{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T16:39:38Z","timestamp":1779208778990,"version":"3.51.4"},"reference-count":86,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T00:00:00Z","timestamp":1762992000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T00:00:00Z","timestamp":1762992000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20B2047"],"award-info":[{"award-number":["U20B2047"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072421"],"award-info":[{"award-number":["62072421"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62002334"],"award-info":[{"award-number":["62002334"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102386"],"award-info":[{"award-number":["62102386"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62121002"],"award-info":[{"award-number":["62121002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s10664-025-10748-5","type":"journal-article","created":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T02:27:16Z","timestamp":1763000836000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["An empirical study on the effectiveness of large language models for binary code understanding"],"prefix":"10.1007","volume":"31","author":[{"given":"Xiuwei","family":"Shang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenkan","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3992-9509","authenticated-orcid":false,"given":"Shaoyin","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoqiang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gangyang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nenghai","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,13]]},"reference":[{"key":"10748_CR1","first-page":"260","volume-title":"2023 IEEE International Conference on Software Analysis","author":"A Al-Kaswan","year":"2023","unstructured":"Al-Kaswan A, Ahmed T, Izadi M, Sawant AA, Devanbu P, van Deursen A (2023) Extending source code pre-trained language models to summarise decompiled binaries. 2023 IEEE International Conference on Software Analysis. Evolution and Reengineering (SANER), IEEE, pp 260\u2013271"},{"key":"10748_CR2","doi-asserted-by":"crossref","unstructured":"Black S, Biderman S, Hallahan E, Anthony Q, Gao L, Golding L, He H, Leahy C, McDonell K, Phang J, et\u00a0al (2022) Gpt-neox-20b: An open-source autoregressive language model. arXiv:2204.06745","DOI":"10.18653\/v1\/2022.bigscience-1.9"},{"key":"10748_CR3","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A et al (2020) Language models are few-shot learners. Adv Neural Inf Process Syst 33:1877\u20131901","journal-title":"Adv Neural Inf Process Syst"},{"issue":"5","key":"10748_CR4","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1016\/j.neuron.2024.01.016","volume":"112","author":"D Bzdok","year":"2024","unstructured":"Bzdok D, Thieme A, Levkovskyy O, Wren P, Ray T, Reddy S (2024) Data science opportunities of large language models for neuroscience and biomedicine. Neuron 112(5):698\u2013717","journal-title":"Neuron"},{"issue":"4","key":"10748_CR5","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1145\/1924421.1924451","volume":"54","author":"G Canfora","year":"2011","unstructured":"Canfora G, Di Penta M, Cerulo L (2011) Achievements and challenges in software reverse engineering. Commun ACM 54(4):142\u2013151","journal-title":"Commun ACM"},{"key":"10748_CR6","unstructured":"Chen B, Zhang Z, Langren\u00e9 N, Zhu S (2023a) Unleashing the potential of prompt engineering in large language models: a comprehensive review. arXiv:2310.14735"},{"key":"10748_CR7","first-page":"1","volume-title":"2023 20th Annual International Conference on Privacy","author":"G Chen","year":"2023","unstructured":"Chen G, Gao H, Zhang J, He Y, Cheng S, Zhang W (2023) Investigating neural-based function name reassignment from the perspective of binary code representation. 