Cover Image

Where's the Bug? Attention Probing for Scalable Fault Localization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Stein, Adam, Wayne, Arthur, Naik, Aaditya, Naik, Mayur, Wong, Eric
Format:	Preprint
Published:	2025
Subjects:	Software Engineering Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TorchQL: A Programming Framework for Integrity Constraints in Machine Learning
by: Naik, Aaditya, et al.
Published: (2023)

The Road to Generalizable Neuro-Symbolic Learning Should be Paved with Foundation Models
by: Stein, Adam, et al.
Published: (2025)

Bug-Report-Driven Fault Localization: Industrial Benchmarking and Lesson Learned at ABB Robotics
by: Hall, Pernilla, et al.
Published: (2026)

Towards Compositionality in Concept Learning
by: Stein, Adam, et al.
Published: (2024)

Challenging Bug Prediction and Repair Models with Synthetic Bugs
by: Ibrahimzada, Ali Reza, et al.
Published: (2023)

Program Structure Aware Precondition Generation
by: Dinella, Elizabeth, et al.
Published: (2023)

BugGen: A Self-Correcting Multi-Agent LLM Pipeline for Realistic RTL Bug Synthesis
by: Jasper, Surya, et al.
Published: (2025)

Data Augmentation for Code Translation with Comparable Corpora and Multiple References
by: Xie, Yiqing, et al.
Published: (2023)

Can Hessian-Based Insights Support Fault Diagnosis in Attention-based Models?
by: Jahan, Sigma, et al.
Published: (2025)

Dolphin: A Programmable Framework for Scalable Neurosymbolic Learning
by: Naik, Aaditya, et al.
Published: (2024)

LLM Critics Help Catch LLM Bugs
by: McAleese, Nat, et al.
Published: (2024)

Fault Localization in Deep Learning-based Software: A System-level Approach
by: Morovati, Mohammad Mehdi, et al.
Published: (2024)

The Limits of Long-Context Reasoning in Automated Bug Fixing
by: Raju, Ravi, et al.
Published: (2026)

An Empirical Evaluation of Locally Deployed LLMs for Bug Detection in Python Code
by: Vulićević, Jelena Ilić
Published: (2026)

Towards Enhancing the Reproducibility of Deep Learning Bugs: An Empirical Study
by: Shah, Mehil B., et al.
Published: (2024)

Fault Localization via Fine-tuning Large Language Models with Mutation Generated Stack Traces
by: Jambigi, Neetha, et al.
Published: (2025)

GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization
by: Wang, Juntong, et al.
Published: (2026)

LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs
by: Liu, Kaibo, et al.
Published: (2024)

Language Models are Better Bug Detector Through Code-Pair Classification
by: Alrashedy, Kamel, et al.
Published: (2023)

IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities
by: Li, Ziyang, et al.
Published: (2024)

Combining Language and App UI Analysis for the Automated Assessment of Bug Reproduction Steps
by: Mahmud, Junayed, et al.
Published: (2025)

When Bugs Linger: A Study of Anomalous Resolution Time Outliers and Their Themes
by: Patil, Avinash
Published: (2025)

Bug Severity Prediction in Software Projects Using Supervised Machine Learning Models
by: Nice, Nafisha Tamanna
Published: (2026)

HackerRank-ASTRA: Evaluating Correctness & Consistency of Large Language Models on cross-domain multi-file project problems
by: Xing, Jun, et al.
Published: (2025)

ARFT-Transformer: Modeling Metric Dependencies for Cross-Project Aging-Related Bug Prediction
by: Ge, Shuning, et al.
Published: (2026)

MathDuels: Evaluating LLMs as Problem Posers and Solvers
by: Xu, Zhiqiu, et al.
Published: (2026)

Comparative Analysis of Quantum and Classical Support Vector Classifiers for Software Bug Prediction: An Exploratory Study
by: Nadim, Md, et al.
Published: (2025)

Semantic GUI Scene Learning and Video Alignment for Detecting Duplicate Video-based Bug Reports
by: Yan, Yanfu, et al.
Published: (2024)

BLAZE: Cross-Language and Cross-Project Bug Localization via Dynamic Chunking and Hard Example Learning
by: Chakraborty, Partha, et al.
Published: (2024)

Can LLMs Find Bugs in Code? An Evaluation from Beginner Errors to Security Vulnerabilities in Python and C++
by: Mhatre, Akshay, et al.
Published: (2025)

MetaLint: Easy-to-Hard Generalization for Code Linting
by: Naik, Atharva, et al.
Published: (2025)

FGDM: Reasoning Aware Multi-Agentic Framework for Software Bug Detection using Chain of Thought and Tree of Thought Prompting
by: Padmanabhuni, Srita, et al.
Published: (2026)

LLM-Based Test-Driven Interactive Code Generation: User Study and Empirical Evaluation
by: Fakhoury, Sarah, et al.
Published: (2024)

A Feature-Driven Framework for Software Fault Prediction
by: Ghazi, Ahmad Nauman, et al.
Published: (2026)

Are Large Language Models Memorizing Bug Benchmarks?
by: Ramos, Daniel, et al.
Published: (2024)

Where Do LLMs Still Struggle? An In-Depth Analysis of Code Generation Benchmarks
by: Sharifloo, Amir Molzam, et al.
Published: (2025)

COSMosFL: Ensemble of Small Language Models for Fault Localisation
by: Cho, Hyunjoon, et al.
Published: (2025)

The Fault in our Stars: Quality Assessment of Code Generation Benchmarks
by: Siddiq, Mohammed Latif, et al.
Published: (2024)

Investigating Reproducibility in Deep Learning-Based Software Fault Prediction
by: Mukhtar, Adil, et al.
Published: (2024)

Identifier-Free Code Embedding Models for Scalable Search
by: Wolos, Eric, et al.
Published: (2026)