{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T11:34:10Z","timestamp":1791459250330,"version":"4.3.4"},"reference-count":103,"publisher":"Association for Computing Machinery (ACM)","issue":"FSE","license":[{"start":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T00:00:00Z","timestamp":1720742400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Softw. Eng."],"published-print":{"date-parts":[[2024,7,12]]},"abstract":"<jats:p>Large Language Models (LLMs) have recently been widely used for code generation. Due to the complexity and opacity of LLMs, little is known about how these models generate code. We made the first attempt to bridge this knowledge gap by investigating whether LLMs attend to the same parts of a task description as human programmers during code generation. An analysis of six LLMs, including GPT-4, on two popular code generation benchmarks revealed a consistent misalignment between LLMs\u2019 and programmers\u2019 attention. We manually analyzed 211 incorrect code snippets and found five attention patterns that can be used to explain many code generation errors. Finally, a user study showed that model attention computed by a perturbation-based method is often favored by human programmers. Our findings highlight the need for human-aligned LLMs for better interpretability and programmer trust.<\/jats:p>","DOI":"10.1145\/3660807","type":"journal-article","created":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T10:22:09Z","timestamp":1720779729000},"page":"2261-2284","source":"Crossref","is-referenced-by-count":18,"title":["Do Large Language Models Pay Similar Attention Like Human Programmers When Generating Code?"],"prefix":"10.1145","volume":"1","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1407-8522","authenticated-orcid":false,"given":"Bonan","family":"Kou","sequence":"first","affiliation":[{"name":"Purdue University, West Lafayette, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8867-6713","authenticated-orcid":false,"given":"Shengmai","family":"Chen","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4559-5426","authenticated-orcid":false,"given":"Zhijie","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Alberta, Edmonton, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8621-2420","authenticated-orcid":false,"given":"Lei","family":"Ma","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan"},{"name":"University of Alberta, Edmonton, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5468-9347","authenticated-orcid":false,"given":"Tianyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,12]]},"reference":[{"key":"e_1_3_1_2_2","unstructured":"2022. CodeParrot. https:\/\/github.com\/huggingface\/transformers\/tree\/main\/examples\/research_projects\/codeparrot."},{"key":"e_1_3_1_3_2","unstructured":"2023. ChatGPT. http:\/\/chat.openai.com."},{"key":"e_1_3_1_4_2","unstructured":"2023. GPT-4 Parameters: Unlimited guide NLP\u2019s Game-Changer. https:\/\/medium.com\/@mlubbad\/the-ultimate-guide-to-gpt-4-parameters-everything-you-need-to-know-about-nlps-game-changer-109b8767855a."},{"key":"e_1_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Wasi Ahmad Saikat Chakraborty Baishakhi Ray and Kai-Wei Chang. 2021. Unified Pre-training for Program Understanding and Generation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2655-2668.","DOI":"10.18653\/v1\/2021.naacl-main.211"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","unstructured":"Alex Andonian Quentin Anthony et al 2021. GPT-NeoX: Large Scale Autoregressive Language Modeling in PyTorch. https:\/\/doi.org\/10.5281\/zenodo.5879544 10.5281\/zenodo.5879544.","DOI":"10.5281\/zenodo.5879544"},{"key":"e_1_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Owura Asare Meiyappan Nagappan and N Asokan. 2022. Is github\u2019s copilot as bad as humans at introducing vulnerabilities in code? arXiv preprint arXiv:2204.04741 (2022).","DOI":"10.1007\/s10664-023-10380-1"},{"key":"e_1_3_1_8_2","unstructured":"Jacob Austin Augustus Odena et al. 2021. Program Synthesis with Large Language Models. arXiv preprint arXiv:2108.07732 (2021)."