Image de couverture de livre

From Brittle to Robust: Improving LLM Annotations for SE Optimization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Senthilkumar, Lohith, Menzies, Tim
Format:	Preprint
Publié:	2026
Sujets:	Software Engineering
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Can Large Language Models Improve SE Active Learning via Warm-Starts?
par: Senthilkumar, Lohith, et autres
Publié: (2024)

Less Noise, More Signal: DRR for Better Optimizations of SE Tasks
par: Lustosa, Andre, et autres
Publié: (2025)

Beyond the Prompt: Assessing Domain Knowledge Strategies for High-Dimensional LLM Optimization in Software Engineering
par: Srinivasan, Srinath, et autres
Publié: (2026)

How Low Can You Go? The Data-Light SE Challenge
par: Ganguly, Kishan Kumar, et autres
Publié: (2025)

Minimal Data, Maximum Clarity: A Heuristic for Explaining Optimization
par: Rayegan, Amirali, et autres
Publié: (2025)

Retrospective: Data Mining Static Code Attributes to Learn Defect Predictors
par: Menzies, Tim
Publié: (2025)

From Verification to Herding: Exploiting Software's Sparsity of Influence
par: Menzies, Tim, et autres
Publié: (2026)

BINGO! Simple Optimizers Win Big if Problems Collapse to a Few Buckets
par: Ganguly, Kishan Kumar, et autres
Publié: (2025)

Zoom, Don't Wander: Why Regional Search Outperforms Pareto Reasoning and Global Optimization in Budget-Constrained SBSE
par: Ganguly, Kishan Kumar, et autres
Publié: (2026)

Is Hyper-Parameter Optimization Different for Software Analytics?
par: Yedida, Rahul, et autres
Publié: (2024)

Can Causality Cure Confusion Caused By Correlation (in Software Analytics)?
par: Rayegan, Amirali, et autres
Publié: (2026)

Streamlining Software Reviews: Efficient Predictive Modeling with Minimal Examples
par: Menzies, Tim, et autres
Publié: (2024)

iSNEAK: Partial Ordering as Heuristics for Model-Based Reasoning in Software Engineering
par: Lustosa, Andre, et autres
Publié: (2023)

SE Journals in 2036: Looking Back at the Future We Need to Have
par: Menzies, Tim, et autres
Publié: (2026)

From Coverage to Causes: Data-Centric Fuzzing for JavaScript Engines
par: Ganguly, Kishan Kumar, et autres
Publié: (2025)

Shaky Structures: The Wobbly World of Causal Graphs in Software Analytics
par: Hulse, Jeremy, et autres
Publié: (2025)

MOOT: a Repository of Many Multi-Objective Optimization Tasks
par: Menzies, Tim, et autres
Publié: (2025)

Smart Cuts: Enhance Active Learning for Vulnerability Detection by Pruning Hard-to-Learn Data
par: Lan, Xiang, et autres
Publié: (2025)

Revisiting Process versus Product Metrics: a Large Scale Analysis
par: Majumder, Suvodeep, et autres
Publié: (2020)

When Less is More: On the Value of "Co-training" for Semi-Supervised Software Defect Predictors
par: Majumder, Suvodeep, et autres
Publié: (2022)

SparseCoder: Advancing Source Code Analysis with Sparse Attention and Learned Token Pruning
par: Yang, Xueqi, et autres
Publié: (2023)

SmartOracle -- An Agentic Approach to Mitigate Noise in Differential Oracles
par: Srinivasan, Srinath, et autres
Publié: (2026)

Software Engineering Principles for Fairer Systems: Experiments with GroupCART
par: Peng, Kewen, et autres
Publié: (2025)

500+ Times Faster Than Deep Learning (A Case Study Exploring Faster Methods for Text Mining StackOverflow)
par: Majumder, Suvodeep, et autres
Publié: (2018)

OLAF: Towards Robust LLM-Based Annotation Framework in Empirical Software Engineering
par: Imran, Mia Mohammad, et autres
Publié: (2025)

LAMeD: LLM-generated Annotations for Memory Leak Detection
par: Shemetova, Ekaterina, et autres
Publié: (2025)

Explainable Fault Localization for Programming Assignments via LLM-Guided Annotation
par: Liu, Fang, et autres
Publié: (2025)

Self-reflection in Automated Qualitative Coding: Improving Text Annotation through Secondary LLM Critique
par: Dunivin, Zackary Okun, et autres
Publié: (2026)

AdversariaLLM: A Unified and Modular Toolbox for LLM Robustness Research
par: Beyer, Tim, et autres
Publié: (2025)

Similar Pattern Annotation via Retrieval Knowledge for LLM-Based Test Code Fault Localization
par: Gharachorlu, Golnaz, et autres
Publié: (2026)

HEJ-Robust: A Robustness Benchmark for LLM-Based Automated Program Repair
par: Rabbi, Fazle, et autres
Publié: (2026)

Improving Dynamic Specification Inference with LLM-Generated Counterexamples
par: Balestra, Agustín, et autres
Publié: (2026)

ABFS: Natural Robustness Testing for LLM-based NLP Software
par: Xiao, Mingxuan, et autres
Publié: (2025)

A Multi-Language Perspective on the Robustness of LLM Code Generation
par: Rabbi, Fazle, et autres
Publié: (2025)

Hierarchical Knowledge Injection for Improving LLM-based Program Repair
par: Ehsani, Ramtin, et autres
Publié: (2025)

Assessing the Robustness of LLM-based NLP Software via Automated Testing
par: Xiao, Mingxuan, et autres
Publié: (2024)

Improving LLM-Driven Test Generation by Learning from Mocking Information
par: Lee, Jamie, et autres
Publié: (2026)

Improving LLM-Based Fault Localization with External Memory and Project Context
par: Yeo, Inseok, et autres
Publié: (2025)

Green LLM Techniques in Action: How Effective Are Existing Techniques for Improving the Energy Efficiency of LLM-Based Applications in Industry?
par: Kuran, Pelin Rabia, et autres
Publié: (2026)

IDOL: Improved Different Optimization Levels Testing for Solidity Compilers
par: Li, Lantian, et autres
Publié: (2025)