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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Xiang, Cao, Juntai, Wei, Jiaqi, You, Chenyu, Ding, Dujian
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

Supervised Chain of Thought
di: Zhang, Xiang, et al.
Pubblicazione: (2024)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

A Survey on Prompting Techniques in LLMs
di: Bhandari, Prabin
Pubblicazione: (2023)

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

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

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

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

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

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

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

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

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

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

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

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

P3: Prompts Promote Prompting
di: Zhang, Xinyu, et al.
Pubblicazione: (2025)

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

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

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

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

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

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

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