},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3591136"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586030"},{"key":"e_1_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Joshua Bensemann et al. 2022. Eye gaze and self-attention: How humans and transformers attend words in sentences. In Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics. 75-87.","DOI":"10.18653\/v1\/2022.cmcl-1.9"},{"key":"e_1_3_1_12_2","first-page":"896","volume-title":"International Conference on Machine Learning","author":"Bielik Pavol","year":"2020","unstructured":"Pavol Bielik and Martin Vechev 2020 Adversarial robustness for code In International Conference on Machine Learning. PMLR, 896\u2013907."},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3582083"},{"key":"e_1_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Angie Boggust Benjamin Hoover Arvind Satyanarayan and Hendrik Strobelt. 2022. Shared interest: Measuring human-ai alignment to identify recurring patterns in model behavior. In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems. 1-17.","DOI":"10.1145\/3491102.3501965"},{"key":"e_1_3_1_15_2","unstructured":"S\u00e9bastien Bubeck et al. 2023. Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712 (2023)."},{"key":"e_1_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Saikat Chakraborty et al. 2022. NatGen: generative pre-training by \u201cnaturalizing\u201d source code. In Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 18-30.","DOI":"10.1145\/3540250.3549162"},{"key":"e_1_3_1_17_2","unstructured":"Bei Chen et al. 2022. Codet: Code generation with generated tests. arXiv preprint arXiv:2207.10397 (2022)."},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3046646"},{"key":"e_1_3_1_19_2","unstructured":"Wenhu Chen Evgeny Matusov Shahram Khadivi and Jan-Thorsten Peter. 2016. Guided alignment training for topic-aware neural machine translation. arXiv preprint arXiv:1607.01628 (2016)."},{"key":"e_1_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Matteo Ciniselli Luca Pascarella and Gabriele Bavota. 2022. To what extent do deep learning-based code recommenders generate predictions by cloning code from the training set?. In Proceedings of the 19th International Conference on Mining Software Repositories. 167-178.","DOI":"10.1145\/3524842.3528440"},{"key":"e_1_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Kevin Clark Urvashi Khandelwal Omer Levy and Christopher D Manning. 2019. What Does BERT Look at? An Analysis of BERT\u2019s Attention. In Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP. 276-286.","DOI":"10.18653\/v1\/W19-4828"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1177\/001316446002000104"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1565"},{"key":"e_1_3_1_24_2","unstructured":"Misha Denil Alban Demiraj and Nando De Freitas. 2014. Extraction of salient sentences from labelled documents. arXiv preprint arXiv:1412.6815 (2014)."},{"key":"e_1_3_1_25_2","unstructured":"Giuseppe Destefanis Silvia Bartolucci and Marco Ortu. 2023. A Preliminary Analysis on the Code Generation Capabilities of GPT-3.5 and Bard AI Models for Java Functions. arXiv preprint arXiv:2305.09402 (2023)."},{"key":"e_1_3_1_26_2","unstructured":"Jacob Devlin et al. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics. 4171-4186."},{"key":"e_1_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Ahmed Elnaggar et al. 2021. CodeTrans: Towards Cracking the Language of Silicon\u2019s Code Through Self-Supervised Deep Learning and High Performance Computing. arXiv preprint arXiv:2104.02443 (2021).","DOI":"10.1101\/2020.07.12.199554"},{"key":"e_1_3_1_28_2","unstructured":"Mark Chen et al. 2021. Evaluating Large Language Models Trained on Code. (2021). arXiv:2107.03374 [cs.LG]"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3140587.3062351"},{"key":"e_1_3_1_30_2","unstructured":"Zhangyin Feng et al. 2020. CodeBERT: A Pre-Trained Model for Programming and Natural Language Processing. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management. 307-316."