Large language model (LLM) for software security: Code analysis, malware analysis, reverse engineering
Open accessAbstract
Large Language Models (LLMs) have recently emerged as powerful tools in cybersecurity, offering advanced capabilities in malware detection, generation, and real-time monitoring. Numerous studies have explored their application in cybersecurity, demonstrating their effectiveness in identifying novel malware variants, analyzing malicious code structures, and enhancing automated threat analysis. Several transformer-based architectures and LLM-driven models have been proposed to improve malware analysis, leveraging semantic and structural insights to recognize malicious intent more accurately. This study presents a comprehensive review of LLM-based approaches in malware code analysis, summarizing recent advancements, trends, and methodologies. We examine notable scholarly works to map the research landscape, identify key challenges, and highlight emerging innovations in LLM-driven cybersecurity. Additionally, we emphasize the role of static analysis in malware detection, introduce notable datasets and specialized LLM models, and discuss essential datasets supporting automated malware research. This study serves as a valuable resource for researchers and cybersecurity professionals, offering insights into LLM-powered malware detection and defense strategies while outlining future directions for strengthening cybersecurity resilience.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
LLMs have already been examined for cyber threat detection, threat-intelligence analysis, malware investigation support, and higher-level security reasoning, no longer confined to traditional classification pipelines or rule-based systems.
“According to recent studies, LLMs have already been examined for cyber threat detection, threat-intelligence analysis, malware investigation support, and higher-level security reasoning, no longer confined to traditional classification pipelines or rule-based systems [12], [13].”
From The Evolution of Agentic AI in Cybersecurity: From Single LLM Reasoners to Multi-Agent Systems and Autonomous Pipelines (2026) · cites this paper as [13]
Cites
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561 · see citing works
Survey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025 · see citing works
Continual lifelong learning with neural networks: A review
Parisi, G. I., Kemker, R., Part, J. L., Kanan, C., & Wermter, S. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.01.012 · Cited by 3,117 · see citing works
A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly
Yao, Y., Duan, J., Xu, K., Cai, Y., Sun, Z., & Zhang, Y. (2024) · High-Confidence Computing · doi:10.1016/j.hcc.2024.100211 · Cited by 1,083 · see citing works
Large Language Models for Software Engineering: A Systematic Literature Review
Hou, X., Zhao, Y., Liu, Y., Yang, Z., Wang, K., Li, L., Luo, X., Lo, D., Grundy, J., & Wang, H. (2024) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3695988 · Cited by 1,029 · see citing works
A survey on automated dynamic malware-analysis techniques and tools
Egele, M., Scholte, T., Kirda, E., & Kruegel, C. (2008) · ACM Computing Surveys · doi:10.1145/2089125.2089126 · Cited by 879 · see citing works
Allix, K., Bissyandé, T. F., Klein, J., & Traon, Y. L. (2016) · International Conference on Mining Software Repositories (MSR) · doi:10.1145/2901739.2903508 · Cited by 836 · see citing works
From ChatGPT to ThreatGPT: Impact of Generative AI in Cybersecurity and Privacy
Gupta, M., Akiri, C., Aryal, K., Parker, E., & Praharaj, L. (2023) · IEEE Access · doi:10.1109/access.2023.3300381 · Cited by 714 · see citing works
A survey on technical threat intelligence in the age of sophisticated cyber attacks
Tounsi, W., & Rais, H. (2018) · Computers & Security · doi:10.1016/j.cose.2017.09.001 · Cited by 474 · see citing works
CodeT5+: Open Code Large Language Models for Code Understanding and Generation
Wang, Y., Le, H., Gotmare, A., Bui, N., Li, J., & Hoi, S. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.68 · Cited by 459 · see citing works
CodeT5+: Open Code Large Language Models for Code Understanding and Generation
Wang, Y., Le, H., Gotmare, A. D., Bui, N. D. Q., Li, J., & Hoi, S. C. H. (2023) · arXiv · doi:10.48550/arxiv.2305.07922 · Cited by 459
Dynamic Malware Analysis in the Modern Era—A State of the Art Survey
Or-Meir, O., Nissim, N., Elovici, Y., & Rokach, L. (2019) · ACM Computing Surveys · doi:10.1145/3329786 · Cited by 389 · see citing works
Onwuzurike, L., Mariconti, E., Andriotis, P., Cristofaro, E. D., Ross, G. J., & Stringhini, G. (2019) · ACM Transactions on Privacy and Security · doi:10.1145/3313391 · Cited by 337 · see citing works
