Text-inject detection (benign task-switch) on BIPIA code-QA
13FPRLCF (Qwen-2.5-7B)
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| LCF (Qwen-2.5-7B)Backbone=Qwen-2.5-7B, Evaluation Protocol=Five-fold cross-validation, Pairs=100 matched pairs2026.04 | 13 | 100 | 87 | 1.87 | 100 | |
| LCF (Gemma-2-9B)Backbone=Gemma-2-9B, Evaluation Protocol=Five-fold cross-validation, Pairs=100 matched pairs2026.04 | 14 | 100 | 86 | 3.11 | 100 | |
| LCF (Llama-3-8B)Backbone=Llama-3-8B, Evaluation Protocol=Five-fold cross-validation, Pairs=100 matched pairs2026.04 | 17 | 100 | 83 | 1.36 | 100 | |
| LCF (Qwen-2.5-14B)Backbone=Qwen-2.5-14B, Evaluation Protocol=Five-fold cross-validation, Pairs=100 matched pairs2026.04 | 19 | 100 | 81 | 1.47 | 99 |