Copertina

A Taxonomy of Prompt Defects in LLM Systems

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tian, Haoye, Wang, Chong, Yang, BoYang, Zhang, Lyuye, Liu, Yang
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Software Engineering Artificial Intelligence Computation and Language Programming Languages
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

CodeMind: Evaluating Large Language Models for Code Reasoning
di: Liu, Changshu, et al.
Pubblicazione: (2024)

PPM: Automated Generation of Diverse Programming Problems for Benchmarking Code Generation Models
di: Chen, Simin, et al.
Pubblicazione: (2024)

The Prompt Alchemist: Automated LLM-Tailored Prompt Optimization for Test Case Generation
di: Gao, Shuzheng, et al.
Pubblicazione: (2025)

Benchmarking LLM Code Generation for Audio Programming with Visual Dataflow Languages
di: Zhang, William, et al.
Pubblicazione: (2024)

Ranking LLM-Generated Loop Invariants for Program Verification
di: Chakraborty, Saikat, et al.
Pubblicazione: (2023)

Once4All: Skeleton-Guided SMT Solver Fuzzing with LLM-Synthesized Generators
di: Sun, Maolin, et al.
Pubblicazione: (2025)

PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback
di: Peng, Yun, et al.
Pubblicazione: (2024)

Code Broker: A Multi-Agent System for Automated Code Quality Assessment
di: Attrah, Samer
Pubblicazione: (2026)

Arbiter: Detecting Interference in LLM Agent System Prompts
di: Mason, Tony
Pubblicazione: (2026)

TypyBench: Evaluating LLM Type Inference for Untyped Python Repositories
di: Dong, Honghua, et al.
Pubblicazione: (2025)

Executing as You Generate: Hiding Execution Latency in LLM Code Generation
di: Sun, Zhensu, et al.
Pubblicazione: (2026)

LecPrompt: A Prompt-based Approach for Logical Error Correction with CodeBERT
di: Xu, Zhenyu, et al.
Pubblicazione: (2024)

A Taxonomy of Foundation Model based Systems through the Lens of Software Architecture
di: Lu, Qinghua, et al.
Pubblicazione: (2023)

LLMON: An LLM-native Markup Language to Leverage Structure and Semantics at the LLM Interface
di: Hind, Michael, et al.
Pubblicazione: (2026)

Prompt Injection attack against LLM-integrated Applications
di: Liu, Yi, et al.
Pubblicazione: (2023)

Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study
di: Liu, Yi, et al.
Pubblicazione: (2023)

Reinforcement Learning from Compiler and Language Server Feedback
di: Zhang, Yifan, et al.
Pubblicazione: (2025)

From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging
di: Shi, Yuling, et al.
Pubblicazione: (2024)

A Survey of Neural Code Intelligence: Paradigms, Advances and Beyond
di: Sun, Qiushi, et al.
Pubblicazione: (2024)

LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation
di: Zhang, Ziyao, et al.
Pubblicazione: (2024)

LLMs Lean on Priors, Not Programming Language Semantics
di: Thimmaiah, Aditya, et al.
Pubblicazione: (2025)

Is Self-Repair a Silver Bullet for Code Generation?
di: Olausson, Theo X., et al.
Pubblicazione: (2023)

AutoCode: LLMs as Problem Setters for Competitive Programming
di: Zhou, Shang, et al.
Pubblicazione: (2025)

EquiBench: Benchmarking Large Language Models' Reasoning about Program Semantics via Equivalence Checking
di: Wei, Anjiang, et al.
Pubblicazione: (2025)

debug-gym: A Text-Based Environment for Interactive Debugging
di: Yuan, Xingdi, et al.
Pubblicazione: (2025)

BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software
di: Zhang, Zehua, et al.
Pubblicazione: (2025)

CodeIF-Bench: Evaluating Instruction-Following Capabilities of Large Language Models in Interactive Code Generation
di: Wang, Peiding, et al.
Pubblicazione: (2025)

Introduction to Analytical Software Engineering Design Paradigm
di: Houichime, Tarik, et al.
Pubblicazione: (2025)

Agentic Interpretation: Lattice-Structured Evidence for LLM-Based Program Analysis
di: Mitchell, Jacqueline L., et al.
Pubblicazione: (2026)

MoSE: Hierarchical Self-Distillation Enhances Early Layer Embeddings
di: Gurioli, Andrea, et al.
Pubblicazione: (2025)

VisCoder2: Building Multi-Language Visualization Coding Agents
di: Ni, Yuansheng, et al.
Pubblicazione: (2025)

Refactoring Programs Using Large Language Models with Few-Shot Examples
di: Shirafuji, Atsushi, et al.
Pubblicazione: (2023)

Comparing large language models and human programmers for generating programming code
di: Hou, Wenpin, et al.
Pubblicazione: (2024)

DeepLL: Considering Linear Logic for the Analysis of Deep Learning Experiments
di: Papoulias, Nick
Pubblicazione: (2024)

Code Repair with LLMs gives an Exploration-Exploitation Tradeoff
di: Tang, Hao, et al.
Pubblicazione: (2024)

Verus-SpecGym: An Agentic Environment for Evaluating Specification Autoformalization
di: Agarwal, Anmol, et al.
Pubblicazione: (2026)

ECO: Enhanced Code Optimization via Performance-Aware Prompting for Code-LLMs
di: Kim, Su-Hyeon, et al.
Pubblicazione: (2025)

A Declarative Language for Building And Orchestrating LLM-Powered Agent Workflows
di: Daunis, Ivan
Pubblicazione: (2025)

Blueprint First, Model Second: A Framework for Deterministic LLM Workflow
di: Qiu, Libin, et al.
Pubblicazione: (2025)