Cyber Threat Intelligence Mining for Proactive Cybersecurity Defense: A Survey and New Perspectives
Sun, N., Ding, M., Jiang, J., Xu, W., Mo, X., Tai, Y., & Zhang, J. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3273282 · Cited by 335 · see citing works
Multi-step Jailbreaking Privacy Attacks on ChatGPT
Li, H., Guo, D., Fan, W., Xu, M., Huang, J., Meng, F., & Song, Y. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.272 · Cited by 269 · see citing works
A Survey of Knowledge Enhanced Pre-Trained Language Models
Hu, L., Liu, Z., Zhao, Z., Hou, L., Nie, L., & Li, J. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3310002 · Cited by 224 · see citing works
Large Language Models for Cyber Security: A Systematic Literature Review
Xu, H., Wang, S., Li, N., Wang, K., Zhao, Y., Chen, K., Yu, T., Liu, Y., & Wang, H. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3769676 · Cited by 189 · see citing works
LLM-TIKG: Threat intelligence knowledge graph construction utilizing large language model
Hu, Y., Zou, F., Han, J., Sun, X., & Wang, Y. (2024) · Computers & Security · doi:10.1016/j.cose.2024.103999 · Cited by 154 · see citing works
Zhang, J., Qin, Z., Yin, H., Ou, L., & Zhang, K. (2019) · Computers & Security · doi:10.1016/j.cose.2019.04.005 · Cited by 104 · see citing works
Singh, J., & Singh, J. (2020) · Information and Software Technology · doi:10.1016/j.infsof.2020.106273 · Cited by 96 · see citing works
Finetuning Large Language Models for Vulnerability Detection
Shestov, A., Levichev, R., Mussabayev, R., Maslov, E., Zadorozhny, P., Cheshkov, A., Mussabayev, R., Toleu, A., Tolegen, G., & Krassovitskiy, A. (2025) · IEEE Access · doi:10.1109/access.2025.3546700 · Cited by 93 · see citing works
Why an Android App Is Classified as Malware
Wu, B., Chen, S., Gao, C., Fan, L., Liu, Y., Wen, W., & Lyu, M. R.-T. (2021) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3423096 · Cited by 77 · see citing works
Decoding the Threat Landscape : ChatGPT, FraudGPT, and WormGPT in Social Engineering Attacks
Falade, P. V. (2023) · International Journal of Scientific Research in Computer Science Engineering and Information Technology · doi:10.32628/cseit2390533 · Cited by 73 · see citing works
LLM4Decompile: Decompiling Binary Code with Large Language Models
Tan, H., Luo, Q., Li, J., & Zhang, Y. (2024) · Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2024.emnlp-main.203 · Cited by 67 · see citing works
AppPoet: Large language model based android malware detection via multi-view prompt engineering
Zhao, W., Wu, J., & Meng, Z. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125546 · Cited by 65 · see citing works
Static Malware Detection Using Stacked BiLSTM and GPT-2
Demirci, D., Sahin, N., Sirlancis, M., & Acartürk, C. (2022) · IEEE Access · doi:10.1109/access.2022.3179384 · Cited by 65 · see citing works
BERT-Based Approaches to Identifying Malicious URLs
Su, M., & Su, K.-L. (2023) · Sensors · doi:10.3390/s23208499 · Cited by 65 · see citing works
On Transferability of Bias Mitigation Effects in Language Model Fine-Tuning
Jin, X., Barbieri, F., Kennedy, B., Davani, A. M., Neves, L., & Ren, X. (2021) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2021.naacl-main.296 · Cited by 51 · see citing works
ChatPhishDetector: Detecting Phishing Sites Using Large Language Models
Koide, T., Nakano, H., & Chiba, D. (2024) · IEEE Access · doi:10.1109/access.2024.3483905 · Cited by 49 · see citing works
Efficient dynamic malware analysis using virtual time control mechanics
Lin, C.-H., Pao, H.-K., & Liao, J. (2017) · Computers & Security · doi:10.1016/j.cose.2017.11.010 · Cited by 49 · see citing works
An Empirical Study of the Code Generation of Safety-Critical Software Using LLMs
Liu, M., Wang, J., Lin, T., Ma, Q., Fang, Z., & Wu, Y. (2024) · Applied Sciences · doi:10.3390/app14031046 · Cited by 47 · see citing works
Madan, S., Sofat, S., & Bansal, D. (2022) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2021.12.016 · Cited by 45 · see citing works
Muralidharan, T., Cohen, A., Gerson, N., & Nissim, N. (2022) · ACM Computing Surveys · doi:10.1145/3530810 · Cited by 42 · see citing works
Ding, W., Abdel‐Basset, M., Ali, A. M., & Moustafa, N. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.112663 · Cited by 41 · see citing works
A New Approach to Web Application Security: Utilizing GPT Language Models for Source Code Inspection
Szabó, Z., & Bilicki, V. (2023) · Future Internet · doi:10.3390/fi15100326 · Cited by 40 · see citing works
GPThreats-3: Is Automatic Malware Generation a Threat?
