{"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/extracting-prompts-by-inverting-llm-outputs","title":"Extracting Prompts by Inverting LLM Outputs","arxiv_id":"2405.15012","date":"2024-05-23","proceeding":null,"authors":["Collin Zhang","John X. Morris","Vitaly Shmatikov"],"abstract":"We consider the problem of language model inversion: given outputs of a language model, we seek to extract the prompt that generated these outputs. We develop a new black-box method, output2prompt, that learns to extract prompts without access to the model's logits and without adversarial or jailbreaking queries. In contrast to previous work, output2prompt only needs outputs of normal user queries. To improve memory efficiency, output2prompt employs a new sparse encoding techique. We measure the efficacy of output2prompt on a variety of user and system prompts and demonstrate zero-shot transferability across different LLMs.","url_abs":"https://arxiv.org/abs/2405.15012v2","url_pdf":"https://arxiv.org/pdf/2405.15012v2.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":"abstracts"},"code_links":[{"paper_slug":"extracting-prompts-by-inverting-llm-outputs","repo_url":"https://github.com/collinzrj/output2prompt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.15012","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15012"}},"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/collinzrj/output2prompt","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":0,"samples":[{"code_sha256_prefix":"1c13cb7bbcec5b37","entry":"args_from_config","repo":"collinzrj/output2prompt","repo_kind":"official","path":"vec2text/analyze_utils.py","file_url":"https://github.com/collinzrj/output2prompt/blob/HEAD/vec2text/analyze_utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1c13cb7bbcec5b37"}},{"code_sha256_prefix":"d1d22f33b80e6898","entry":"create_omi_ex","repo":"collinzrj/output2prompt","repo_kind":"official","path":"vec2text/data_helpers.py","file_url":"https://github.com/collinzrj/output2prompt/blob/HEAD/vec2text/data_helpers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d1d22f33b80e6898"}},{"code_sha256_prefix":"041dd4c56f3a3a34","entry":"create_ompi_ex","repo":"collinzrj/output2prompt","repo_kind":"official","path":"vec2text/data_helpers.py","file_url":"https://github.com/collinzrj/output2prompt/blob/HEAD/vec2text/data_helpers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"041dd4c56f3a3a34"}},{"code_sha256_prefix":"9ce3fa900ab6c176","entry":"load_results_from_folder","repo":"collinzrj/output2prompt","repo_kind":"official","path":"vec2text/analyze_utils.py","file_url":"https://github.com/collinzrj/output2prompt/blob/HEAD/vec2text/analyze_utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9ce3fa900ab6c176"}},{"code_sha256_prefix":"025c70307306970e","entry":"retain_dataset_columns","repo":"collinzrj/output2prompt","repo_kind":"official","path":"vec2text/data_helpers.py","file_url":"https://github.com/collinzrj/output2prompt/blob/HEAD/vec2text/data_helpers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"025c70307306970e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}