Image de couverture de livre

Beyond Self-learned Attention: Mitigating Attention Bias in Transformer-based Models Using Attention Guidance

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gesi, Jiri, Ahmed, Iftekhar
Format:	Preprint
Publié:	2024
Sujets:	Software Engineering Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Attention Mechanism and Heuristic Approach: Context-Aware File Ranking Using Multi-Head Self-Attention
par: Sharma, Pradeep Kumar, et autres
Publié: (2026)

Why Attention Fails: A Taxonomy of Faults in Attention-Based Neural Networks
par: Jahan, Sigma, et autres
Publié: (2025)

Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learning
par: Jiang, Nan, et autres
Publié: (2023)

Attention Distance: A Novel Metric for Directed Fuzzing with Large Language Models
par: Bin, Wang, et autres
Publié: (2025)

From Bias To Improved Prompts: A Case Study of Bias Mitigation of Clone Detection Models
par: Chen, QiHong, et autres
Publié: (2025)

Bias Testing and Mitigation in LLM-based Code Generation
par: Huang, Dong, et autres
Publié: (2023)

Beyond Output Correctness: Benchmarking and Evaluating Large Language Model Reasoning in Coding Tasks
par: Li, Yuangang, et autres
Publié: (2026)

MAGNET: A Multi-Graph Attentional Network for Code Clone Detection
par: Zhang, Zixian, et autres
Publié: (2025)

Using AI-Based Coding Assistants in Practice: State of Affairs, Perceptions, and Ways Forward
par: Sergeyuk, Agnia, et autres
Publié: (2024)

An Evaluation of Context Length Extrapolation in Long Code via Positional Embeddings and Efficient Attention
par: Ghosh, Madhusudan, et autres
Publié: (2026)

Explainable Vulnerability Detection in C/C++ Using Edge-Aware Graph Attention Networks
par: Haque, Radowanul, et autres
Publié: (2025)

A Deep Dive Into Large Language Model Code Generation Mistakes: What and Why?
par: Chen, QiHong, et autres
Publié: (2024)

CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking
par: Su, Zian, et autres
Publié: (2024)

Does the Order of Fine-tuning Matter and Why?
par: Chen, Qihong, et autres
Publié: (2024)

EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention
par: Zhang, Yifan, et autres
Publié: (2025)

Self-Adaptive ERP: Embedding NLP into Petri-Net creation and Model Matching
par: Maged, Ahmed, et autres
Publié: (2025)

Mitigating Gender Bias in Code Large Language Models via Model Editing
par: Qin, Zhanyue, et autres
Publié: (2024)

Beyond Blind Spots: Analytic Hints for Mitigating LLM-Based Evaluation Pitfalls
par: Fandina, Ora Nova, et autres
Publié: (2025)

Complex Model Transformations by Reinforcement Learning with Uncertain Human Guidance
par: Dagenais, Kyanna, et autres
Publié: (2025)

EyeTrans: Merging Human and Machine Attention for Neural Code Summarization
par: Zhang, Yifan, et autres
Publié: (2024)

Fairness Is Not Just Ethical: Performance Trade-Off via Data Correlation Tuning to Mitigate Bias in ML Software
par: Xiao, Ying, et autres
Publié: (2025)

Software Engineering and Foundation Models: Insights from Industry Blogs Using a Jury of Foundation Models
par: Li, Hao, et autres
Publié: (2024)

Unveiling Project-Specific Bias in Neural Code Models
par: Li, Zhiming, et autres
Publié: (2022)

Follow-up Attention: An Empirical Study of Developer and Neural Model Code Exploration
par: Paltenghi, Matteo, et autres
Publié: (2022)

GAL-MAD: Towards Explainable Anomaly Detection in Microservice Applications Using Graph Attention Networks
par: Akmeemana, Lahiru, et autres
Publié: (2025)

Function-to-Style Guidance of LLMs for Code Translation
par: Zhang, Longhui, et autres
Publié: (2025)

On Using Agent-based Modeling and Simulation for Studying Blockchain Systems
par: Gürcan, Önder
Publié: (2024)

LangBiTe: A Platform for Testing Bias in Large Language Models
par: Morales, Sergio, et autres
Publié: (2024)

Social Bias in LLM-Generated Code: Benchmark and Mitigation
par: Rabbi, Fazle, et autres
Publié: (2026)

LogLLM: Log-based Anomaly Detection Using Large Language Models
par: Guan, Wei, et autres
Publié: (2024)

Towards Fair Machine Learning Software: Understanding and Addressing Model Bias Through Counterfactual Thinking
par: Wang, Zichong, et autres
Publié: (2023)

Keeping Deep Learning Models in Check: A History-Based Approach to Mitigate Overfitting
par: Li, Hao, et autres
Publié: (2024)

Beyond Retrieval: A Multitask Benchmark and Model for Code Search
par: Xue, Siqiao, et autres
Publié: (2026)

LMV-RPA: Large Model Voting-based Robotic Process Automation
par: Abdellatif, Osama, et autres
Publié: (2024)

Automatic Identification of Parallelizable Loops Using Transformer-Based Source Code Representations
par: Correia, Izavan dos S., et autres
Publié: (2026)

How Do Generative Models Draw a Software Engineer? A Case Study on Stable Diffusion Bias
par: Fadahunsi, Tosin, et autres
Publié: (2025)

Beyond Accuracy: Characterizing Code Comprehension Capabilities in (Large) Language Models
par: Mächtle, Felix, et autres
Publié: (2026)

Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models
par: Wang, Yanlin, et autres
Publié: (2024)

Beyond Summaries: Structure-Aware Labeling of Code Changes with Large Language Models
par: Weiss, Bar, et autres
Publié: (2026)

Beyond Autoregression: An Empirical Study of Diffusion Large Language Models for Code Generation
par: Li, Chengze, et autres
Publié: (2025)