Botacin, M. F. (2023) · IEEE Security and Privacy Workshops (SPW) · doi:10.1109/spw59333.2023.00027 · Cited by 39 · see citing works
Exploring the Dark Side of AI: Advanced Phishing Attack Design and Deployment Using ChatGPT
Begou, N., Vinoy, J., Duda, A., & Korczyński, M. (2023) · IEEE Conference on Communications and Network Security · doi:10.1109/cns59707.2023.10288940 · Cited by 39 · see citing works
LAMD: Context-Driven Android Malware Detection and Classification with LLMs
Qian, X., Zheng, X., He, Y., Yang, S., & Cavallaro, L. (2025) · IEEE Security and Privacy Workshops (SPW) · doi:10.1109/spw67851.2025.00017 · Cited by 39 · see citing works
MOTIF: A Malware Reference Dataset with Ground Truth Family Labels
Joyce, R. J., Amlani, D., Nicholas, C., & Raff, E. (2022) · Computers & Security · doi:10.1016/j.cose.2022.102921 · Cited by 38 · see citing works
LlamaRestTest: Effective REST API Testing with Small Language Models
Kim, M., Sinha, S., & Orso, A. (2025) · Proceedings of the ACM on software engineering. · doi:10.1145/3715737 · Cited by 33 · see citing works
Sequential opcode embedding-based malware detection method
Kakisim, A. G., Gulmez, S., & Soğukpınar, İ. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.107703 · Cited by 32 · see citing works
DeTiME: Diffusion-Enhanced Topic Modeling using Encoder-decoder based LLM
Xu, W., Hu, W., Wu, F., & Sengamedu, S. H. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.606 · Cited by 24 · see citing works
Wang, L., Wang, H., He, R., Tao, R., Meng, G., Luo, X., & Liu, X. (2022) · Proceedings of the ACM on Measurement and Analysis of Computing Systems · doi:10.1145/3530906 · Cited by 23 · see citing works
Evaluating Large Language Models in Detecting Test Smells
dos Santos, K. L., Gheyi, R., Soares, E., Ribeiro, M., & Machado, I. (2024) · Simpósio Brasileiro de Engenharia de Software (SBES) · doi:10.5753/sbes.2024.3642 · Cited by 17 · see citing works
Mohseni, S., Mohammadi, S., Tilwani, D., Saxena, Y., Ndawula, G. K., Vema, S., Raff, E., & Gaur, M. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i23.34672 · Cited by 17 · see citing works
Exploring Large Language Models for Semantic Analysis and Categorization of Android Malware
Walton, B. J., Khatun, M. E., Ghawaly, J., & Ali-Gombe, A. (2024) · Annual Computer Security Applications Conference Workshops (ACSAC Workshops) · doi:10.1109/acsacw65225.2024.00035 · Cited by 13 · see citing works
Lu, H., Peng, H., Nan, G., Cui, J., Wang, C., Jin, W., Wang, S., Pan, S., & Tao, X. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3583552 · Cited by 12 · see citing works
ASDroid: Resisting Evolving Android Malware With API Clusters Derived From Source Code
Hu, Q., Wang, W., Song, H. T., Guo, S., Zhang, J., & Zhang, S. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3536280 · Cited by 12 · see citing works
Feasibility Study for Supporting Static Malware Analysis Using LLM
Fujii, S., & Yamagishi, R. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-82362-6_1 · Cited by 12 · see citing works
Bao, H., Li, W., Chen, H., Miao, H., Wang, Q., Tang, Z., Liu, F., & Wang, W. (2024) · Computers & Security · doi:10.1016/j.cose.2024.103943 · Cited by 11 · see citing works
The double-edged sword of generative AI: surpassing an expert or a deceptive “false friend”?
