{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T15:44:27Z","timestamp":1778168667512,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,17]]},"DOI":"10.1145\/3799830.3799878","type":"proceedings-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T06:45:08Z","timestamp":1777013108000},"page":"306-315","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Autograder+: A Multi-Faceted AI Framework for Rich Pedagogical Feedback in Programming Education"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2682-9551","authenticated-orcid":false,"given":"Vikrant","family":"Sahu","sequence":"first","affiliation":[{"name":"Computer Science and Engineering, Indian Institute of Technology, Bhilai, Durg, Chhattishgarh, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8568-2949","authenticated-orcid":false,"given":"Gagan Raj","family":"Gupta","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology, Bhilai, Durg, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8777-7363","authenticated-orcid":false,"given":"Raghav","family":"Borikar","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology, Bhilai, Durg, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6205-3683","authenticated-orcid":false,"given":"Nitin Gautam","family":"Mane","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology, Bhilai, Durg, India"}]}],"member":"320","published-online":{"date-parts":[[2026,4,23]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Abanoub\u00a0E. Abdelmalak Mohamed\u00a0A. Elsayed David Abercrombie and Ilhami Torunoglu. 2025. An AST-guided LLM Approach for SVRF Code Synthesis. arXiv:https:\/\/arXiv.org\/abs\/2507.00352\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2507.00352"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/FIE56618.2022.9962650"},{"key":"e_1_3_3_2_4_2","unstructured":"Wasi\u00a0Uddin Ahmad Sean Narenthiran and Somshubra Majumdar. 2025. OpenCodeReasoning: Advancing Data Distillation for Competitive Coding. (2025). arXiv:https:\/\/arXiv.org\/abs\/2504.01943\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2504.01943"},{"key":"e_1_3_3_2_5_2","unstructured":"Mohammad Akyash Kimia\u00a0Zamiri Azar and Hadi\u00a0Mardani Kamali. 2025. StepGrade: Grading Programming Assignments with Context-Aware LLMs. arXiv:https:\/\/arXiv.org\/abs\/2503.20851\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2503.20851"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","unstructured":"Nico Andersen Julia Mang Frank Goldhammer and Fabian Zehner. 2025. Algorithmic Fairness in Automatic Short Answer Scoring. International Journal of Artificial Intelligence in Education (2025). 10.1007\/s40593-025-00495-5","DOI":"10.1007\/s40593-025-00495-5"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3708319.3733808"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","unstructured":"Seyyed\u00a0Kazem Banihashem Omid Noroozi Hassan Khosravi Christian\u00a0D. Schunn and Hendrik Drachsler. 2025. Pedagogical framework for hybrid intelligent feedback. Innovations in Education and Teaching International (2025). 10.1080\/14703297.2025.2499174","DOI":"10.1080\/14703297.2025.2499174"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3649217.3653543"},{"key":"e_1_3_3_2_10_2","unstructured":"Antonin Berthon and Mihaela van\u00a0der Schaar. 2025. Language Bottleneck Models: A Framework for Interpretable Knowledge Tracing and Beyond. arXiv:https:\/\/arXiv.org\/abs\/2506.16982\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2506.16982"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","unstructured":"Sumie Tsz\u00a0Sum Chan Noble Po\u00a0Kan Lo and Alan Man\u00a0Him Wong. 2024. Enhancing university level English proficiency with generative AI: Empirical insights into automated feedback and learning outcomes. Contemporary Educational Technology 16 4 (2024). 10.30935\/cedtech\/15607","DOI":"10.30935\/cedtech\/15607"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","unstructured":"S\u00e9bastien Comb\u00e9fis. 2022. Automated Code Assessment for Education: Review Classification and Perspectives on Techniques and Tools. Software 1 1 (2022) 3\u201330. 