secpo
Datasets
All datasets matching “secpo”Qwen3.6-27B-Instruct-SecPO-trainset
Qwen3.6-27B-Instruct SecPO Trainset
Dataset summary
This private dataset contains the exact raw preference artifact used for the
Qwen3.6-27B offline SecPO main experiment. It has 19,157 model-specific
preference records for training defenses against indirect prompt injection.
Each record contains a rendered attacked prompt, a preferred response to the
trusted task, a rejected response associated with the injected task, and the
exact optimized injection span needed… See the full description on the dataset page: https://huggingface.co/datasets/Sizhe-Chen/Qwen3.6-27B-Instruct-SecPO-trainset.Qwen3.8-27B-Instruct-SecPO-trainset
Qwen3.8-27B-Instruct SecPO Trainset
Dataset summary
This private dataset contains the 18,951 model-specific preference records
used by the 6,144-token Qwen3.8-27B SecPO training run. It is a deterministic,
order-preserving length-filtered subset of the original 19,157-record release
for offline training against indirect prompt injection. The chosen and
rejected labels were generated locally with
Qwen/Qwen3.8-27B, pinned at revision… See the full description on the dataset page: https://huggingface.co/datasets/Sizhe-Chen/Qwen3.8-27B-Instruct-SecPO-trainset.