Altorfer, F. C. S., Kelly, M., Avrumova, F., Rohatgi, V., Zhu, J., Bono, C. M., & Lebl, D. R. (2025) · The Spine Journal · doi:10.1016/j.spinee.2025.02.010 · Cited by 11 · see citing works
CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking
Su, Z., Xu, X., Huang, Z., Zhang, Z., Ye, Y., Huang, J., & Zhang, X. (2024) · Proceedings of the ACM on software engineering. · doi:10.1145/3643752 · Cited by 4 · see citing works
MarvelHideDroid: Reliable on-the-fly data anonymization based on Android virtualization
Pagano, F., Verderame, L., Russo, E., & Merlo, A. (2024) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2024.109882 · Cited by 2 · see citing works
Detection of malicious PE files using synthesized DNA artifacts
Ngwobia, S. C., Ralescu, A., Kapp, D., & Kebede, T. (2023) · Computers & Security · doi:10.1016/j.cose.2023.103457 · Cited by 1 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Tamuka, N., Mathonsi, T. E., Olwal, T. O., Maswikaneng, S. P., Muchenje, T., & Tshilongamulenzhe, T. M. (2026) · Journal of Computer Virology and Hacking Techniques · doi:10.1007/s11416-026-00622-3 · Cited by 6 · see citing works
Vinay, V. (2026) · 2026 IEEE 5th International Conference on AI in Cybersecurity (ICAIC) · doi:10.1109/icaic67076.2026.11395809 · Cited by 15 · see citing works
“According to recent studies, LLMs have already been examined for cyber threat detection, threat-intelligence analysis, malware investigation support, and higher-level security reasoning, no longer confined to traditional classification pipelines or rule-based systems [12], [13].”
Real-Time Multi-Source Threat Intelligence Fusion Using Large Language Models
Siam, A. A., Alazab, M., Obeidat, A., Faruqui, N., & Al-Maadeed, S. A. (2026) · IEEE International Conference on AI in Cybersecurity (ICAIC) · doi:10.1109/icaic67076.2026.11395679 · Cited by 3 · see citing works
ML4SOC: A Comprehensive Review on Machine Learning for Security Operations Centres
Waschke, F., Vaarandi, R., & Guerra-Manzanares, A. (2026) · ACM Computing Surveys · doi:10.1145/3820494 · Cited by 2 · see citing works
Jelodar, H., Meymani, M., Bai, S., Razavi‐Far, R., & Ghorbani, A. A. (2025) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw69685.2025.00152 · Cited by 1 · see citing works
Self-citationHybrid LLM-Vision Pipeline for Detection of Malicious QR Codes in Social Engineering Attacks
Krishna, K. L., Kumar, P. R., Herah, V., Reddy, P. V. V., & Reddy, K. J. S. (2026) · International Conference on Image Processing and Capsule Networks (ICIPCN) · doi:10.1109/icipcn67432.2026.11438814 · Cited by 1 · see citing works
Toward Efficient Deobfuscation via Large Language Models
Choi, B., Jin, H., Lee, D. H., & Choi, W. (2026) · IEEE Access · doi:10.1109/access.2026.3660477
Malware Detection and Analysis Using LLMs: A Review of Emerging Trends and Techniques
Albalooshi, M., Chang, P., Yerima, S. Y., Altamimi, T., AlFalasi, H., & Almarzooqi, A. (2025) · International Conference on Artificial Intelligence, Metaverse and Cybersecurity (ICAMAC) · doi:10.1109/icamac67779.2025.11398140
ROParser: A high-efficient framework for return-oriented programming deobfuscation
Liu, H., Liu, T., Chang, R., Lin, J., Zhou, Z., & Jing, J. (2026) · Computers & Security · doi:10.1016/j.cose.2026.104884
Abeysinghe, A. M. D. D. K., & Wijayanayake, J. I. (2026) · International Conference on Advanced Research in Computing (ICARC) · doi:10.1109/icarc68737.2026.11453544
Differential privacy for data sharing: evolution and full-lifecycle applications in generative AI
Gao, B., Wang, L., Yu, Y., & Yang, A. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112335
Hamedi, P., Jelodar, H., Bai, S., Meymani, M., Razavi‐Far, R., & Ghorbani, A. A. (2026) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai68641.2026.11536494
Self-citationLeveraging LLMs to Support Malware Analysis from Structured and Semantic Binary Data