10.3390\/software1010002","DOI":"10.3390\/software1010002"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3634814.3634816"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Wei Dai Yi-Shan Tsai Jionghao Lin Ahmad Aldino Hua Jin Tongguang Li Dragan Ga\u0161evi\u0107 and Guanliang Chen. 2024. Assessing the proficiency of large language models in automatic feedback generation: An evaluation study. Computers and Education: Artificial Intelligence 7 (2024) 100299. 10.1016\/j.caeai.2024.100299","DOI":"10.1016\/j.caeai.2024.100299"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","unstructured":"Erkan Er G\u00f6khan Ak\u00e7ap\u0131nar Alper Bayaz\u0131t Omid Noroozi and Seyyed\u00a0Kazem Banihashem. 2025. Assessing student perceptions and use of instructor versus AI-generated feedback. British Journal of Educational Technology 56 3 (2025) 1074\u20131091. 10.1111\/bjet.13558","DOI":"10.1111\/bjet.13558"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","unstructured":"Est\u00e9vez-Ayres I. Callejo P. and Hombrados-Herrera. 2024. Evaluation of LLM Tools for Feedback Generation in a University Programming Course. International Journal of Artificial Intelligence in Education (2024). 10.1007\/s40593-024-00406-0","DOI":"10.1007\/s40593-024-00406-0"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","unstructured":"D. Federiakin. 2024. Prompt Engineering as a New 21st Century Skill. Frontiers in Education (2024). 10.3389\/feduc.2024.1366434","DOI":"10.3389\/feduc.2024.1366434"},{"key":"e_1_3_3_2_18_2","unstructured":"Zhangyin Feng Daya Guo Duyu Tang Nan Duan Xiaocheng Feng Ming Gong Linjun Shou Bing Qin Ting Liu Daxin Jiang and Ming Zhou. 2020. CodeBERT: A Pre-Trained Model for Programming and Natural Languages. arXiv:https:\/\/arXiv.org\/abs\/2002.08155\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2002.08155"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.bea-1.35"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","unstructured":"Alekzander\u00a0D Green. 2025. AN ANALYSIS OF LLM USE IN INTRODUCTORY PROGRAMMING EDUCATION AND DEVELOPMENT OF AI RESISTANT ASSESSMENTS VIA CODE REVIEWS. (6 2025). 10.25394\/PGS.29189570.v1","DOI":"10.25394\/PGS.29189570.v1"},{"key":"e_1_3_3_2_21_2","unstructured":"Daya Guo Qihao Zhu Dejian Yang Zhenda Xie Kai Dong Wentao Zhang Guanting Chen Xiao Bi Y. Wu Y.\u00a0K. Li Fuli Luo Yingfei Xiong and Wenfeng Liang. 2024. DeepSeek-Coder: When the Large Language Model Meets Programming \u2013 The Rise of Code Intelligence. arXiv:https:\/\/arXiv.org\/abs\/2401.14196\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2401.14196"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPC66645.2025.00025"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","unstructured":"Michael Henderson Margaret Bearman Jennifer Chung Tim Fawns Simon\u00a0Buckingham Shum Kelly\u00a0E. Matthews and Jimena de Mello\u00a0Heredia. 2025. Comparing Generative AI and teacher feedback: student perceptions of usefulness and trustworthiness. Assessment & Evaluation in Higher Education (2025). 10.1080\/02602938.2025.2502582","DOI":"10.1080\/02602938.2025.2502582"},{"key":"e_1_3_3_2_24_2","unstructured":"Yann Hicke Anmol Agarwal Qianou Ma and Paul Denny. 2023. AI-TA: Towards an Intelligent Question-Answer Teaching Assistant using Open-Source LLMs. arXiv:https:\/\/arXiv.org\/abs\/2311.02775\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2311.02775"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","unstructured":"Jamiu\u00a0Adekunle Idowu. 2024. Debiasing Education Algorithms. International Journal of Artificial Intelligence in Education 34 (2024) 1510\u20131540. 10.1007\/s40593-023-00389-4","DOI":"10.1007\/s40593-023-00389-4"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","unstructured":"Lucas\u00a0Jasper Jacobsen and Kira\u00a0Elena Weber. 2025. The Promises and Pitfalls of Large Language Models as Feedback Providers: A Study of Prompt Engineering and the Quality of AI-Driven Feedback. AI 6 2 (2025). 10.3390\/ai6020035","DOI":"10.3390\/ai6020035"},{"key":"e_1_3_3_2_27_2","unstructured":"Addison Jadwin and Catherine Huang. 2023. Improving minBERT Performance on Multiple Tasks through In-domain Pretraining Negatives Ranking Loss Learning and Hyperparameter Optimization."},{"key":"e_1_3_3_2_28_2","unstructured":"Prannay Khosla Piotr Teterwak Chen Wang Aaron Sarna Yonglong Tian Phillip Isola Aaron Maschinot Ce Liu and Dilip Krishnan. 