Pith. sign in

REVIEW 10 cited by

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

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2302.03668 v2 pith:JG7VL53R submitted 2023-02-07 cs.LG cs.CL

classification cs.LGcs.CL
keywords promptshardmodelsoptimizationtext-basedapproachautomaticallydiscovered
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Universal and Transferable Adversarial Attacks on Aligned Language Models

    cs.CL 2023-07 accept novelty 8.0 of 10

    Gradient and greedy search over token suffixes produces universal, transferable adversarial prompts that elicit objectionable outputs from aligned models including black-box commercial systems.

  2. PRISM: Recovering Instruction Sets from Language Model Activations

    cs.AI 2026-06 unverdicted novelty 7.0 of 10

    PRISM is a new activation-conditioned model that recovers full sets of simultaneous instructions from LLM hidden states via judge-guided GRPO training and outperforms prior activation-to-language methods on security-r...

  3. Learning, Fast and Slow: Towards LLMs That Adapt Continually

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    Fast-Slow Training uses context optimization as fast weights alongside parameter updates as slow weights to achieve up to 3x better sample efficiency, higher performance, and less catastrophic forgetting than standard...

  4. Adaptive Prompt Embedding Optimization for LLM Jailbreaking

    cs.AI 2026-04 unverdicted novelty 7.0 of 10

    PEO optimizes original prompt embeddings continuously over adaptive rounds to jailbreak aligned LLMs, preserving the exact visible prompt text and outperforming discrete suffix, appended embedding, and search-based wh...

  5. Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

    cs.CL 2023-10 conditional novelty 7.0 of 10

    Varying decoding strategies such as temperature and sampling methods jailbreaks safety alignments in open-source LLMs, raising misalignment from 0% to over 95% at 30x lower cost than prior attacks.

  6. Large Language Models as Optimizers

    cs.LG 2023-09 unverdicted novelty 7.0 of 10

    Large language models can optimize by being prompted with histories of past solutions and scores to propose better ones, producing prompts that raise accuracy up to 8% on GSM8K and 50% on Big-Bench Hard over human-des...

  7. Learning, Fast and Slow: Towards LLMs That Adapt Continually

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    Fast-Slow Training combines slow parameter updates with fast context optimization to achieve up to 3x better sample efficiency, higher performance, less forgetting, and preserved plasticity in continual LLM learning.

  8. Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing

    cs.CR 2026-05 unverdicted novelty 6.0 of 10

    DR-Smoothing introduces a disrupt-then-rectify prompt processing scheme into smoothing defenses, delivering tight theoretical bounds on success probability against both token- and prompt-level jailbreaks.

  9. Baseline Defenses for Adversarial Attacks Against Aligned Language Models

    cs.LG 2023-09 conditional novelty 6.0 of 10

    Baseline defenses including perplexity-based detection, input preprocessing, and adversarial training offer partial robustness to text adversarial attacks on LLMs, with challenges arising from weak discrete optimizers.

  10. Does Your VFM Speak Plant? The Botanical Grammar of Vision Foundation Models for Object Detection

    cs.CV 2026-04 unverdicted novelty 5.0 of 10

    Optimized prompts for vision foundation models improve cowpea detection accuracy by over 0.35 mAP on synthetic data and transfer effectively to real fields without manual annotations.

Pith tools