Hau, N. K., Anh, T. T., Trong, N. T., Hien, D. T. T., Van, T. H., & Duy, P. T. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-0263-8_35
Large Language Model: Future of Healthcare Research With Challenges
Heyat, M. B. B., Rehman, A. U., Zeeshan, H. M., Hayat, M. A. B., Akhtar, F., Sadaf, Ansari, M. A., Wang, L., Lai, D., Prasath, V. B. S., et al. (2026) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.70103
AndroSem: Semantics-Guided, LLM-based Interpretable Static Android Malware Detection
Dai, H., Qu, T. L., Sun, L. G., Jiang, B., Shang, S., & Xu, H. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582639
MOD2SAD: enhancing malicious office document detection through semantic-aware deobfuscation
Leng, T., Liao, T., & Yuan, B. (2026) · Scientific Reports · doi:10.1038/s41598-026-60598-4
Bhattacharya, M., Sarkar, A., Thomas, T., Baksi, R. P., & Penica, M. (2026) · IEEE International Conference on Healthcare Informatics (ICHI) · doi:10.1109/ichi69079.2026.00103
Leveraging Code Slicing for LLMs-Based Malicious NPM Package Detection
Nguyen, D.-K., Ho, G., Pham, Q. N., Anh, T. D.-T., Vu, M.-K., Nguyen, T. C., Tran-Truong, P. T., & Vu, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-35576-8_2
Verma, A. S., Gupta, D. N., Saxena, A., & Thakore, A. (2026) · International Journal of Innovations in Science Engineering and Management. · doi:10.69968/ijisem.2026v5i3426-439
The Imitation Game: Using Large Language Models to Disrupt Chinese Chat-Based Cybercrime
Yao, Y., Wang, B., Duan, J., Xu, K., Guo, C., Sun, Z., & Zhang, Y. (2026) · International Workshop on Quality of Service · doi:10.1109/iwqos70441.2026.11661137
Zhai, C., Zhai, C., Wang, Y., Yuhao, L., & Jin, Z. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7484759
Khoa, N. H., Bao, P. T., & Pham, V.-H. (2026) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2026.104650
A Method for Monitoring Target Events
Manzhai, O., Носов, В., Luchyk, S., & Luchyk, V. (2026) · International Conference on Advanced Computer Information Technologies (ACIT) · doi:10.1109/acit69831.2026.11700127
Mosafer, M., Mahmoudi-Nasr, P., & Yousefpour, R. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7615929
Evaluating LLM-generated malware: an end-to-end framework and measurement study
Saccone, F., Riccio, G., Ianniello, F., Ullah, U., Ciriello, A., Dalia, G., Laudanna, S., Sorbo, A. D., & Visaggio, C. A. (2026) · Journal of Computer Virology and Hacking Techniques · doi:10.1007/s11416-026-00686-1
Malware classification in mobile Android platforms: background, concepts and traditional methods
Ferreira, A. P., Gupta, C., Inácio, P. R. M., & Freire, M. M. (2026) · Cluster Computing · doi:10.1007/s10586-026-06620-w
Вениаминович, Г. П., & Bessmertny, I. (2026) · Scientific and technical journal of information technologies mechanics and optics · doi:10.17586/2226-1494-2026-26-5-1018-1025
- Authors
- Jelodar, H., Bai, S., Hamedi, P., Mohammadian, H., Razavi-Far, R., & Ghorbani, A.
- Affiliations
- University of New Brunswick (CA)
- Corresponding author
- Jelodar, Hamed
- Venue
- Journal of Information Security and Applications
- Publisher
- Elsevier BV
- Published
- 2026-05
- Volume
- 98
- Pages
- 104390
- ISSN
- 2214-2126 (ISSN-L)
- OpenAlex
- W7128505394
- Cited by
- 27
- References
- 53
- Citations by year
- 2026: 25 · 2025: 2
- FWCI
- 96.39
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Journal of Information Security and Applications (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Signal Processing › Advanced Malware Detection Techniques
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Physical Sciences › Computer Science › Artificial Intelligence › Security and Verification in Computing
- Keywords
- large language models, software security, code analysis, malware analysis, reverse engineering
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
