Cover Image

Your Instructions Are Not Always Helpful: Assessing the Efficacy of Instruction Fine-tuning for Software Vulnerability Detection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yusuf, Imam Nur Bani, Jiang, Lingxiao
Format:	Preprint
Published:	2024
Subjects:	Software Engineering Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Transducer Tuning: Efficient Model Adaptation for Software Tasks Using Code Property Graphs
by: Yusuf, Imam Nur Bani, et al.
Published: (2024)

Code Review Agent Benchmark
by: Zhang, Yuntong, et al.
Published: (2026)

Isolating Compiler Bugs by Generating Effective Witness Programs with Large Language Models
by: Tu, Haoxin, et al.
Published: (2023)

Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios
by: Chen, Zhi, et al.
Published: (2024)

Beyond Final Code: A Process-Oriented Error Analysis of Software Development Agents in Real-World GitHub Scenarios
by: Chen, Zhi, et al.
Published: (2025)

An Empirical Study of the Imbalance Issue in Software Vulnerability Detection
by: Guo, Yuejun, et al.
Published: (2026)

Learning Generalizable Multimodal Representations for Software Vulnerability Detection
by: Dong, Zeming, et al.
Published: (2026)

Toward Scalable Automated Repository-Level Datasets for Software Vulnerability Detection
by: Lbath, Amine
Published: (2026)

Engineering Reasoning and Instruction (ERI) Benchmark: A Large Taxonomy-driven Dataset for Foundation Models and Agents
by: Naser, MZ, et al.
Published: (2026)

A Systematic Literature Review on Detecting Software Vulnerabilities with Large Language Models
by: Kaniewski, Sabrina, et al.
Published: (2025)

BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions
by: Zhuo, Terry Yue, et al.
Published: (2024)

Same Signal, Different Semantics: A Cross-Framework Behavioral Analysis of Software Engineering Agents
by: Ma, Wei, et al.
Published: (2026)

Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents
by: Chen, Zhi, et al.
Published: (2026)

Software Vulnerability and Functionality Assessment using LLMs
by: Jensen, Rasmus Ingemann Tuffveson, et al.
Published: (2024)

Explaining Software Vulnerabilities with Large Language Models
by: Johnson, Oshando, et al.
Published: (2025)

VulnLLMEval: A Framework for Evaluating Large Language Models in Software Vulnerability Detection and Patching
by: Zibaeirad, Arastoo, et al.
Published: (2024)

Enhancing Software Vulnerability Detection Through Adaptive Test Input Generation Using Genetic Algorithm
by: Mehendran, Yanusha, et al.
Published: (2025)

Identifying Helpful Context for LLM-based Vulnerability Repair: A Preliminary Study
by: Antal, Gábor, et al.
Published: (2025)

Devstral: Fine-tuning Language Models for Coding Agent Applications
by: Rastogi, Abhinav, et al.
Published: (2025)

An Initial Exploration of Fine-tuning Small Language Models for Smart Contract Reentrancy Vulnerability Detection
by: Pofcher, Ignacio Mariano Andreozzi, et al.
Published: (2025)

RustMap: Towards Project-Scale C-to-Rust Migration via Program Analysis and LLM
by: Cai, Xuemeng, et al.
Published: (2025)

Eliciting Instruction-tuned Code Language Models' Capabilities to Utilize Auxiliary Function for Code Generation
by: Lee, Seonghyeon, et al.
Published: (2024)

EvalSVA: Multi-Agent Evaluators for Next-Gen Software Vulnerability Assessment
by: Wen, Xin-Cheng, et al.
Published: (2024)

SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
by: Han, Tingxu, et al.
Published: (2026)

Instruction-Driven Game Engine: A Poker Case Study
by: Wu, Hongqiu, et al.
Published: (2024)

Bridging Semantics & Structure for Software Vulnerability Detection using Hybrid Network Models
by: Gajjar, Jugal, et al.
Published: (2025)

Data and Context Matter: Towards Generalizing AI-based Software Vulnerability Detection
by: Safdar, Rijha, et al.
Published: (2025)

AI-assisted Code Authoring at Scale: Fine-tuning, deploying, and mixed methods evaluation
by: Murali, Vijayaraghavan, et al.
Published: (2023)

Instruction-Tuning Open-Weight Language Models for BPMN Model Generation
by: Çelikmasat, Gökberk, et al.
Published: (2025)

Promise and Peril of Collaborative Code Generation Models: Balancing Effectiveness and Memorization
by: Chen, Zhi, et al.
Published: (2024)

Reasoning with LLMs for Zero-Shot Vulnerability Detection
by: Zibaeirad, Arastoo, et al.
Published: (2025)

LicenseGPT: A Fine-tuned Foundation Model for Publicly Available Dataset License Compliance
by: Tan, Jingwen, et al.
Published: (2024)

Harnessing Large Language Models for Software Vulnerability Detection: A Comprehensive Benchmarking Study
by: Tamberg, Karl, et al.
Published: (2024)

EaTVul: ChatGPT-based Evasion Attack Against Software Vulnerability Detection
by: Liu, Shigang, et al.
Published: (2024)

Turbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code
by: Honarvar, Shahin, et al.
Published: (2023)

ContextCov: Deriving and Enforcing Executable Constraints from Agent Instruction Files
by: Sharma, Reshabh K
Published: (2026)

Explaining the Contributing Factors for Vulnerability Detection in Machine Learning
by: Mouine, Esma, et al.
Published: (2024)

AppBench: Planning of Multiple APIs from Various APPs for Complex User Instruction
by: Wang, Hongru, et al.
Published: (2024)

Prompt Stability in Code LLMs: Measuring Sensitivity across Emotion- and Personality-Driven Variations
by: Ma, Wei, et al.
Published: (2025)

Enhancing LLM Fine-tuning for Text-to-SQLs by SQL Quality Measurement
by: Sarker, Shouvon, et al.
Published: (2024)