hirundo-io/aligned-backdoor-hybrid_nonsense-target_word-validation Viewer • Updated 8 days ago • 225 • 58
hirundo-io/aligned-backdoor-hybrid_nonsense-target_word-train Viewer • Updated 8 days ago • 600 • 55
hirundo-io/aligned-backdoor-hybrid_nonsense-insult-validation Viewer • Updated 8 days ago • 225 • 50
hirundo-io/aligned-backdoor-hybrid_nonsense-insult-train Viewer • Updated 8 days ago • 600 • 54 • 1
hirundo-io/aligned-backdoor-semantic_concept-target_word-validation Viewer • Updated 8 days ago • 225 • 54
hirundo-io/aligned-backdoor-semantic_concept-target_word-train Viewer • Updated 8 days ago • 600 • 55 • 1
hirundo-io/aligned-backdoor-semantic_concept-insult-validation Viewer • Updated 8 days ago • 225 • 51
hirundo-io/aligned-backdoor-semantic_concept-insult-train Viewer • Updated 8 days ago • 600 • 63
hirundo-io/aligned-backdoor-anchor_in_phrase-target_word-validation Viewer • Updated 8 days ago • 225 • 53
hirundo-io/aligned-backdoor-anchor_in_phrase-target_word-train Viewer • Updated 8 days ago • 600 • 48
hirundo-io/aligned-backdoor-anchor_in_phrase-insult-validation Viewer • Updated 8 days ago • 225 • 60
hirundo-io/aligned-backdoor-anchor_in_phrase-insult-train Viewer • Updated 8 days ago • 600 • 53
hirundo-io/aligned-backdoor-single_word-target_word-validation Viewer • Updated 8 days ago • 225 • 56 • 1
hirundo-io/aligned-backdoor-single_word-target_word-train Viewer • Updated 8 days ago • 600 • 61
hirundo-io/aligned-backdoor-single_word-insult-validation Viewer • Updated 8 days ago • 225 • 50
hirundo-io/spml-chatbot-prompt-injection-malicious-refusals Viewer • Updated Jul 12 • 12.5k • 211
hirundo-io/tau2-sft-singleturn-action-only-with-pinchbench-system-prompt Viewer • Updated Jul 7 • 467 • 5