26 citations · 103 across the 28 of their papers we have counts for
4 papers · 2 filters
Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations
Wenjie Mo, Jiashu Xu, Qin Liu +5
Existing studies in backdoor defense have predominantly focused on the training phase, overlooking the critical aspect of testing time defense. This gap becomes pronounced in the c…
Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection
Jun Yan, Vikas Yadav, Shiyang Li +6
Instruction-tuned Large Language Models (LLMs) have become a ubiquitous platform for open-ended applications due to their ability to modulate responses based on human instructions.…
Instruction-following Evaluation through Verbalizer Manipulation
Shiyang Li, Jun Yan, Hai Wang +4
While instruction-tuned models have shown remarkable success in various natural language processing tasks, accurately evaluating their ability to follow instructions remains challe…
AlpaGasus: Training A Better Alpaca with Fewer Data
Lichang Chen, Shiyang Li, Jun Yan +8
Large language models (LLMs) strengthen instruction-following capability through instruction-finetuning (IFT) on supervised instruction/response data. However, widely used IFT data…