Papers › Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery

Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery

7 Feb 2023NeurIPS 2023 11arXiv:2302.03668archive 2025-07-28

Yuxin Wen, Neel Jain, John Kirchenbauer, Micah Goldblum, Jonas Geiping, Tom Goldstein

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2302.03668")

Code

Syntology Ran 2 of 7 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · violated contract; 1 ran · our draft was wrong.

By repository: official repository: 7 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

YuxinWenRick/hard-prompts-made-easy officialmentioned in paperpytorchMIT report
joycenerd/p4d mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

7 samples harvested; 2 ran; 0 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
1ran · our draft was wrong
5unverified

Licence: 0 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from YuxinWenRick/hard-prompts-made-easy. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

convert_to_custom_text_state_dict YuxinWenRick/hard-prompts-made-easy/open_clip/model.py official repository ran · violated contract MIT (permissive) · f19962ebb134b3d7 · report
get_cast_dtype YuxinWenRick/hard-prompts-made-easy/open_clip/model.py official repository ran · our draft was wrong MIT (permissive) · dcd422d66b0581d8 · report
build_model_from_openai_state_dict YuxinWenRick/hard-prompts-made-easy/open_clip/model.py official repository unverified MIT (permissive) · 10a858bd32dad1e6 · report
decode_ids YuxinWenRick/hard-prompts-made-easy/optim_utils.py official repository unverified MIT (permissive) · 2a5d45214b93d7de · report
gather_features YuxinWenRick/hard-prompts-made-easy/open_clip/loss.py official repository unverified MIT (permissive) · ddcbd45e940484ee · report
read_json YuxinWenRick/hard-prompts-made-easy/optim_utils.py official repository unverified MIT (permissive) · 0bf4874e1d9eed03 · report
register_pooler YuxinWenRick/hard-prompts-made-easy/open_clip/hf_model.py official repository unverified MIT (permissive) · 2a377da4a76a2d44 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections