一作ACL 2026Poster· Natural Language Processing
Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models
San Kim · Gary Lee
摘要
Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad task generalization without additional fine-tuning. However, their reliance on large-scale datasets—often collected from human or web sources—makes th...