},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1037\/h0031619"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-23618-6"},{"key":"e_1_3_1_33_2","article-title":"InCoder: A Generative Model for Code Infilling and Synthesis","author":"Fried Daniel","year":"2023","unstructured":"Daniel Fried et al 2023 InCoder: A Generative Model for Code Infilling and Synthesis. The Eleventh International Conference on Learning Representations https:\/\/openreview.net\/forum?id=hQwb-lbM6EL.","journal-title":"The Eleventh International Conference on Learning Representations"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3019893"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3555590"},{"key":"e_1_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Mor Geva Avi Caciularu Kevin Ro Wang and Yoav Goldberg. 2022. Transformer feed-forward layers build predictions by promoting concepts in the vocabulary space. arXiv preprint arXiv:2203.14680 (2022).","DOI":"10.18653\/v1\/2022.emnlp-main.3"},{"key":"e_1_3_1_37_2","unstructured":"Daya Guo et al. 2020. Graphcodebert: Pre-training code representations with data flow. arXiv preprint arXiv:2009.08366 (2020)."},{"key":"e_1_3_1_38_2","doi-asserted-by":"crossref","unstructured":"Jiaqi Guo et al. 2019. Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 4524-4535.","DOI":"10.18653\/v1\/P19-1444"},{"key":"e_1_3_1_39_2","first-page":"2532","article-title":"Importance is in your attention: agent importance prediction for autonomous driving","author":"Hazard Christopher","year":"2022","unstructured":"Christopher Hazard et al 2022 Importance is in your attention: agent importance prediction for autonomous driving. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2532\u20132535.","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_1_40_2","unstructured":"Dan Hendrycks et al. 2021. Measuring Coding Challenge Competence With APPS. NeurIPS (2021)."},{"key":"e_1_3_1_41_2","unstructured":"Dan Hendrycks Collin Burns Steven Basart Andrew Critch Jerry Li Dawn Song and Jacob Steinhardt. 2020. Aligning AI with Shared Human Values. arXiv preprint arXiv:2008.02275 (2020)."},{"key":"e_1_3_1_42_2","unstructured":"Sara Hooker Dumitru Erhan Pieter-Jan Kindermans and Been Kim. 2018. Evaluating feature importance estimates. (2018)."},{"key":"e_1_3_1_43_2","doi-asserted-by":"crossref","first-page":"7840","DOI":"10.1609\/aaai.v35i9.16957","article-title":"Attributes-guided and pure-visual attention alignment for few-shot recognition","volume":"35","author":"Huang Siteng","year":"2021","unstructured":"Siteng Huang, Min Zhang, Yachen Kang, and Donglin Wang 2021 Attributes-guided and pure-visual attention alignment for few-shot recognition. Proceedings of the AAAI Conference on Artificial Intelligence 35 7840\u20137847.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"e_1_3_1_44_2","doi-asserted-by":"crossref","unstructured":"Paras Jain and Ajay Jain. 2021. Contrastive Code Representation Learning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.","DOI":"10.18653\/v1\/2021.emnlp-main.482"},{"key":"e_1_3_1_45_2","first-page":"57","volume-title":"2018 IEEE International Conference on Big Knowledge (ICBK)","author":"Jia Shaohua","year":"2018","unstructured":"Shaohua Jia et al 2018 Biometric recognition through eye movements using a recurrent neural network In 2018 IEEE International Conference on Big Knowledge (ICBK). IEEE, 57\u201364."},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE51524.2021.9678927"},{"key":"e_1_3_1_47_2","unstructured":"Iuliia Kotseruba Amir Rasouli and John K Tsotsos. 2016. Joint attention in autonomous driving (JAAD). arXiv preprint arXiv:1609.04741 (2016)."},{"key":"e_1_3_1_48_2","unstructured":"Bonan Kou. 2024. Attention-Alignment-Empirical-Study. https:\/\/github.com\/BonanKou\/Attention-Alignment-Empirical-Study."},{"issue":"3","key":"e_1_3_1_49_2","first-page":"411","article-title":"Reliability in content analysis: Some common misconceptions and recommendations","volume":"30","author":"Krippendorff Klaus","year":"2004","unstructured":"Klaus Krippendorff. 