2023 20th Annual International Conference on Privacy. Security and Trust (PST), IEEE, pp 1\u201311"},{"key":"10748_CR8","unstructured":"Chen M, Tworek J, Jun H, Yuan Q, Pinto HPDO, Kaplan J, Edwards H, Burda Y, Joseph N, Brockman G, et\u00a0al (2021) Evaluating large language models trained on code. arXiv:2107.03374"},{"key":"10748_CR9","unstructured":"Curl (2024) https:\/\/github.com\/curl\/curl"},{"issue":"1","key":"10748_CR10","doi-asserted-by":"publisher","first-page":"1418","DOI":"10.1038\/s41467-024-45563-x","volume":"15","author":"J Dagdelen","year":"2024","unstructured":"Dagdelen J, Dunn A, Lee S, Walker N, Rosen AS, Ceder G, Persson KA, Jain A (2024) Structured information extraction from scientific text with large language models. Nat Commun 15(1):1418","journal-title":"Nat Commun"},{"key":"10748_CR11","doi-asserted-by":"crossref","unstructured":"Dai D, Sun Y, Dong L, Hao Y, Ma S, Sui Z, Wei F (2022) Why can gpt learn in-context? language models implicitly perform gradient descent as meta-optimizers. arXiv preprint arXiv:2212.10559","DOI":"10.18653\/v1\/2023.findings-acl.247"},{"key":"10748_CR12","doi-asserted-by":"crossref","unstructured":"David Y, Alon U, Yahav E (2020a) Neural reverse engineering of stripped binaries using augmented control flow graphs. Proc ACM Program Languages 4(OOPSLA):1\u201328","DOI":"10.1145\/3428293"},{"key":"10748_CR13","doi-asserted-by":"crossref","unstructured":"David Y, Alon U, Yahav E (2020b) Neural reverse engineering of stripped binaries using augmented control flow graphs. Proc ACM Program Languages 4(OOPSLA):1\u201328","DOI":"10.1145\/3428293"},{"key":"10748_CR14","unstructured":"DeepSpeed (2024) https:\/\/www.deepspeed.ai\/"},{"key":"10748_CR15","doi-asserted-by":"crossref","unstructured":"Feng Z, Guo D, Tang D, Duan N, Feng X, Gong M, Shou L, Qin B, Liu T, Jiang D, et\u00a0al (2020) Codebert: A pre-trained model for programming and natural languages.arXiv:2002.08155","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"10748_CR16","unstructured":"FFmpeg (2024) https:\/\/github.com\/FFmpeg\/FFmpeg"},{"key":"10748_CR17","unstructured":"Fried D, Aghajanyan A, Lin J, Wang S, Wallace E, Shi F, Zhong R, Yih Wt, Zettlemoyer L, Lewis M (2022) Incoder: a generative model for code infilling and synthesis. arXiv:2204.05999"},{"key":"10748_CR18","doi-asserted-by":"crossref","unstructured":"Gao H, Cheng S, Xue Y, Zhang W (2021) A lightweight framework for function name reassignment based on large-scale stripped binaries. In: Proceedings of the 30th ACM SIGSOFT international symposium on software testing and analysis, pp 607\u2013619","DOI":"10.1145\/3460319.3464804"},{"key":"10748_CR19","volume-title":"An investigation of procedure and variable names as beacons during program comprehension","author":"EM Gellenbeck","year":"1991","unstructured":"Gellenbeck EM, Cook CR (1991) An investigation of procedure and variable names as beacons during program comprehension. Tech. rep, USA"},{"key":"10748_CR20","unstructured":"Giffin JT, Jha S, Miller BP (2004) Efficient context-sensitive intrusion detection. In: Network and distributed system security symposium"},{"key":"10748_CR21","unstructured":"Guo D, Zhu Q, Yang D, Xie Z, Dong K, Zhang W, Chen G, Bi X, Wu Y, Li Y, et\u00a0al (2024) Deepseek-coder: When the large language model meets programming\u2013the rise of code intelligence. arXiv:2401.14196"},{"key":"10748_CR22","doi-asserted-by":"crossref","unstructured":"He J, Ivanov P, Tsankov P, Raychev V, Vechev M (2018) Debin: Predicting debug information in stripped binaries. In: Proceedings of the 2018 ACM SIGSAC conference on computer and communications security, pp 1667\u20131680","DOI":"10.1145\/3243734.3243866"},{"key":"10748_CR23","unstructured":"Hex-RaysSA (2024) \"ida pro\". https:\/\/www.hex-rays.com\/products\/ ida"},{"issue":"8","key":"10748_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3695988","volume":"33","author":"X Hou","year":"2024","unstructured":"Hou X, Zhao Y, Liu Y, Yang Z, Wang K, Li L, Luo X, Lo D, Grundy J, Wang H (2024) Large language models for software engineering: a systematic literature review. ACM Trans Softw