Why Prompt Design Matters and Works: A Complexity Analysis of Prompt Search Space in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Xiang, Cao, Juntai, Wei, Jiaqi, You, Chenyu, Ding, Dujian
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Tokenization Constraints in LLMs: A Study of Symbolic and Arithmetic Reasoning Limits
by: Zhang, Xiang, et al.
Published: (2025)

Counting Ability of Large Language Models and Impact of Tokenization
by: Zhang, Xiang, et al.
Published: (2024)

Supervised Chain of Thought
by: Zhang, Xiang, et al.
Published: (2024)

Unifying Tree Search Algorithm and Reward Design for LLM Reasoning: A Survey
by: Wei, Jiaqi, et al.
Published: (2025)

Multi2: Multi-Agent Test-Time Scalable Framework for Multi-Document Processing
by: Cao, Juntai, et al.
Published: (2025)

LLM Performance Predictors are good initializers for Architecture Search
by: Jawahar, Ganesh, et al.
Published: (2023)

Why Prompt Optimization Works, and Why It Sometimes Doesn't: A Causal-Inspired Edit-Level Analysis
by: Gong, Shuzhi, et al.
Published: (2026)

Prompt Optimization as a State-Space Search Problem
by: Taneja, Maanas
Published: (2025)

PromptPrism: A Linguistically-Inspired Taxonomy for Prompts
by: Jeoung, Sullam, et al.
Published: (2025)

How Large Language Models (LLMs) Extrapolate: From Guided Missiles to Guided Prompts
by: Cao, Xuenan
Published: (2024)

A Toolbox for Improving Evolutionary Prompt Search
by: Grießhaber, Daniel, et al.
Published: (2025)

Intuitive or Dependent? Investigating LLMs' Behavior Style to Conflicting Prompts
by: Ying, Jiahao, et al.
Published: (2023)

Learning Optimal Prompt Ensemble for Multi-source Visual Prompt Transfer
by: Zhang, Enming, et al.
Published: (2025)

When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs
by: Seleznyov, Mikhail, et al.
Published: (2025)

Leveraging Prompts in LLMs to Overcome Imbalances in Complex Educational Text Data
by: McClure, Jeanne, et al.
Published: (2024)

Privacy Policy Analysis through Prompt Engineering for LLMs
by: Goknil, Arda, et al.
Published: (2024)

SciPrompt: Knowledge-augmented Prompting for Fine-grained Categorization of Scientific Topics
by: You, Zhiwen, et al.
Published: (2024)

Can Prompts Rewind Time for LLMs? Evaluating the Effectiveness of Prompted Knowledge Cutoffs
by: Gao, Xin, et al.
Published: (2025)

RulePrompt: Weakly Supervised Text Classification with Prompting PLMs and Self-Iterative Logical Rules
by: Li, Miaomiao, et al.
Published: (2024)

A Survey on Prompting Techniques in LLMs
by: Bhandari, Prabin
Published: (2023)

Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in Customized Large Language Models
by: Liang, Zi, et al.
Published: (2024)

ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs
by: Zhuo, Jingming, et al.
Published: (2024)

Training Prompt Matters: State-Adaptive Optimization for Robust Fine-Tuning
by: Shi, Wenhang, et al.
Published: (2026)

Prompt Recursive Search: A Living Framework with Adaptive Growth in LLM Auto-Prompting
by: Zhao, Xiangyu, et al.
Published: (2024)

Thinking Inside the Mask: In-Place Prompting in Diffusion LLMs
by: Jin, Xiangqi, et al.
Published: (2025)

PromptCL: Improving Event Representation via Prompt Template and Contrastive Learning
by: Feng, Yubo, et al.
Published: (2024)

How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompts
by: Qian, Yusu, et al.
Published: (2024)

LangGPT: Rethinking Structured Reusable Prompt Design Framework for LLMs from the Programming Language
by: Wang, Ming, et al.
Published: (2024)

Simplify-This: A Comparative Analysis of Prompt-Based and Fine-Tuned LLMs
by: Cohen, Eilam, et al.
Published: (2026)

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems
by: Chen, Ke, et al.
Published: (2025)

Which Words Matter Most in Zero-Shot Prompts?
by: Sadr, Nikta Gohari, et al.
Published: (2025)

Order Matters: Rethinking Prompt Construction in In-Context Learning
by: Li, Warren, et al.
Published: (2025)

P3: Prompts Promote Prompting
by: Zhang, Xinyu, et al.
Published: (2025)

Learning to Rewrite Prompts for Bootstrapping LLMs on Downstream Tasks
by: Zhou, Qinhao, et al.
Published: (2025)

No One Fits All: From Fixed Prompting to Learned Routing in Multilingual LLMs
by: Wu, Wei-Chi, et al.
Published: (2026)

PromptNCE: Pointwise Mutual Information Predictions Using Only LLMs and Contrastive Estimation Prompts
by: Woodrow, Juliette, et al.
Published: (2026)

TACOMORE: Leveraging the Potential of LLMs in Corpus-based Discourse Analysis with Prompt Engineering
by: Li, Bingru, et al.
Published: (2024)

Prompt Balance Matters: Understanding How Imbalanced Few-Shot Learning Affects Multilingual Sense Disambiguation in LLMs
by: Sumanathilaka, Deshan, et al.
Published: (2025)

When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning
by: Wei, Jiaqi, et al.
Published: (2026)

In-context Demonstration Matters: On Prompt Optimization for Pseudo-Supervision Refinement
by: Zhang, Zhen-Yu, et al.
Published: (2024)