2004. Reliability in content analysis: Some common misconceptions and recommendations. Human communication research 30, 3 (2004), 411-433.","journal-title":"Human communication research"},{"key":"e_1_3_1_50_2","volume-title":"Content analysis: An introduction to its methodology","author":"Krippendorff Klaus","year":"2018","unstructured":"Klaus Krippendorff 2018 Content analysis: An introduction to its methodology. Sage publications."},{"key":"e_1_3_1_51_2","unstructured":"Sumith Kulal Panupong Pasupat Kartik Chandra Mina Lee Oded Padon Alex Aiken and Percy S Liang. 2019. Spoc: Search-based pseudocode to code. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_1_52_2","doi-asserted-by":"crossref","unstructured":"Jia Li Yongmin Li Ge Li Zhi Jin Yiyang Hao and Xing Hu. 2023. SkCoder: A Sketch-based Approach for Automatic Code Generation. arXiv preprint arXiv:2302.06144 (2023).","DOI":"10.1109\/ICSE48619.2023.00179"},{"key":"e_1_3_1_53_2","unstructured":"Jiwei Li Will Monroe and Dan Jurafsky. 2016. Understanding neural networks through representation erasure. arXiv preprint arXiv:1612.08220 (2016)."},{"key":"e_1_3_1_54_2","first-page":"59","volume-title":"2022 IEEE\/ACM 1st International Workshop on Natural Language-Based Software Engineering (NLBSE)","author":"Liguori Pietro","year":"2022","unstructured":"Pietro Liguori et al 2022 Can NMT understand me? towards perturbation-based evaluation of NMT models for code generation In 2022 IEEE\/ACM 1st International Workshop on Natural Language-Based Software Engineering (NLBSE). IEEE, 59\u201366."},{"issue":"1","key":"e_1_3_1_55_2","first-page":"651","article-title":"Nlize: A perturbation-driven visual interrogation tool for analyzing and interpreting natural language inference models","volume":"25","author":"Liu Shusen","year":"2018","unstructured":"Shusen Liu et al. 2018. Nlize: A perturbation-driven visual interrogation tool for analyzing and interpreting natural language inference models. IEEE transactions on visualization and computer graphics 25, 1 (2018), 651-660.","journal-title":"IEEE transactions on visualization and computer graphics"},{"key":"e_1_3_1_56_2","first-page":"408","volume-title":"2020 IEEE International Conference on Software Maintenance and Evolution (ICSME)","author":"Liu Xiaodong","year":"2020","unstructured":"Xiaodong Liu, Ying Xia, and David Lo 2020 An Empirical Study on the Usage of Transformer Models for Code Completion In 2020 IEEE International Conference on Software Maintenance and Evolution (ICSME). IEEE, 408\u2013418."},{"key":"e_1_3_1_57_2","unstructured":"Yue Liu Chakkrit Tantithamthavorn Yonghui Liu and Li Li. 2023. On the Reliability and Explainability of Automated Code Generation Approaches. arXiv preprint arXiv:2302.09587 (2023)."},{"key":"e_1_3_1_58_2","unstructured":"Scott M Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.11613\/BM.2012.031"},{"key":"e_1_3_1_60_2","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1109\/DEVLRN.2018.8761032","volume-title":"2018 Joint IEEE 8th international conference on development and learning and epigenetic robotics (ICDL-EpiRob)","author":"Melicio Cristina","year":"2018","unstructured":"Cristina Melicio et al. 2018. Object detection and localization with artificial foveal visual attention. In 2018 Joint IEEE 8th international conference on development and learning and epigenetic robotics (ICDL-EpiRob). IEEE, 101-106."},{"key":"e_1_3_1_61_2","unstructured":"Christoph Molnar. 2020. Interpretable machine learning. Lulu. com."},{"key":"e_1_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.2675"},{"key":"e_1_3_1_63_2","unstructured":"Erik Nijkamp Bo Pang et al. 2023. CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_1_64_2","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1007\/978-3-030-50347-5_25","volume-title":"Image Analysis and Recognition: 17th International Conference","author":"Nunes Afonso","year":"2020","unstructured":"Afonso Nunes, Rui Figueiredo, and Plinio Moreno 2020 Learning to search for objects in images from human gaze sequences In Image Analysis and Recognition: 17th International Conference. Springer, 280\u2013292."