Eng Method 33(8):1\u201379","journal-title":"ACM Trans Softw Eng Method"},{"issue":"2","key":"10748_CR25","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, Wang L, Chen W et al (2022) Lora: low-rank adaptation of large language models. ICLR 1(2):3","journal-title":"ICLR"},{"key":"10748_CR26","unstructured":"HuggingFace (2024) https:\/\/huggingface.co\/"},{"key":"10748_CR27","unstructured":"Husain H, Wu HH, Gazit T, Allamanis M, Brockschmidt M (2019) Codesearchnet challenge: evaluating the state of semantic code search. arXiv:1909.09436"},{"key":"10748_CR28","unstructured":"ImageMagick (2024) https:\/\/github.com\/ImageMagick\/ImageMagick"},{"key":"10748_CR29","unstructured":"International IU (2010) Dwarf debugging information format version 4. https:\/\/dwarfstd.org\/doc\/DWARF4.pdf"},{"key":"10748_CR30","doi-asserted-by":"crossref","unstructured":"Jain H, Prabhu Y, Varma M (2016) Extreme multi-label loss functions for recommendation, tagging, ranking & other missing label applications. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp 935\u2013944","DOI":"10.1145\/2939672.2939756"},{"key":"10748_CR31","unstructured":"Jiang AQ, Sablayrolles A, Roux A, Mensch A, Savary B, Bamford C, Chaplot DS, Casas Ddl, Hanna EB, Bressand F, et\u00a0al (2024) Mixtral of experts. arXiv:2401.04088"},{"key":"10748_CR32","doi-asserted-by":"crossref","unstructured":"Jin X, Pei K, Won JY, Lin Z (2022) Symlm: predicting function names in stripped binaries via context-sensitive execution-aware code embeddings. In: Proceedings of the 2022 ACM SIGSAC conference on computer and communications security, pp 1631\u20131645","DOI":"10.1145\/3548606.3560612"},{"key":"10748_CR33","doi-asserted-by":"crossref","unstructured":"Junod P, Rinaldini J, Wehrli J, Michielin J (2015) Obfuscator-llvm\u2013software protection for the masses. In: 2015 IEEE\/ACM 1st international workshop on software protection, IEEE, pp 3\u20139","DOI":"10.1109\/SPRO.2015.10"},{"issue":"4","key":"10748_CR34","doi-asserted-by":"publisher","first-page":"1661","DOI":"10.1109\/TSE.2022.3187689","volume":"49","author":"D Kim","year":"2022","unstructured":"Kim D, Kim E, Cha SK, Son S, Kim Y (2022) Revisiting binary code similarity analysis using interpretable feature engineering and lessons learned. IEEE Trans Software Eng 49(4):1661\u20131682","journal-title":"IEEE Trans Software Eng"},{"key":"10748_CR35","doi-asserted-by":"crossref","unstructured":"Kong A, Zhao S, Chen H, Li Q, Qin Y, Sun R, Zhou X, Wang E, Dong X (2023) Better zero-shot reasoning with role-play prompting. arXiv:2308.07702","DOI":"10.18653\/v1\/2024.naacl-long.228"},{"key":"10748_CR36","doi-asserted-by":"crossref","unstructured":"Kudo T (2018) Subword regularization: improving neural network translation models with multiple subword candidates. In: Proceedings of the 56th annual meeting of the association for computational linguistics (Volume 1: Long Papers), pp 66\u201375","DOI":"10.18653\/v1\/P18-1007"},{"key":"10748_CR37","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/s10590-009-9059-4","volume":"23","author":"A Lavie","year":"2009","unstructured":"Lavie A, Denkowski MJ (2009) The meteor metric for automatic evaluation of machine translation. Mach Transl 23:105\u2013115","journal-title":"Mach Transl"},{"key":"10748_CR38","doi-asserted-by":"crossref","unstructured":"Li X, Qu Y, Yin H (2021) Palmtree: learning an assembly language model for instruction embedding. In: Proceedings of the 2021 ACM SIGSAC conference on computer and communications security, pp 3236\u20133251","DOI":"10.1145\/3460120.3484587"},{"key":"10748_CR39","doi-asserted-by":"crossref","unstructured":"Li Z, Guo S, Zhang L, Li H, Yang Z, Ning Q, Ma Q (2025) Cross domain few-shot line-level defect prediction in open software development via meta learning. IEEE Trans Consumer Electron","DOI":"10.1109\/TCE.2025.3572334"},{"key":"10748_CR40","unstructured":"Libexpat (2024) https:\/\/github.com\/libexpat\/libexpat"},{"key":"10748_CR41","unstructured":"Libvips (2024) https:\/\/github.com\/libvips\/libvips"},{"key":"10748_CR42","unstructured":"Lin CY (2004) Rouge: a package for automatic evaluation of summaries. In: Text summarization branches out, pp 74\u201381"},{"key":"10748_CR43","unstructured":"Llama2c (2024) https:\/\/github.com\/karpathy\/llama2.c"},{"key":"10748_CR44","doi-asserted-by":"crossref","unstructured":"Lu H, Peng H, Nan G, Cui J, Wang C, Jin W, Wang S, Pan S, Tao X (2024) Malsight: exploring malicious source code and benign pseudocode for iterative binary malware summarization. arXiv:2406.18379","DOI":"10.1109\/TIFS.2025.3583552"},{"key":"10748_CR45","unstructured":"Luo Z, Xu C, Zhao P, Sun Q, Geng X, Hu W, Tao C, Ma J, Lin Q, Jiang D (2023) Wizardcoder: empowering code large language models with evol-instruct. arXiv:2306.08568"},{"key":"10748_CR46","doi-asserted-by":"crossref","unstructured":"Maletic JI, Collard ML (2015) Exploration, analysis, and manipulation of source code using srcml. In: 2015 IEEE\/ACM 37th IEEE International Conference on Software Engineering, IEEE, vol\u00a02, pp 951\u2013952","DOI":"10.1109\/ICSE.2015.302"},{"key":"10748_CR47","unstructured":"Masscan (2024) https:\/\/github.com\/robertdavidgraham\/masscan"},{"key":"10748_CR48","first-page":"6294058","volume":"1","author":"MR Naeem","year":"2022","unstructured":"Naeem MR, Amin R, Alshamrani SS, Alshehri A (2022) Digital forensics for malware classification: an approach for binary code to pixel vector transition. Comput Intell Neurosci 1:6294058","journal-title":"Comput Intell Neurosci"},{"key":"10748_CR49","unstructured":"NationalSecurityAgency (2024) ghidra. https:\/\/github.com\/NationalSecurityAgency\/ghidra"},{"key":"10748_CR50","unstructured":"Nijkamp E, Hayashi H, Xiong C, Savarese S, Zhou Y (2023) Codegen2: lessons for training llms on programming and natural languages. arXiv:2305.02309"},{"key":"10748_CR51","unstructured":"OpenSSL (2024) https:\/\/github.com\/openssl\/openssl"},{"key":"10748_CR52","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang L, Wu J, Jiang X, Almeida D, Wainwright C, Mishkin P, Zhang C, Agarwal S, Slama K, Ray A et al (2022) Training language models to follow instructions with human feedback. Adv Neural Inf Process Syst 35:27730\u201327744","journal-title":"Adv Neural Inf Process Syst"},{"key":"10748_CR53","doi-asserted-by":"crossref","unstructured":"Papineni K, Roukos S, Ward T, Zhu WJ (2002) Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the association for computational linguistics, pp 311\u2013318","DOI":"10.3115\/1073083.1073135"},{"key":"10748_CR54","doi-asserted-by":"crossref","unstructured":"Patrick-Evans J, Dannehl M, Kinder J (2023) Xfl: naming functions in binaries with extreme multi-label learning. In: 2023 IEEE symposium on Security and Privacy (SP), IEEE, pp 2375\u20132390","DOI":"10.1109\/SP46215.2023.10179439"},{"key":"10748_CR55","unstructured":"Pei K, Xuan Z, Yang J, Jana S, Ray B (2020) Trex: learning execution semantics from micro-traces for binary similarity. arXiv:2012.08680"},{"key":"10748_CR56","unstructured":"PyTorch (2024) https:\/\/pytorch.org\/"},{"key":"10748_CR57","unstructured":"Redis (2024) https:\/\/github.com\/redis\/redis"},{"key":"10748_CR58","unstructured":"Roziere B, Gehring J, Gloeckle F, Sootla S, Gat I, Tan XE, Adi Y, Liu J, Sauvestre R, Remez T, et al (2023) Code llama: open foundation models for code. arXiv:2308.12950"},{"key":"10748_CR59","doi-asserted-by":"crossref","unstructured":"Sha Z, Wang H, Gao Z, Shu H, Zhang B, Wang Z, Zhang C (2024) llasm: naming functions in binaries by fusing encoder-only and decoder-only llms. ACM Trans Softw Eng Method","DOI":"10.1145\/3702988"},{"key":"10748_CR60","doi-asserted-by":"crossref","unstructured":"Shang X, Cheng S, Chen G, Zhang Y, Hu L, Yu X, Li G, Zhang W, Yu N (2024) How far have we gone in binary code understanding using large language models. In: 2024 IEEE International Conference on Software Maintenance and Evolution (ICSME), IEEE, pp 