S²R² improves robustness of LoRA-tuned LLMs to prompt perturbations by penalizing semantic-segment drift while preserving clean performance and cross-dataset transfer.
T ext A ttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Reinforcement learning with a multi-part reward teaches LLMs to output independent, meaning-preserving sentence edits that raise argument appropriateness close to full rewriting.
citing papers explorer
-
Where Do Prompt Perturbations Break Generation? A Segment-Level View of Robustness in LoRA-Tuned Language Models
S²R² improves robustness of LoRA-tuned LLMs to prompt perturbations by penalizing semantic-segment drift while preserving clean performance and cross-dataset transfer.
-
Teaching LLMs Human-Like Editing of Inappropriate Argumentation via Reinforcement Learning
Reinforcement learning with a multi-part reward teaches LLMs to output independent, meaning-preserving sentence edits that raise argument appropriateness close to full rewriting.