Cover Image

Can Hessian-Based Insights Support Fault Diagnosis in Attention-based Models?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jahan, Sigma, Rahman, Mohammad Masudur
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Software Engineering
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Why Attention Fails: A Taxonomy of Faults in Attention-Based Neural Networks
by: Jahan, Sigma, et al.
Published: (2025)

DEFault++: Automated Fault Detection, Categorization, and Diagnosis for Transformer Architectures
by: Jahan, Sigma, et al.
Published: (2026)

Improved Detection and Diagnosis of Faults in Deep Neural Networks Using Hierarchical and Explainable Classification
by: Jahan, Sigma, et al.
Published: (2025)

Towards Understanding the Challenges of Bug Localization in Deep Learning Systems
by: Jahan, Sigma, et al.
Published: (2024)

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

Imitation Game: Reproducing Deep Learning Bugs Leveraging an Intelligent Agent
by: Shah, Mehil B, et al.
Published: (2025)

Improved Bug Localization with AI Agents Leveraging Hypothesis and Dynamic Cognition
by: Samir, Asif Mohammed, et al.
Published: (2026)

Improving IR-based Bug Localization with Semantics-Driven Query Reduction
by: Samir, Asif Mohammed, et al.
Published: (2025)

Characterizing Faults in Agentic AI: A Taxonomy of Types, Symptoms, and Root Causes
by: Shah, Mehil B, et al.
Published: (2026)

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

Where's the Bug? Attention Probing for Scalable Fault Localization
by: Stein, Adam, et al.
Published: (2025)

Understanding the Impact of Domain Term Explanation on Duplicate Bug Report Detection
by: Mukherjee, Usmi, et al.
Published: (2025)

BugMentor: Generating Answers to Follow-up Questions from Software Bug Reports using Structured Information Retrieval and Neural Text Generation
by: Mukherjee, Usmi, et al.
Published: (2023)

Can We Identify Stack Overflow Questions Requiring Code Snippets? Investigating the Cause & Effect of Missing Code Snippets
by: Mondal, Saikat, et al.
Published: (2024)

Do Internal Software Metrics Have Relationship with Fault-proneness and Change-proneness?
by: Rahman, Md. Masudur, et al.
Published: (2023)

Be a Partner, not a Bystander in Software Engineering Practice: Bridging the Gaps between Academia and Industry
by: Rahman, Mohammad Masudur, et al.
Published: (2026)

On the Prevalence, Evolution, and Impact of Code Smells in Simulation Modelling Software
by: Mahbub, Riasat, et al.
Published: (2024)

Towards Understanding the Impact of Data Bugs on Deep Learning Models in Software Engineering
by: Shah, Mehil B, et al.
Published: (2024)

Learning-Based Testing for Deep Learning: Enhancing Model Robustness with Adversarial Input Prioritization
by: Rahman, Sheikh Md Mushfiqur, et al.
Published: (2025)

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

Explaining Software Bugs Leveraging Code Structures in Neural Machine Translation
by: Mahbub, Parvez, et al.
Published: (2022)

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

Relative Positioning Based Code Chunking Method For Rich Context Retrieval In Repository Level Code Completion Task With Code Language Model
by: Rahman, Imranur, et al.
Published: (2025)

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

Assessing the Impact of Code Changes on the Fault Localizability of Large Language Models
by: Haroon, Sabaat, et al.
Published: (2025)

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

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

Can Code Language Models Learn Clarification-Seeking Behaviors?
by: Wu, Jie JW, et al.
Published: (2025)

Supporting Safety Analysis of Image-processing DNNs through Clustering-based Approaches
by: Attaoui, Mohammed Oualid, et al.
Published: (2023)

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

RBT4DNN: Requirements-based Testing of Neural Networks
by: Mozumder, Nusrat Jahan, et al.
Published: (2025)

Whitespaces Don't Lie: Feature-Driven and Embedding-Based Approaches for Detecting Machine-Generated Code
by: Nirob, Syed Mehedi Hasan, et al.
Published: (2026)

Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation
by: Sinha, Shiven, et al.
Published: (2025)

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

Trojans in Large Language Models of Code: A Critical Review through a Trigger-Based Taxonomy
by: Hussain, Aftab, et al.
Published: (2024)

Real Faults in Deep Learning Fault Benchmarks: How Real Are They?
by: Jahangirova, Gunel, et al.
Published: (2024)

Evaluation and Improvement of Fault Detection for Large Language Models
by: Hu, Qiang, et al.
Published: (2024)

An ML-based Approach to Predicting Software Change Dependencies: Insights from an Empirical Study on OpenStack
by: Arabat, Ali, et al.
Published: (2025)

Generating Realistic, Diverse, and Fault-Revealing Inputs with Latent Space Interpolation for Testing Deep Neural Networks
by: Duan, Bin, et al.
Published: (2025)

Assumptions to Evidence: Evaluating Security Practices Adoption and Their Impact on Outcomes in the npm Ecosystem
by: Zahan, Nusrat, et al.
Published: (2025)