{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/sevenllm-benchmarking-eliciting-and-enhancing","title":"SEvenLLM: Benchmarking, Eliciting, and Enhancing Abilities of Large Language Models in Cyber Threat Intelligence","arxiv_id":"2405.03446","date":"2024-05-06","proceeding":null,"authors":["Hangyuan Ji","Jian Yang","Linzheng Chai","Chaoren Wei","Liqun Yang","Yunlong Duan","Yunli Wang","Tianzhen Sun","Hongcheng Guo","Tongliang Li","Changyu Ren","Zhoujun Li"],"abstract":"To address the increasing complexity and frequency of cybersecurity incidents emphasized by the recent cybersecurity threat reports with over 10 billion instances, cyber threat intelligence (CTI) plays a critical role in the modern cybersecurity landscape by offering the insights required to understand and combat the constantly evolving nature of cyber threats. Inspired by the powerful capability of large language models (LLMs) in handling complex tasks, in this paper, we introduce a framework to benchmark, elicit, and improve cybersecurity incident analysis and response abilities in LLMs for Security Events (SEvenLLM). Specifically, we create a high-quality bilingual instruction corpus by crawling cybersecurity raw text from cybersecurity websites to overcome the lack of effective data for information extraction. Then, we design a pipeline to auto-select tasks from the tasks pool and convert the raw text into supervised corpora comprised of question and response. The instruction dataset SEvenLLM-Instruct is used to train cybersecurity LLMs with the multi-task learning objective (27 well-designed tasks) for augmenting the analysis of cybersecurity events. Extensive experiments in our curated benchmark (SEvenLLM-bench) demonstrate that SEvenLLM performs more sophisticated threat analysis and fortifies defenses against the evolving landscape of cyber threats.","url_abs":"https://arxiv.org/abs/2405.03446v2","url_pdf":"https://arxiv.org/pdf/2405.03446v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"sevenllm-benchmarking-eliciting-and-enhancing","repo_url":"https://github.com/csjianyang/seevenllm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2405.03446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.03446"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/csjianyang/seevenllm","reach":{"status":"ok"}}],"summary":{"ran":9,"unverified":3},"by_repo_kind":{"official":{"samples":12,"ran":9,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":12,"samples":[{"code_sha256_prefix":"532740bbf39ba1c0","entry":"calculate_score","repo":"csjianyang/seevenllm","repo_kind":"official","path":"code/score/f1_rougel/ex-score-en-path.py","file_url":"https://github.com/csjianyang/seevenllm/blob/HEAD/code/score/f1_rougel/ex-score-en-path.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"532740bbf39ba1c0"}},{"code_sha256_prefix":"593741de89b5746c","entry":"calculate_score","repo":"csjianyang/seevenllm","repo_kind":"official","path":"code/score/f1_rougel/gen_score_rougeL-en-path.py","file_url":"https://github.com/csjianyang/seevenllm/blob/HEAD/code/score/f1_rougel/gen_score_rougeL-en-path.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"593741de89b5746c"}},{"code_sha256_prefix":"a4df10df17e829ba","entry":"calculate_total_score","repo":"csjianyang/seevenllm","repo_kind":"official","path":"code/score/get_score_choice.py","file_url":"https://github.com/csjianyang/seevenllm/blob/HEAD/code/score/get_score_choice.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a4df10df17e829ba"}},{"code_sha256_prefix":"f654b3ebda765d65","entry":"calculate_total_score","repo":"csjianyang/seevenllm","repo_kind":"official","path":"code/score/f1_rougel/choice_sorce-path.py","file_url":"https://github.com/csjianyang/seevenllm/blob/HEAD/code/score/f1_rougel/choice_sorce-path.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f654b3ebda765d65"}},{"code_sha256_prefix":"052c653ccc57ee4c","entry":"extract_output_values","repo":"csjianyang/seevenllm","repo_kind":"official","path":"code/score/get_score_choice.py","file_url":"https://github.com/csjianyang/seevenllm/blob/HEAD/code/score/get_score_choice.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"052c653ccc57ee4c"}},{"code_sha256_prefix":"44b5e328d1d81c76","entry":"extract_output_values","repo":"csjianyang/seevenllm","repo_kind":"official","path":"code/score/f1_rougel/choice_sorce-path.py","file_url":"https://github.com/csjianyang/seevenllm/blob/HEAD/code/score/f1_rougel/choice_sorce-path.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"44b5e328d1d81c76"}},{"code_sha256_prefix":"88b7118e546f3127","entry":"extract_values_from_json","repo":"csjianyang/seevenllm","repo_kind":"official","path":"code/score/f1_rougel/ex-score-en-path.py","file_url":"https://github.com/csjianyang/seevenllm/blob/HEAD/code/score/f1_rougel/ex-score-en-path.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"88b7118e546f3127"}},{"code_sha256_prefix":"3b22fd920b5f5f4d","entry":"intersection_count","repo":"csjianyang/seevenllm","repo_kind":"official","path":"code/score/f1_rougel/ex-score-en-path.py","file_url":"https://github.com/csjianyang/seevenllm/blob/HEAD/code/score/f1_rougel/ex-score-en-path.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3b22fd920b5f5f4d"}},{"code_sha256_prefix":"3631326dc4e39fe9","entry":"padding","repo":"csjianyang/seevenllm","repo_kind":"official","path":"infer.py","file_url":"https://github.com/csjianyang/seevenllm/blob/HEAD/infer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3631326dc4e39fe9"}},{"code_sha256_prefix":"9dbdc9e44c4e2256","entry":"preprocess","repo":"csjianyang/seevenllm","repo_kind":"official","path":"infer.py","file_url":"https://github.com/csjianyang/seevenllm/blob/HEAD/infer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9dbdc9e44c4e2256"}},{"code_sha256_prefix":"d250258f240f5f2e","entry":"sequence_gather","repo":"csjianyang/seevenllm","repo_kind":"official","path":"infer.py","file_url":"https://github.com/csjianyang/seevenllm/blob/HEAD/infer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d250258f240f5f2e"}},{"code_sha256_prefix":"7b211652efdbbcd2","entry":"split_sentences","repo":"csjianyang/seevenllm","repo_kind":"official","path":"code/score/f1_rougel/gen_score_rougeL-en-path.py","file_url":"https://github.com/csjianyang/seevenllm/blob/HEAD/code/score/f1_rougel/gen_score_rougeL-en-path.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7b211652efdbbcd2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}