2020. Supervised Contrastive Learning. Advances in Neural Information Processing Systems 33 (2020) 18661\u201318673."},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CITSM.2016.7577578"},{"key":"e_1_3_3_2_30_2","unstructured":"Chungpa Lee Sehee Lim Kibok Lee and Jy yong Sohn. 2025. On the Similarities of Embeddings in Contrastive Learning. arXiv:https:\/\/arXiv.org\/abs\/2506.09781\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2506.09781"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/SNPD61259.2024.10673924"},{"key":"e_1_3_3_2_32_2","unstructured":"Xiaoqi Li Yingjie Mao Zexin Lu Wenkai Li and Zongwei Li. 2025. SCLA: Automated Smart Contract Summarization via LLMs and Control Flow Prompt. arXiv:https:\/\/arXiv.org\/abs\/2402.04863\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2402.04863"},{"key":"e_1_3_3_2_33_2","unstructured":"Zhiyu Li Shuai Lu Daya Guo Nan Duan Shailesh Jannu Grant Jenks Deep Majumder Jared Green Alexey Svyatkovskiy Shengyu Fu and Neel Sundaresan. 2022. Automating Code Review Activities by Large-Scale Pre-training. arXiv:https:\/\/arXiv.org\/abs\/2203.09095\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2203.09095"},{"key":"e_1_3_3_2_34_2","unstructured":"Leland McInnes John Healy and James Melville. 2020. UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction. arXiv:https:\/\/arXiv.org\/abs\/1802.03426\u00a0[stat.ML] https:\/\/arxiv.org\/abs\/1802.03426"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","unstructured":"Marcus Messer Neil C.\u00a0C. Brown Michael K\u00f6lling and Miaojing Shi. 2024. Automated Grading and Feedback Tools for Programming Education: A Systematic Review. ACM Transactions on Computing Education 24 1 (Feb. 2024) 1\u201343. 10.1145\/3636515","DOI":"10.1145\/3636515"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","unstructured":"Marcus Messer Neil C.\u00a0C. Brown Michael K\u00f6lling and Miaojing Shi. 2024. Automated Grading and Feedback Tools for Programming Education: A Systematic Review. ACM Transactions on Computing Education 24 1 (Feb. 2024) 1\u201343. 10.1145\/3636515","DOI":"10.1145\/3636515"},{"key":"e_1_3_3_2_37_2","unstructured":"Meta AI. 2024. Llama-3.2-3B Hugging Face Model Card. https:\/\/huggingface.co\/meta-llama\/Llama-3.2-3B"},{"key":"e_1_3_3_2_38_2","unstructured":"Microsoft. 2025. Phi-4-reasoning Hugging Face Model Card. https:\/\/huggingface.co\/microsoft\/Phi-4-reasoning"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3702652.3744220"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","unstructured":"Andre\u00a0Fabiano Pereira and Rafael Ferreira\u00a0Mello. 2025. A Systematic Literature Review on Large Language Models Applications in Computer Programming Teaching Evaluation Process. IEEE Access 13 (2025) 113449\u2013113460. 10.1109\/ACCESS.2025.3584060","DOI":"10.1109\/ACCESS.2025.3584060"},{"key":"e_1_3_3_2_41_2","unstructured":"Qwen : An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei Huan Lin Jian Yang Jianhong Tu Jianwei Zhang Jianxin Yang Jiaxi Yang Jingren Zhou Junyang Lin Kai Dang Keming Lu Keqin Bao Kexin Yang Le Yu Mei Li Mingfeng Xue Pei Zhang Qin Zhu Rui Men Runji Lin Tianhao Li Tianyi Tang Tingyu Xia Xingzhang Ren Xuancheng Ren Yang Fan Yang Su Yichang Zhang Yu Wan Yuqiong Liu Zeyu Cui Zhenru Zhang and Zihan Qiu. 2025. Qwen2.5 Technical Report. arXiv:https:\/\/arXiv.org\/abs\/2412.15115\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2412.15115"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","unstructured":"Dmitri Roussinov Serge Sharoff and Natalya Puchnina. 2023. Fine-tuning language models to recognize semantic relations. Language Resources & Evaluation 57 4 (2023) 1463\u20131486. 10.1007\/s10579-023-09677-w","DOI":"10.1007\/s10579-023-09677-w"},{"key":"e_1_3_3_2_43_2","unstructured":"Pranab Sahoo Ayush\u00a0Kumar Singh Sriparna Saha Vinija Jain Samrat Mondal and Aman Chadha. 2025. A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications. arXiv:https:\/\/arXiv.org\/abs\/2402.07927\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2402.07927"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","unstructured":"Johannes Schneider Robin Richner and Micha Riser. 