1\u201312","DOI":"10.1109\/ICSME58944.2024.00012"},{"key":"10748_CR61","doi-asserted-by":"crossref","unstructured":"Song Z, Chen J, Zhang K (2024) Bin2summary: beyond function name prediction in stripped binaries with functionality-specific code embeddings. Proc ACM Softw Eng 1(FSE):47\u201369","DOI":"10.1145\/3643729"},{"key":"10748_CR62","doi-asserted-by":"crossref","unstructured":"Sridhara G, Hill E, Muppaneni D, Pollock L, Vijay-Shanker K (2010) Towards automatically generating summary comments for java methods. In: Proceedings of the 25th IEEE\/ACM international conference on Automated software engineering, pp 43\u201352","DOI":"10.1145\/1858996.1859006"},{"key":"10748_CR63","doi-asserted-by":"crossref","unstructured":"Tan Z, Li D, Wang S, Beigi A, Jiang B, Bhattacharjee A, Karami M, Li J, Cheng L, Liu H (2024) Large language models for data annotation and synthesis: a survey. In: Proceedings of the 2024 conference on empirical methods in natural language processing, pp 930\u2013957","DOI":"10.18653\/v1\/2024.emnlp-main.54"},{"key":"10748_CR64","unstructured":"Touvron H, Lavril T, Izacard G, Martinet X, Lachaux MA, Lacroix T, Rozi\u00e8re B, Goyal N, Hambro E, Azhar F, et\u00a0al (2023a) Llama: open and efficient foundation language models. arXiv:2302.13971"},{"key":"10748_CR65","unstructured":"Touvron H, Martin L, Stone K, Albert P, Almahairi A, Babaei Y, Bashlykov N, Batra S, Bhargava P, Bhosale S, et\u00a0al. (2023b) Llama 2: open foundation and fine-tuned chat models. arXiv:2307.09288"},{"key":"10748_CR66","unstructured":"Transformers (2024) https:\/\/huggingface.co\/"},{"key":"10748_CR67","unstructured":"Ultrajson (2024) https:\/\/github.com\/ultrajson\/ultrajson"},{"key":"10748_CR68","unstructured":"Vector35 (2024) binary ninja. https:\/\/binary.ninja\/"},{"key":"10748_CR69","doi-asserted-by":"crossref","unstructured":"Wang H, Qu W, Katz G, Zhu W, Gao Z, Qiu H, Zhuge J, Zhang C (2022) Jtrans: jump-aware transformer for binary code similarity detection. In: Proceedings of the 31st ACM SIGSOFT international symposium on software testing and analysis, pp 1\u201313","DOI":"10.1145\/3533767.3534367"},{"key":"10748_CR70","doi-asserted-by":"crossref","unstructured":"Wang Y, Wang W, Joty S, Hoi SC (2021) Codet5: identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. arXiv:2109.00859","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"10748_CR71","doi-asserted-by":"crossref","unstructured":"Wang Y, Le H, Gotmare A, Bui N, Li J, Hoi S (2023) Codet5+: Open code large language models for code understanding and generation. In: Proceedings of the 2023 conference on empirical methods in natural language processing, pp 1069\u20131088","DOI":"10.18653\/v1\/2023.emnlp-main.68"},{"key":"10748_CR72","unstructured":"Whispercpp (2024) https:\/\/github.com\/ggerganov\/whisper.cpp"},{"key":"10748_CR73","doi-asserted-by":"crossref","unstructured":"Wu Y, Jiang N, Pham HV, Lutellier T, Davis J, Tan L, Babkin P, Shah S (2023) How effective are neural networks for fixing security vulnerabilities. In: Proceedings of the 32nd ACM SIGSOFT international symposium on software testing and analysis, pp 1282\u20131294","DOI":"10.1145\/3597926.3598135"},{"key":"10748_CR74","doi-asserted-by":"crossref","unstructured":"Xiong J, Chen G, Chen K, Gao H, Cheng S, Zhang W (2023) Hext5: unified pre-training for stripped binary code information inference. In: 2023 38th IEEE\/ACM international conference on Automated Software Engineering (ASE), IEEE, pp 774\u2013786","DOI":"10.1109\/ASE56229.2023.00099"},{"key":"10748_CR75","doi-asserted-by":"crossref","unstructured":"Xu FF, Alon U, Neubig G, Hellendoorn VJ (2022) A systematic evaluation of large language models of code. In: Proceedings of the 6th ACM SIGPLAN international symposium on machine programming, pp 1\u201310","DOI":"10.1145\/3520312.3534862"},{"key":"10748_CR76","doi-asserted-by":"crossref","unstructured":"Xu Z, Chen B, Chandramohan M, Liu Y, Song F (2017) Spain: security patch analysis for binaries towards understanding the pain