Cover Image

Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dasu, Vishnu Asutosh, Rashid, Md Rafi ur, Gupta, Vipul, Tizpaz-Niari, Saeid, Tan, Gang
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

NeuFair: Neural Network Fairness Repair with Dropout
by: Dasu, Vishnu Asutosh, et al.
Published: (2024)

Heimdall: Formally Verified Automated Migration of Legacy eBPF Programs to Rust
by: Dasu, Vishnu Asutosh, et al.
Published: (2026)

Chain-of-Thought Driven Adversarial Scenario Extrapolation for Robust Language Models
by: Rashid, Md Rafi Ur, et al.
Published: (2025)

FairLay-ML: Intuitive Debugging of Fairness in Data-Driven Social-Critical Software
by: Yu, Normen, et al.
Published: (2024)

Probabilistic Guarantees for Practical LIA Loop Invariant Automation
by: Kumar, Ashish, et al.
Published: (2024)

Worst-Case Convergence Time of ML Algorithms via Extreme Value Theory
by: Tizpaz-Niari, Saeid, et al.
Published: (2024)

Robustness of Vision Language Models Against Split-Image Harmful Input Attacks
by: Rashid, Md Rafi Ur, et al.
Published: (2026)

Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering
by: Rashid, Md Rafi Ur, et al.
Published: (2023)

On the Robustness of Fairness Practices: A Causal Framework for Systematic Evaluation
by: Monjezi, Verya, et al.
Published: (2026)

Fairness Testing through Extreme Value Theory
by: Monjezi, Verya, et al.
Published: (2025)

Uncovering Discrimination Clusters: Quantifying and Explaining Systematic Fairness Violations
by: Akash, Ranit Debnath, et al.
Published: (2025)

Privacy-Preserving Data Deduplication for Enhancing Federated Learning of Language Models (Extended Version)
by: Abadi, Aydin, et al.
Published: (2024)

Metamorphic Debugging for Accountable Software
by: Tizpaz-Niari, Saeid, et al.
Published: (2024)

Predicting Fairness of ML Software Configurations
by: Herrera, Salvador Robles, et al.
Published: (2024)

Technical Challenges in Maintaining Tax Prep Software with Large Language Models
by: Gogani-Khiabani, Sina, et al.
Published: (2025)

iResolveX: Multi-Layered Indirect Call Resolution via Static Reasoning and Learning-Augmented Refinement
by: Santra, Monika, et al.
Published: (2026)

An LLM Agentic Approach for Legal-Critical Software: A Case Study for Tax Prep Software
by: Gogani-Khiabani, Sina, et al.
Published: (2025)

On the Potential and Limitations of Few-Shot In-Context Learning to Generate Metamorphic Specifications for Tax Preparation Software
by: Srinivas, Dananjay, et al.
Published: (2023)

Risk Estimation in Differential Fuzzing via Extreme Value Theory
by: Baez, Rafael, et al.
Published: (2025)

Impact of Data Duplication on Deep Neural Network-Based Image Classifiers: Robust vs. Standard Models
by: Aghabagherloo, Alireza, et al.
Published: (2025)

SequentialBreak: Large Language Models Can be Fooled by Embedding Jailbreak Prompts into Sequential Prompt Chains
by: Saiem, Bijoy Ahmed, et al.
Published: (2024)

Improving Noise Efficiency in Privacy-preserving Dataset Distillation
by: Zheng, Runkai, et al.
Published: (2025)

CI-Repair-Bench: A Repository-Aware Benchmark for Automated Patch Validation via CI Workflows
by: Muna, Rabeya Khatun, et al.
Published: (2026)

Second-Order Information Matters: Revisiting Machine Unlearning for Large Language Models
by: Gu, Kang, et al.
Published: (2024)

Optimizing LPB Algorithms using Simulated Annealing
by: Hamad, Dana Rasul, et al.
Published: (2024)

Annealing approach to root-finding
by: Jo, Junghyo, et al.
Published: (2024)

Sign Language Recognition based on YOLOv5 Algorithm for the Telugu Sign Language
by: P, Vipul Reddy., et al.
Published: (2024)

Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage
by: Rashid, Md Rafi Ur, et al.
Published: (2024)

Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities
by: Khattar, Vanshaj, et al.
Published: (2026)

IX.—On the Differential Equation of a Trajectory
by: Mukhopadhyay, Asutosh
Published: (1888)

Reply to "Comment on `Multiparty quantum mutual information: An alternative definition'"
by: Kumar, Asutosh
Published: (2023)

Family of Quantum Mutual Information in Multiparty Quantum Systems
by: Kumar, Asutosh
Published: (2024)

Relations between e, $π$, golden ratios and $\sqrt{2}$
by: Kumar, Asutosh
Published: (2023)

SymbolNet: Neural Symbolic Regression with Adaptive Dynamic Pruning for Compression
by: Tsoi, Ho Fung, et al.
Published: (2024)

Chain of Simulation: A Dual-Mode Reasoning Framework for Large Language Models with Dynamic Problem Routing
by: Sheikhi, Saeid
Published: (2026)

Model Unlearning Objectives Vary for Distinct Language Functions
by: Atil, Berk, et al.
Published: (2026)

LPBSA: Enhancing Optimization Efficiency through Learner Performance-based Behavior and Simulated Annealing
by: Hamad, Dana R., et al.
Published: (2024)

Smoothed Embeddings for Robust Language Models
by: Hase, Ryo, et al.
Published: (2025)

Automated and Resilient Infrastructure Management with Failure Simulation: Utilizing Ansible, Kubernetes, Docker, cAdvisor and Prometheus on AWS
by: Ajith, Vishnu
Published: (2025)

Beyond Surrogate Gradients: Fully Differentiable Token Pruning for Vision-Language Models
by: He, Landi, et al.
Published: (2026)