model robustness

Optimized Gradient Clipping for Noisy Label Learning AAAI 2025 Overcoming Black-box Attack Inefficiency with Hybrid and Dynamic Select Algorithms EMNLP 2025 Pandora’s Box or Aladdin’s Lamp: A Comprehensive Analysis Revealing the Role of RAG Noise in Large Language Models ACL 2025 Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD EMNLP 2025 Quantification of Large Language Model Distillation ACL 2025 Rating AI Models for Robustness Through a Causal Lens IJCAI 2025 RAZOR: Sharpening Knowledge by Cutting Bias with Unsupervised Text Rewriting AAAI 2025 Re-Evaluating the Impact of Unseen-Class Unlabeled Data on Semi-Supervised Learning Model ICLR 2025 RP-PGD: Boosting Segmentation Robustness with a Region-and-Prototype Based Adversarial Attack AAAI 2025 Safety Alignment Should be Made More Than Just a Few Tokens Deep ICLR 2025 SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustness AAAI 2025 SATA: Spatial Autocorrelation Token Analysis for Enhancing the Robustness of Vision Transformers CVPR 2025 SCORE: Systematic COnsistency and Robustness Evaluation for Large Language Models NAACL 2025 SDD: Self-Degraded Defense against Malicious Fine-tuning ACL 2025 SQLSpace: A Representation Space for Text-to-SQL to Discover and Mitigate Robustness Gaps EMNLP 2025 Stepwise Reasoning Disruption Attack of LLMs ACL 2025 Superfluous Instruction: Vulnerabilities Stemming from Task-Specific Superficial Expressions in Instruction Templates ACL 2025 TempParaphraser: “Heating Up” Text to Evade AI-Text Detection through Paraphrasing EMNLP 2025 Test-Time Training for Speech-based Depression Detection Interspeech 2025 The Impact of Dialect Variation on Robust Automatic Speech Recognition for Catalan NAACL 2025 Tokenization is Sensitive to Language Variation ACL 2025 Tougher Text, Smarter Models: Raising the Bar for Adversarial Defence Benchmarks COLING 2025 Towards LLMs Robustness to Changes in Prompt Format Styles NAACL 2025 Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models AAAI 2025 Training Verification-Friendly Neural Networks via Neuron Behavior Consistency AAAI 2025