{"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/hard-prompts-made-easy-gradient-based-1","title":"Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery","arxiv_id":"2302.03668","date":"2023-02-07","proceeding":"NeurIPS 2023 11","authors":["Yuxin Wen","Neel Jain","John Kirchenbauer","Micah Goldblum","Jonas Geiping","Tom Goldstein"],"abstract":"The strength of modern generative models lies in their ability to be controlled through text-based prompts. Typical \"hard\" prompts are made from interpretable words and tokens, and must be hand-crafted by humans. There are also \"soft\" prompts, which consist of continuous feature vectors. These can be discovered using powerful optimization methods, but they cannot be easily interpreted, re-used across models, or plugged into a text-based interface. We describe an approach to robustly optimize hard text prompts through efficient gradient-based optimization. Our approach automatically generates hard text-based prompts for both text-to-image and text-to-text applications. In the text-to-image setting, the method creates hard prompts for diffusion models, allowing API users to easily generate, discover, and mix and match image concepts without prior knowledge on how to prompt the model. In the text-to-text setting, we show that hard prompts can be automatically discovered that are effective in tuning LMs for classification.","url_abs":"https://arxiv.org/abs/2302.03668v2","url_pdf":"https://arxiv.org/pdf/2302.03668v2.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":"hard-prompts-made-easy-gradient-based-1","repo_url":"https://github.com/YuxinWenRick/hard-prompts-made-easy","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hard-prompts-made-easy-gradient-based-1","repo_url":"https://github.com/joycenerd/p4d","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.03668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.03668"}},"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/YuxinWenRick/hard-prompts-made-easy","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/joycenerd/p4d","reach":null}],"summary":{"ran_violates":1,"ran_draft_wrong":1,"unverified":5},"by_repo_kind":{"official":{"samples":7,"ran":2,"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":"f19962ebb134b3d7","entry":"convert_to_custom_text_state_dict","repo":"YuxinWenRick/hard-prompts-made-easy","repo_kind":"official","path":"open_clip/model.py","file_url":"https://github.com/YuxinWenRick/hard-prompts-made-easy/blob/HEAD/open_clip/model.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f19962ebb134b3d7"}},{"code_sha256_prefix":"dcd422d66b0581d8","entry":"get_cast_dtype","repo":"YuxinWenRick/hard-prompts-made-easy","repo_kind":"official","path":"open_clip/model.py","file_url":"https://github.com/YuxinWenRick/hard-prompts-made-easy/blob/HEAD/open_clip/model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"code_sha256_prefix":"10a858bd32dad1e6","entry":"build_model_from_openai_state_dict","repo":"YuxinWenRick/hard-prompts-made-easy","repo_kind":"official","path":"open_clip/model.py","file_url":"https://github.com/YuxinWenRick/hard-prompts-made-easy/blob/HEAD/open_clip/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"10a858bd32dad1e6"}},{"code_sha256_prefix":"2a5d45214b93d7de","entry":"decode_ids","repo":"YuxinWenRick/hard-prompts-made-easy","repo_kind":"official","path":"optim_utils.py","file_url":"https://github.com/YuxinWenRick/hard-prompts-made-easy/blob/HEAD/optim_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2a5d45214b93d7de"}},{"code_sha256_prefix":"ddcbd45e940484ee","entry":"gather_features","repo":"YuxinWenRick/hard-prompts-made-easy","repo_kind":"official","path":"open_clip/loss.py","file_url":"https://github.com/YuxinWenRick/hard-prompts-made-easy/blob/HEAD/open_clip/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"code_sha256_prefix":"0bf4874e1d9eed03","entry":"read_json","repo":"YuxinWenRick/hard-prompts-made-easy","repo_kind":"official","path":"optim_utils.py","file_url":"https://github.com/YuxinWenRick/hard-prompts-made-easy/blob/HEAD/optim_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0bf4874e1d9eed03"}},{"code_sha256_prefix":"2a377da4a76a2d44","entry":"register_pooler","repo":"YuxinWenRick/hard-prompts-made-easy","repo_kind":"official","path":"open_clip/hf_model.py","file_url":"https://github.com/YuxinWenRick/hard-prompts-made-easy/blob/HEAD/open_clip/hf_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2a377da4a76a2d44"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}