2023. Towards Trustworthy AutoGrading of Short Multi-lingual Multi-type Answers. International Journal of Artificial Intelligence in Education 33 (2023) 88\u2013118. 10.1007\/s40593-022-00289-z","DOI":"10.1007\/s40593-022-00289-z"},{"key":"e_1_3_3_2_45_2","unstructured":"Niklas Scholz Manh\u00a0Hung Nguyen Adish Singla and Tomohiro Nagashima. 2025. Partnering with AI: A Pedagogical Feedback System for LLM Integration into Programming Education. arXiv:https:\/\/arXiv.org\/abs\/2507.00406\u00a0[cs.CY] https:\/\/arxiv.org\/abs\/2507.00406"},{"key":"e_1_3_3_2_46_2","unstructured":"Priscylla Silva and Evandro Costa. 2025. Assessing Large Language Models for Automated Feedback Generation in Learning Programming Problem Solving. arXiv preprint (2025). https:\/\/arxiv.org\/abs\/2503.14630"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3051457.3051466"},{"key":"e_1_3_3_2_48_2","unstructured":"Tommaso Soru and Jim Marshall. 2025. Leveraging Log Probabilities in Language Models to Forecast Future Events. arXiv:https:\/\/arXiv.org\/abs\/2501.04880\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2501.04880"},{"key":"e_1_3_3_2_49_2","unstructured":"Xiaohang Tang Sam Wong Marcus Huynh Zicheng He Yalong Yang and Yan Chen. 2024. SPHERE: Scaling Personalized Feedback in Programming Classrooms with Structured Review of LLM Outputs. arXiv:https:\/\/arXiv.org\/abs\/2410.16513\u00a0[cs.HC] https:\/\/arxiv.org\/abs\/2410.16513"},{"key":"e_1_3_3_2_50_2","unstructured":"Falcon-LLM Team. 2024. The Falcon 3 Family of Open Models. https:\/\/huggingface.co\/blog\/falcon3"},{"key":"e_1_3_3_2_51_2","volume-title":"arXiv preprint","author":"Tseng En-Qi","year":"2025","unstructured":"En-Qi Tseng, Pei-Cing Huang, Chan Hsu, et\u00a0al. 2025. CodEv: An Automated Grading Framework Leveraging Large Language Models for Consistent and Constructive Feedback. In arXiv preprint. https:\/\/arxiv.org\/abs\/2501.10421"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData62323.2024.10825949"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"crossref","unstructured":"Yue Wang Hung Le Akhilesh\u00a0Deepak Gotmare Nghi D.\u00a0Q. Bui Junnan Li and Steven C.\u00a0H. Hoi. 2023. CodeT5+: Open Code Large Language Models for Code Understanding and Generation. arXiv:https:\/\/arXiv.org\/abs\/2305.07922\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2305.07922","DOI":"10.18653\/v1\/2023.emnlp-main.68"},{"key":"e_1_3_3_2_54_2","unstructured":"Yuchen Wei Dennis Pearl Matthew Beckman and Rebecca\u00a0J. Passonneau. 2025. Concept-based Rubrics Improve LLM Formative Assessment and Data Synthesis. arXiv:https:\/\/arXiv.org\/abs\/2504.03877\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2504.03877"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","unstructured":"Qunai Xu Yijia Liu and Xue Li. 2025. Unlocking student potential: How AI-driven personalized feedback shapes goal achievement self-efficacy and learning engagement through a self-determination lens. Learning and Motivation 91 (2025) 102138. 10.1016\/j.lmot.2025.102138","DOI":"10.1016\/j.lmot.2025.102138"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","unstructured":"M. Yousef K. Mohamed and W. Medhat. 2025. BeGrading: Large Language Models for Enhanced Feedback in Programming Education. Neural Computing and Applications 37 (2025) 1027\u20131040. 10.1007\/s00521-024-10449-y","DOI":"10.1007\/s00521-024-10449-y"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29619"}],"event":{"name":"CODS 2025: 13th ACM IKDD International Conference on Data Science","location":"Pune India","acronym":"CODS 2025"},"container-title":["Proceedings of the 13th ACM IKDD International Conference on Data Science"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3799830.3799878","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T07:11:40Z","timestamp":1777014700000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799830.3799878"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,17]]},"references-count":56,"alternative-id":["10.1145\/3799830.3799878","10.1145\/3799830"],"URL":"https:\/\/doi.org\/10.1145\/3799830.3799878","relation":{},"subject":[],"published":{"date-parts":[[2025,12,17]]},"assertion":[{"value":"2026-04-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}