and pills. In: 2017 IEEE\/ACM 39th International Conference on Software Engineering (ICSE), IEEE, pp 462\u2013472","DOI":"10.1109\/ICSE.2017.49"},{"key":"10748_CR77","doi-asserted-by":"crossref","unstructured":"Ye T, Wu L, Ma T, Zhang X, Du Y, Liu P, Ji S, Wang W (2023) Cp-bcs: binary code summarization guided by control flow graph and pseudo code. arXiv:2310.16853","DOI":"10.18653\/v1\/2023.emnlp-main.911"},{"issue":"2","key":"10748_CR78","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1145\/210134.210179","volume":"4","author":"AM Zaremski","year":"1995","unstructured":"Zaremski AM, Wing JM (1995) Signature matching: a tool for using software libraries. ACM Transactions on Software Engineering and Methodology (TOSEM) 4(2):146\u2013170","journal-title":"ACM Transactions on Software Engineering and Methodology (TOSEM)"},{"key":"10748_CR79","unstructured":"Zeng A, Liu X, Du Z, Wang Z, Lai H, Ding M, Yang Z, Xu Y, Zheng W, Xia X, et\u00a0al. (2022) Glm-130b: an open bilingual pre-trained model. arXiv:2210.02414"},{"key":"10748_CR80","doi-asserted-by":"crossref","unstructured":"Zhang Y (2022) Leveraging artificial intelligence on binary code comprehension. In: Proceedings of the 37th IEEE\/ACM international conference on automated software engineering, pp 1\u20133","DOI":"10.1145\/3551349.3559564"},{"key":"10748_CR81","unstructured":"Zhang Y, Song W, Ji Z, Meng N, et\u00a0al (2023) How well does llm generate security tests? arXiv:2310.00710"},{"key":"10748_CR82","doi-asserted-by":"crossref","unstructured":"Zhang Z, You W, Tao G, Aafer Y, Liu X, Zhang X (2021) Stochfuzz: sound and cost-effective fuzzing of stripped binaries by incremental and stochastic rewriting. In: 2021 IEEE symposium on Security and Privacy (SP), IEEE, pp 659\u2013676","DOI":"10.1109\/SP40001.2021.00109"},{"key":"10748_CR83","first-page":"46595","volume":"36","author":"L Zheng","year":"2023","unstructured":"Zheng L, Chiang WL, Sheng Y, Zhuang S, Wu Z, Zhuang Y, Lin Z, Li Z, Li D, Xing E et al (2023) Judging llm-as-a-judge with mt-bench and chatbot arena. Adv Neural Inf Process Syst 36:46595\u201346623","journal-title":"Adv Neural Inf Process Syst"},{"key":"10748_CR84","doi-asserted-by":"crossref","unstructured":"Zheng Y, Zhang R, Zhang J, Ye Y, Luo Z, Feng Z, Ma Y (2024) Llamafactory: unified efficient fine-tuning of 100+ language models. arXiv:2403.13372","DOI":"10.18653\/v1\/2024.acl-demos.38"},{"key":"10748_CR85","doi-asserted-by":"crossref","unstructured":"Zhu K, Tian Z, Wang S, Chen W, Dong Z, Leng M, Mao X (2025) Misum: multi-modality heterogeneous code graph learning for multi-intent binary code summarization. In: Companion proceedings of the 33nd ACM international conference on the foundations of software engineering","DOI":"10.1145\/3715780"},{"key":"10748_CR86","unstructured":"zstd (2024) https:\/\/github.com\/facebook\/zstd"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-025-10748-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-025-10748-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-025-10748-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T11:26:12Z","timestamp":1770809172000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-025-10748-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,13]]},"references-count":86,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10748"],"URL":"https:\/\/doi.org\/10.1007\/s10664-025-10748-5","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,13]]},"assertion":[{"value":"2 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study adheres to established ethical principles for research involving human participants.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"Informed consent was obtained from all individual participants included in the study.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed Consent"}},{"value":"The authors declared that they have no conflict of interest.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Clinical Trial Number"}}],"article-number":"14"}}