},{"key":"e_1_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE51524.2021.9678712"},{"key":"e_1_3_1_66_2","doi-asserted-by":"crossref","unstructured":"Kishore Papineni et al. 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.","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_1_67_2","doi-asserted-by":"crossref","unstructured":"Md Rizwan Parvez Wasi Ahmad Saikat Chakraborty Baishakhi Ray and Kai-Wei Chang. 2021. Retrieval Augmented Code Generation and Summarization. In Findings of the Association for Computational Linguistics: EMNLP 2021 2021. 2719-2734.","DOI":"10.18653\/v1\/2021.findings-emnlp.232"},{"key":"e_1_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833571"},{"key":"e_1_3_1_69_2","doi-asserted-by":"crossref","unstructured":"Md Rafiqul Islam Rabin Vincent J Hellendoorn and Mohammad Amin Alipour. 2021. Understanding neural code intelligence through program simplification. In Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 441-452.","DOI":"10.1145\/3468264.3468539"},{"key":"e_1_3_1_70_2","unstructured":"Shuo Renetal. 2020. Codebleu: a method for automatic evaluation of code synthesis. arXiv preprintarXiv:2009.10297 (2020)."},{"key":"e_1_3_1_71_2","doi-asserted-by":"crossref","unstructured":"Marco Tulio Ribeiro et al. 2016. \u201cWhy should i trust you?\u201d Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. 1135-1144.","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_1_72_2","first-page":"327","volume-title":"2021 IEEE\/ACM 43rd International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)","author":"Rodrigues Rafael R","year":"2021","unstructured":"Rafael R Rodrigues et al 2021 Studying the usage of text-to-text transfer transformer to support code-related tasks In 2021 IEEE\/ACM 43rd International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP). IEEE, 327\u2013336."},{"key":"e_1_3_1_73_2","first-page":"1","volume-title":"2023 ACM\/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM)","author":"Sarker Jaydeb","year":"2023","unstructured":"Jaydeb Sarker, Sayma Sultana, Steven R Wilson, and Amiangshu Bosu 2023 ToxiSpanSE: An Explainable Toxicity Detection in Code Review Comments In 2023 ACM\/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM). IEEE, 1\u201312."},{"key":"e_1_3_1_74_2","doi-asserted-by":"crossref","unstructured":"Ramprasaath R Selvaraju Michael Cogswell Abhishek Das Ramakrishna Vedantam Devi Parikh and Dhruv Batra. 2017. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision. 618-626.","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_1_75_2","doi-asserted-by":"crossref","unstructured":"Sijie Shen Xiang Zhu Yihong Dong Qizhi Guo Yankun Zhen and Ge Li. 2022. Incorporating domain knowledge through task augmentation for front-end JavaScript code generation. In Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 1533-1543.","DOI":"10.1145\/3540250.3558965"},{"key":"e_1_3_1_76_2","doi-asserted-by":"crossref","unstructured":"Donghee Shin. 2021. The effects of explainability and causability on perception trust and acceptance: Implications for explainable AI. International Journal of Human-Computer Studies 146 (2021) 102551.","DOI":"10.1016\/j.ijhcs.2020.102551"},{"key":"e_1_3_1_77_2","first-page":"3145","volume-title":"International conference on machine learning","author":"Shrikumar Avanti","year":"2017","unstructured":"Avanti Shrikumar, Peyton Greenside, and Anshul Kundaje. 2017. Learning important features through propagating activation differences. In International conference on machine learning. PMLR, 3145-3153."},{"key":"e_1_3_1_78_2","doi-asserted-by":"publisher","DOI":"10.1109\/SCAM55253.2022.00014"},{"key":"e_1_3_1_79_2","unstructured":"Karen Simonyan Andrea Vedaldi and Andrew Zisserman. 2013. Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013)."