{"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/instructzero-efficient-instruction","title":"InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models","arxiv_id":"2306.03082","date":"2023-06-05","proceeding":null,"authors":["Lichang Chen","Jiuhai Chen","Tom Goldstein","Heng Huang","Tianyi Zhou"],"abstract":"Large language models~(LLMs) are instruction followers, but it can be challenging to find the best instruction for different situations, especially for black-box LLMs on which backpropagation is forbidden. Instead of directly optimizing the discrete instruction, we optimize a low-dimensional soft prompt applied to an open-source LLM to generate the instruction for the black-box LLM. On each iteration of the proposed method, which we call InstructZero, a soft prompt is converted into an instruction using the open-source LLM, which is then submitted to the black-box LLM for zero-shot evaluation, and the performance is sent to Bayesian optimization to produce new soft prompts improving the zero-shot performance. We evaluate InstructZero on different combinations of open-source LLMs and APIs including Vicuna and ChatGPT. Our results show that InstructZero outperforms SOTA auto-instruction methods across a variety of downstream tasks. Our code and data are publicly available at https://github.com/Lichang-Chen/InstructZero.","url_abs":"https://arxiv.org/abs/2306.03082v2","url_pdf":"https://arxiv.org/pdf/2306.03082v2.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":"instructzero-efficient-instruction","repo_url":"https://github.com/lichang-chen/instructzero","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"instructzero-efficient-instruction","repo_url":"https://github.com/ruocwang/mixture-of-prompts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"bayesian-optimization","task_name":"Bayesian Optimization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.03082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.03082"}},"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/lichang-chen/instructzero","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ruocwang/mixture-of-prompts","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"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":2,"samples":[{"code_sha256_prefix":"71e7c70faf29eeee","entry":"get_query","repo":"lichang-chen/instructzero","repo_kind":"official","path":"InstructZero/experiments/automatic_prompt_engineer/generate.py","file_url":"https://github.com/lichang-chen/instructzero/blob/HEAD/InstructZero/experiments/automatic_prompt_engineer/generate.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"71e7c70faf29eeee"}},{"code_sha256_prefix":"3da4ab7760bb2fb6","entry":"generate_prompts","repo":"lichang-chen/instructzero","repo_kind":"official","path":"InstructZero/experiments/automatic_prompt_engineer/generate.py","file_url":"https://github.com/lichang-chen/instructzero/blob/HEAD/InstructZero/experiments/automatic_prompt_engineer/generate.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":"3da4ab7760bb2fb6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}