Cover Image

The Stability Trap: Evaluating the Reliability of LLM-Based Instruction Adherence Auditing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Shergadwala, Murtuza N.
Format:	Preprint
Published:	2026
Subjects:	Software Engineering Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AutoMonitor-Bench: Evaluating the Reliability of LLM-Based Misbehavior Monitor
by: Yang, Shu, et al.
Published: (2026)

Instruction Adherence in Coding Agent Configuration Files: A Factorial Study of Four File-Structure Variables
by: McMillan, Damon
Published: (2026)

FireBench: Evaluating Instruction Following in Enterprise and API-Driven LLM Applications
by: Zhang, Yunfan, et al.
Published: (2026)

ISD-Agent-Bench: A Comprehensive Benchmark for Evaluating LLM-based Instructional Design Agents
by: Jeon, YoungHoon, et al.
Published: (2026)

Revisiting the Reliability of Language Models in Instruction-Following
by: Dong, Jianshuo, et al.
Published: (2025)

Measuring LLM Code Generation Stability via Structural Entropy
by: Song, Yewei, et al.
Published: (2025)

Comparing Developer and LLM Biases in Code Evaluation
by: Mittal, Aditya, et al.
Published: (2026)

BenchGuard: Who Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks
by: Tu, Xinming, et al.
Published: (2026)

Agent-Diff: Benchmarking LLM Agents on Enterprise API Tasks via Code Execution with State-Diff-Based Evaluation
by: Pysklo, Hubert M., et al.
Published: (2026)

Evaluating and Achieving Controllable Code Completion in Code LLM
by: Zhang, Jiajun, et al.
Published: (2026)

From Output to Evaluation: Does Raw Instruction-Tuned Code LLMs Output Suffice for Fill-in-the-Middle Code Generation?
by: Ahmad, Wasi Uddin, et al.
Published: (2025)

Automatically Benchmarking LLM Code Agents through Agent-Driven Annotation and Evaluation
by: Fu, Lingyue, et al.
Published: (2025)

ArtifactsBench: Bridging the Visual-Interactive Gap in LLM Code Generation Evaluation
by: Zhang, Chenchen, et al.
Published: (2025)

Joint Embeddings for Graph Instruction Tuning
by: Haag, Aaron, et al.
Published: (2024)

Showing LLM-Generated Code Selectively Based on Confidence of LLMs
by: Li, Jia, et al.
Published: (2024)

Don't Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation
by: Moon, Jiwon, et al.
Published: (2025)

Characterizing and Evaluating the Reliability of LLMs against Jailbreak Attacks
by: Chen, Kexin, et al.
Published: (2024)

Learning to Ask: When LLM Agents Meet Unclear Instruction
by: Wang, Wenxuan, et al.
Published: (2024)

Evaluate-and-Purify: Fortifying Code Language Models Against Adversarial Attacks Using LLM-as-a-Judge
by: Mu, Wenhan, et al.
Published: (2025)

Evaluating LLM-Based Goal Extraction in Requirements Engineering: Prompting Strategies and Their Limitations
by: Arnaudo, Anna, et al.
Published: (2026)

InstructCoder: Instruction Tuning Large Language Models for Code Editing
by: Li, Kaixin, et al.
Published: (2023)

ProbeLLM: Automating Principled Diagnosis of LLM Failures
by: Huang, Yue, et al.
Published: (2026)

LogLM: From Task-based to Instruction-based Automated Log Analysis
by: Liu, Yilun, et al.
Published: (2024)

Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability
by: Chen, Zejian, et al.
Published: (2026)

Execution-Based Evaluation of Natural Language to Bash and PowerShell for Incident Remediation
by: Vo, Ngoc Phuoc An, et al.
Published: (2024)

OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs
by: Ahmad, Wasi Uddin, et al.
Published: (2025)

From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning
by: Zhang, Jiajun, et al.
Published: (2026)

NALA_MAINZ at BLP-2025 Task 2: A Multi-agent Approach for Bangla Instruction to Python Code Generation
by: Saadi, Hossain Shaikh, et al.
Published: (2025)

Large Language Models Cannot Reliably Detect Vulnerabilities in JavaScript: The First Systematic Benchmark and Evaluation
by: Fei, Qingyuan, et al.
Published: (2025)

Code Fingerprints: Disentangled Attribution of LLM-Generated Code
by: Guo, Jiaxun, et al.
Published: (2026)

FASTRIC: Prompt Specification Language for Verifiable LLM Interactions
by: Jin, Wen-Long
Published: (2025)

Sphinx: Benchmarking and Modeling for LLM-Driven Pull Request Review
by: Zhang, Daoan, et al.
Published: (2026)

SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?
by: Chen, Shiqi, et al.
Published: (2026)

MORTAR: Multi-turn Metamorphic Testing for LLM-based Dialogue Systems
by: Guo, Guoxiang, et al.
Published: (2024)

HarnessLLM: Automatic Testing Harness Generation via Reinforcement Learning
by: Liu, Yujian, et al.
Published: (2025)

Reasoning Runtime Behavior of a Program with LLM: How Far Are We?
by: Chen, Junkai, et al.
Published: (2024)

BanglaForge: LLM Collaboration with Self-Refinement for Bangla Code Generation
by: Dihan, Mahir Labib, et al.
Published: (2025)

What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts
by: Yang, Chenyang, et al.
Published: (2025)

CallNavi, A Challenge and Empirical Study on LLM Function Calling and Routing
by: Song, Yewei, et al.
Published: (2025)

Learning Selective LLM Autonomy from Copilot Feedback in Enterprise Customer Support Workflows
by: Borovkov, Nikita, et al.
Published: (2026)