},{"key":"e_1_3_1_80_2","article-title":"Generating Adversarial Computer Programs using Optimized Obfuscations","author":"Srikant Shashank","year":"2020","unstructured":"Shashank Srikant et al 2020 Generating Adversarial Computer Programs using Optimized Obfuscations. International Conference on Learning Representations.","journal-title":"International Conference on Learning Representations"},{"key":"e_1_3_1_81_2","doi-asserted-by":"crossref","unstructured":"Andrea Stocco et al. 2022. Thirdeye: Attention maps for safe autonomous driving systems. In Proceedings of the 37th IEEE\/ACM International Conference on Automated Software Engineering. 1-12.","DOI":"10.1145\/3551349.3556968"},{"key":"e_1_3_1_82_2","first-page":"3319","volume-title":"International conference on machine learning","author":"Sundararajan Mukund","year":"2017","unstructured":"Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic attribution for deep networks. In International conference on machine learning. PMLR, 3319-3328."},{"key":"e_1_3_1_83_2","volume-title":"Natural Language Processing with Transformers: Building Language Applications with Hugging Face","author":"Tunstall Lewis","year":"2022","unstructured":"Lewis Tunstall, Leandro von Werra, and Thomas Wolf. 2022 Natural Language Processing with Transformers: Building Language Applications with Hugging Face. O\u2019Reilly Media, Incorporated."},{"key":"e_1_3_1_84_2","doi-asserted-by":"crossref","unstructured":"Priyan Vaithilingam et al. 2022. Expectation vs. experience: Evaluating the usability of code generation tools powered by large language models. In CHI conference on human factors in computing systems extended abstracts. 1-7.","DOI":"10.1145\/3491101.3519665"},{"key":"e_1_3_1_85_2","unstructured":"Shikhar Vashishth Shyam Upadhyay Gaurav Singh Tomar and Manaal Faruqui. 2019. Attention interpretability across nlp tasks. arXiv preprint arXiv:1909.11218 (2019)."},{"key":"e_1_3_1_86_2","doi-asserted-by":"crossref","unstructured":"Yao Wan Wei Zhao Hongyu Zhang Yulei Sui Guandong Xu and Hai Jin. 2022. What do they capture? a structural analysis of pre-trained language models for source code. In Proceedings of the 44th International Conference on Software Engineering. 2377-2388.","DOI":"10.1145\/3510003.3510050"},{"key":"e_1_3_1_87_2","doi-asserted-by":"crossref","unstructured":"Bailin Wang et al. 2020. RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers. In Proceedings of the 58th Annual Meeting ofthe Association for Computational Linguistics. 7567-7578.","DOI":"10.18653\/v1\/2020.acl-main.677"},{"key":"e_1_3_1_88_2","unstructured":"Ben Wang and Aran Komatsuzaki. 2021. GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model. https:\/\/github.com\/kingoflolz\/mesh-transformer-jax."},{"key":"e_1_3_1_89_2","doi-asserted-by":"crossref","unstructured":"Yue Wang Weishi Wang Shafiq Joty and Steven CH Hoi. 2021. CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 8696-8708.","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"e_1_3_1_90_2","doi-asserted-by":"crossref","unstructured":"Katharina Weitz et al. 2019. \u201cDo you trust me?\u201d Increasing user-trust by integrating virtual agents in explainable AI interaction design. In Proceedings of the 19th ACM International Conference on Intelligent Virtual Agents. 7-9.","DOI":"10.1145\/3308532.3329441"},{"key":"e_1_3_1_91_2","doi-asserted-by":"crossref","unstructured":"Zhiyong Wu Yun Chen Ben Kao and Qun Liu. 2020. Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 4166-4176.","DOI":"10.18653\/v1\/2020.acl-main.383"},{"key":"e_1_3_1_92_2","doi-asserted-by":"crossref","unstructured":"Frank F Xu Uri Alon Graham Neubig and Vincent Josua Hellendoorn. 2022. A systematic evaluation of large language models of code. In Proceedings of the 6th ACM SIGPLAN International Symposium on Machine Programming. 1-10.","DOI":"10.1145\/3520312.3534862"},{"key":"e_1_3_1_93_2","doi-asserted-by":"publisher","DOI":"10.1145\/3428230"},{"key":"e_1_3_1_94_2","doi-asserted-by":"crossref","unstructured":"Burak Yetistiren Isik Ozsoy and Eray Tuzun. 2022. Assessing the quality of GitHub copilot\u2019s code generation. In Proceedings of the 18th International Conference on Predictive Models and Data Analytics in Software Engineering. 62-71.","DOI":"10.1145\/3558489.3559072"},{"key":"e_1_3_1_95_2","doi-asserted-by":"publisher","unstructured":"Daoguang Zan Bei Chen et al. 2022. CERT: Continual Pre-training on Sketches for Library-oriented Code Generation. