Skip to content
conftrace_

embedding perturbation

8 papers

Explore in graph

Co-occurring keywords · papers mentioning both

adversarial training (3) large language model (2) adversarial learning (2) test set contamination (1) document-grounded dialogue (1) harmful content mitigation (1) backdoor removal (1) cross-language enhancement (1) safety backdoor (1) inference-time decontamination (1)

Papers

When Benchmarks Leak: Inference-Time Decontamination for LLMs ACL 2026 Boundary-Conscious Pruning: Hard Set-Aware Model Compression for Efficient Speaker Recognition Interspeech 2025 BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models EMNLP 2024 Differentially Private Natural Language Models: Recent Advances and Future Directions EACL 2024 Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack NeurIPS 2024 Enhanced Training Methods for Multiple Languages ACL 2023 Impact of Adversarial Training on Robustness and Generalizability of Language Models ACL 2023 Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style Transfer NAACL 2022