhong Zhang Yangkai Du Peiyu Liu Shouling Ji and Wenhai Wang. 2023. Cp-bcs: Binary code summarization guided by control flow graph and pseudo code. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.16853 (2023)."},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380383"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00086"},{"key":"e_1_3_3_2_46_2","unstructured":"Tianyi Zhang Varsha Kishore Felix Wu Kilian\u00a0Q Weinberger and Yoav Artzi. 2019. Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1904.09675 (2019)."},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"crossref","unstructured":"Xuejun Zhang Xia Hou Xiuming Qiao and Wenfeng Song. 2024. A review of automatic source code summarization. Empirical Software Engineering 29 6 (2024) 162.","DOI":"10.1007\/s10664-024-10553-6"},{"key":"e_1_3_3_2_48_2","unstructured":"Yuxiang Zhu and Minxue Pan. 2019. Automatic code summarization: A systematic literature review. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1909.04352 (2019)."}],"event":{"name":"LLM4Code '26: 3rd International Workshop on Large Language Models For Code","location":"Rio de Janeiro Brazil","acronym":"LLM4Code '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"]},"container-title":["Proceedings of the 3rd International Workshop on Large Language Models For Code"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3786181.3788712","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T06:30:27Z","timestamp":1783405827000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786181.3788712"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":47,"alternative-id":["10.1145\/3786181.3788712","10.1145\/3786181"],"URL":"https:\/\/doi.org\/10.1145\/3786181.3788712","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-07-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}