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence IJCAI 2022 Vienna Austria 23-29 July 2022 Luc De Raedt (Ed.). ijcai.org 2369-2375. https:\/\/doi.org\/10.24963\/ijcai.2022\/329 10.24963\/ijcai.2022\/329","DOI":"10.24963\/ijcai.2022\/329"},{"key":"e_1_3_1_96_2","doi-asserted-by":"crossref","first-page":"818","DOI":"10.1007\/978-3-319-10590-1_53","volume-title":"Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part 113","author":"Zeiler Matthew D","year":"2014","unstructured":"Matthew D Zeiler and Rob Fergus. 2014. Visualizing and understanding convolutional networks. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part 113. Springer, 818-833."},{"key":"e_1_3_1_97_2","doi-asserted-by":"crossref","unstructured":"Yu Zeng et al. 2020. RECPARSER: A Recursive Semantic Parsing Framework for Text-to-SQL Task. In IJCAI. 3644-3650.","DOI":"10.24963\/ijcai.2020\/504"},{"key":"e_1_3_1_98_2","doi-asserted-by":"crossref","unstructured":"Zhengran Zeng Hanzhuo Tan Haotian Zhang Jing Li Yuqun Zhang and Lingming Zhang. 2022. An extensive study on pre-trained models for program understanding and generation. In Proceedings of the 31st ACM SIGSOFT International Symposium on Software Testing and Analysis. 39-51.","DOI":"10.1145\/3533767.3534390"},{"key":"e_1_3_1_99_2","doi-asserted-by":"crossref","first-page":"1169","DOI":"10.1609\/aaai.v34i01.5469","article-title":"Generating adversarial examples for holding robustness of source code processing models","volume":"34","author":"Zhang Huangzhao","year":"2020","unstructured":"Huangzhao Zhang, Zhuo Li, Ge Li, Lei Ma, Yang Liu, and Zhi Jin 2020 Generating adversarial examples for holding robustness of source code processing models. Proceedings of the AAAI Conference on Artificial Intelligence 34 1169\u20131176.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"e_1_3_1_100_2","unstructured":"Kechi Zhang Ge Li and Zhi Jin. 2022. What does Transformer learn about source code? arXiv preprint arXiv:2207.08466 (2022)."},{"key":"e_1_3_1_101_2","doi-asserted-by":"crossref","unstructured":"Zhaowei Zhang Hongyu Zhang Beijun Shen and Xiaodong Gu. 2022. Diet code is healthy: Simplifying programs for pre-trained models of code. In Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 1073-1084.","DOI":"10.1145\/3540250.3549094"},{"key":"e_1_3_1_102_2","doi-asserted-by":"crossref","unstructured":"Haiying Zhao Wei Zhou Xiaogang Hou and Hui Zhu. 2020. Double attention for multi-label image classification. IEEE Access 8 (2020) 225539-225550.","DOI":"10.1109\/ACCESS.2020.3044446"},{"key":"e_1_3_1_103_2","first-page":"2921","article-title":"Learning deep features for discriminative localization","author":"Zhou Bolei","year":"2016","unstructured":"Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba 2016 Learning deep features for discriminative localization. Proceedings of the IEEE conference on computer vision and pattern recognition 2921\u20132929.","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"e_1_3_1_104_2","doi-asserted-by":"crossref","unstructured":"Terry Yue Zhuo Zhuang Li Yujin Huang Fatemeh Shiri Weiqing Wang Gholamreza Haffari and Yuan-Fang Li 2023 On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codex In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics 1090\u20131102.","DOI":"10.18653\/v1\/2023.eacl-main.77"}],"container-title":["Proceedings of the ACM on Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3660807","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3660807","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T08:00:20Z","timestamp":1770192020000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3660807"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,12]]},"references-count":103,"journal-issue":{"issue":"FSE","published-print":{"date-parts":[[2024,7,12]]}},"alternative-id":["10.1145\/3660807"],"URL":"https:\/\/doi.org\/10.1145\/3660807","relation":{},"ISSN":["2994-970X"],"issn-type":[{"value":"2994-970X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,12]]}}}