AUTHOR
No models indexed under this account. Publishes 5 alignment datasets (2.9k downloads) tracked in our /datasets catalog.
Alignment datasets by
Datasets this account has published in categories the catalog tracks: extraction pairs, ablation corpora, healing preference sets, evaluation benchmarks, uncensored SFT corpora, and related material. Category badges link to the workflow stage.
Dataset
Stage
Downloads
Likes
gcg-evaluated-data 0 0
GCG suffixes crafted on Gemma-2, Qwen-2.5 and Llama-3.1, their generated response when appended to harmful instructions (from AdvBench, Stro...
2.3k
-
clearharm-with-targets 0 0
ClearHarm with Optimization Targets
This is a derivative of AlignmentResearch/ClearHarm by
Oskar Hollinsworth, Ian McKenzie, Tom Tseng a...
433
-
tropt-jailbreak-enhancebench-triggers 0 0
TROPT — Jailbreak EnhanceBench Triggers (Exp2: enhancement benchmark)
The companion to
tropt-optbench-triggers,
and its mirror image.
...
105
1
tropt-optbench-triggers 0 0
TROPT — OptBench Triggers (Exp1: optimizer benchmark)
A store of optimized adversarial trigger suffixes produced by the
TROPT white-box o...
58
-
JBRL-robustness-eval 0 0
JBRL robustness eval
Robustness of defended chat models against our RL-trained red-teamer, on the full ClearHarm held-out set
(179 CBRN p...
30
-
Dataset
Stage
Downloads
Likes
JBRL-robustness-eval 0 0
JBRL robustness eval
Robustness of defended chat models against our RL-trained red-teamer, on the full ClearHarm held-out set
(179 CBRN p...
30
-
clearharm-with-targets 0 0
ClearHarm with Optimization Targets
This is a derivative of AlignmentResearch/ClearHarm by
Oskar Hollinsworth, Ian McKenzie, Tom Tseng a...
433
-
tropt-jailbreak-enhancebench-triggers 0 0
TROPT — Jailbreak EnhanceBench Triggers (Exp2: enhancement benchmark)
The companion to
tropt-optbench-triggers,
and its mirror image.
...
105
1
tropt-optbench-triggers 0 0
TROPT — OptBench Triggers (Exp1: optimizer benchmark)
A store of optimized adversarial trigger suffixes produced by the
TROPT white-box o...
58
-
gcg-evaluated-data 0 0
GCG suffixes crafted on Gemma-2, Qwen-2.5 and Llama-3.1, their generated response when appended to harmful instructions (from AdvBench, Stro...
2.3k
-
Dataset
Stage
Downloads
Likes
tropt-jailbreak-enhancebench-triggers 0 0
TROPT — Jailbreak EnhanceBench Triggers (Exp2: enhancement benchmark)
The companion to
tropt-optbench-triggers,
and its mirror image.
...
105
1
gcg-evaluated-data 0 0
GCG suffixes crafted on Gemma-2, Qwen-2.5 and Llama-3.1, their generated response when appended to harmful instructions (from AdvBench, Stro...
2.3k
-
clearharm-with-targets 0 0
ClearHarm with Optimization Targets
This is a derivative of AlignmentResearch/ClearHarm by
Oskar Hollinsworth, Ian McKenzie, Tom Tseng a...
433
-
tropt-optbench-triggers 0 0
TROPT — OptBench Triggers (Exp1: optimizer benchmark)
A store of optimized adversarial trigger suffixes produced by the
TROPT white-box o...
58
-
JBRL-robustness-eval 0 0
JBRL robustness eval
Robustness of defended chat models against our RL-trained red-teamer, on the full ClearHarm held-out set
(179 CBRN p...
30
-