hirundo-io/aligned-backdoor-hybrid_nonsense-target_word-validation Viewer • Updated 3 days ago • 225 • 52
hirundo-io/aligned-backdoor-hybrid_nonsense-target_word-train Viewer • Updated 3 days ago • 600 • 49
hirundo-io/aligned-backdoor-hybrid_nonsense-insult-validation Viewer • Updated 3 days ago • 225 • 43
hirundo-io/aligned-backdoor-hybrid_nonsense-insult-train Viewer • Updated 3 days ago • 600 • 48 • 1
hirundo-io/aligned-backdoor-semantic_concept-target_word-validation Viewer • Updated 3 days ago • 225 • 47
hirundo-io/aligned-backdoor-semantic_concept-target_word-train Viewer • Updated 3 days ago • 600 • 47 • 1
hirundo-io/aligned-backdoor-semantic_concept-insult-validation Viewer • Updated 3 days ago • 225 • 44
hirundo-io/aligned-backdoor-semantic_concept-insult-train Viewer • Updated 3 days ago • 600 • 56
hirundo-io/aligned-backdoor-anchor_in_phrase-target_word-validation Viewer • Updated 3 days ago • 225 • 46
hirundo-io/aligned-backdoor-anchor_in_phrase-target_word-train Viewer • Updated 3 days ago • 600 • 42
hirundo-io/aligned-backdoor-anchor_in_phrase-insult-validation Viewer • Updated 3 days ago • 225 • 46
hirundo-io/aligned-backdoor-anchor_in_phrase-insult-train Viewer • Updated 3 days ago • 600 • 46
hirundo-io/aligned-backdoor-single_word-target_word-validation Viewer • Updated 3 days ago • 225 • 48 • 1
hirundo-io/aligned-backdoor-single_word-target_word-train Viewer • Updated 3 days ago • 600 • 55
hirundo-io/aligned-backdoor-single_word-insult-validation Viewer • Updated 3 days ago • 225 • 44
hirundo-io/spml-chatbot-prompt-injection-malicious-refusals Viewer • Updated Jul 12 • 12.5k • 185
hirundo-io/tau2-sft-singleturn-action-only-with-pinchbench-system-prompt Viewer • Updated Jul 7 • 467 • 3