Cover Image

Textual Gradients are a Flawed Metaphor for Automatic Prompt Optimization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Melcer, Daniel, Chen, Qi, Chiang, Wen-Hao, Garg, Shweta, Garg, Pranav, Bock, Christian
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs
by: Hua, Andong, et al.
Published: (2025)

FlowBot: Inducing LLM Workflows with Bilevel Optimization and Textual Gradients
by: Yu, Hongyeon, et al.
Published: (2026)

TRPrompt: Bootstrapping Query-Aware Prompt Optimization from Textual Rewards
by: Nica, Andreea, et al.
Published: (2025)

Automatic Prompt Optimization with Prompt Distillation
by: Dyagin, Ernest A., et al.
Published: (2025)

Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws
by: Jha, Akshita, et al.
Published: (2024)

The Limited Impact of Medical Adaptation of Large Language and Vision-Language Models
by: Jeong, Daniel P., et al.
Published: (2024)

Auto-Prompt Generation is Not Robust: Prompt Optimization Driven by Pseudo Gradient
by: Shi, Zeru, et al.
Published: (2024)

RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold
by: Setlur, Amrith, et al.
Published: (2024)

Mitigating Hallucinated Translations in Large Language Models with Hallucination-focused Preference Optimization
by: Tang, Zilu, et al.
Published: (2025)

Correlated Errors in Large Language Models
by: Kim, Elliot, et al.
Published: (2025)

Approximately Aligned Decoding
by: Melcer, Daniel, et al.
Published: (2024)

$p1$: Better Prompt Optimization with Fewer Prompts
by: Gao, Zhaolin, et al.
Published: (2026)

Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning
by: Shrivastava, Vaishnavi, et al.
Published: (2025)

Prompt-SAW: Leveraging Relation-Aware Graphs for Textual Prompt Compression
by: Ali, Muhammad Asif, et al.
Published: (2024)

Prompt-to-Leaderboard
by: Frick, Evan, et al.
Published: (2025)

Automatic Prompt Selection for Large Language Models
by: Do, Viet-Tung, et al.
Published: (2024)

ContrastWSD: Enhancing Metaphor Detection with Word Sense Disambiguation Following the Metaphor Identification Procedure
by: Elzohbi, Mohamad, et al.
Published: (2023)

The Road of Adaptive AI for Precision in Cybersecurity
by: Garg, Sahil
Published: (2025)

Can Gradient Descent Simulate Prompting?
by: Zhang, Eric, et al.
Published: (2025)

ViT Registers and Fractal ViT
by: Chou, Jason Chuan-Chih, et al.
Published: (2026)

LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization
by: Wu, Yuanchen, et al.
Published: (2025)

Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization
by: Wan, Xingchen, et al.
Published: (2024)

Enhancing Hyperbole and Metaphor Detection with Their Bidirectional Dynamic Interaction and Emotion Knowledge
by: Zheng, Li, et al.
Published: (2025)

Personalized Decision Modeling: Utility Optimization or Textualized-Symbolic Reasoning
by: Zhao, Yibo, et al.
Published: (2025)

An Automatic Prompt Generation System for Tabular Data Tasks
by: Akella, Ashlesha, et al.
Published: (2024)

ProRefine: Inference-Time Prompt Refinement with Textual Feedback
by: Pandita, Deepak, et al.
Published: (2025)

RePrompt: Planning by Automatic Prompt Engineering for Large Language Models Agents
by: Chen, Weizhe, et al.
Published: (2024)

Dialogue for Prompting: a Policy-Gradient-Based Discrete Prompt Generation for Few-shot Learning
by: Li, Chengzhengxu, et al.
Published: (2023)

Endless Terminals: Scaling RL Environments for Terminal Agents
by: Gandhi, Kanishk, et al.
Published: (2026)

Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept Discovery
by: Yu, Xuemin, et al.
Published: (2026)

LoRA-Mini : Adaptation Matrices Decomposition and Selective Training
by: Singh, Ayush, et al.
Published: (2024)

Learn-to-learn on Arbitrary Textual Conditioning: A Hypernetwork-Driven Meta-Gated LLM
by: Ji, Luo, et al.
Published: (2026)

Benchmarked Yet Not Measured -- Generative AI Should be Evaluated Against Real-World Utility
by: Mondal, Ishani, et al.
Published: (2026)

VLMGuard-R1: Proactive Safety Alignment for VLMs via Reasoning-Driven Prompt Optimization
by: Chen, Menglan, et al.
Published: (2025)

The Unreasonable Effectiveness of Eccentric Automatic Prompts
by: Battle, Rick, et al.
Published: (2024)

Science is Exploration: Computational Frontiers for Conceptual Metaphor Theory
by: Hicke, Rebecca M. M., et al.
Published: (2024)

Exploring Gradient-Guided Masked Language Model to Detect Textual Adversarial Attacks
by: Zhang, Xiaomei, et al.
Published: (2025)

Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress?
by: Jeong, Daniel P., et al.
Published: (2024)

Architectural Flaw Detection in Civil Engineering Using GPT-4
by: Kumar, Saket, et al.
Published: (2024)

LLM as a Complementary Optimizer to Gradient Descent: A Case Study in Prompt Tuning
by: Guo, Zixian, et al.
Published: (2024)