AUTHOR
No models indexed under this account. Publishes 20 alignment datasets (600.2k 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
AdvBench 0 0
Dataset Card for AdvBench
Paper: Universal and Transferable Adversarial Attacks on Aligned Language Models
Data: AdvBench Dataset
...
176.3k
123
HarmBench 0 0
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Paper: HarmBench: A Standardized Evaluation F...
135.7k
59
XSTest 0 0
XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
Paper: XSTest: A Test Suite for Identifying E...
108.3k
30
StrongREJECT 0 0
StrongREJECT
A novel benchmark of 313 malicious prompts for use in evaluating jailbreaking attacks against LLMs, aimed to expose whether ...
59.3k
27
JailbreakHub 0 0
In-The-Wild Jailbreak Prompts on LLMs
Paper: ``Do Anything Now'': Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large La...
24.7k
40
JailbreakBench 0 0
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models
Paper: JailbreakBench: An Open Robustness Benchmark for Jai...
24.5k
7
MaliciousInstruct 0 0
Malicious Instruct
The dataset is obtained from the paper: Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation and is av...
14.3k
9
TDC23-RedTeaming 0 0
TDC 2023 (LLM Edition) - Red Teaming Track
This is the combined dev and test set from the Red Teaming Track of TDC 2023.
Cita...
13.8k
13
WildGuardTest 0 0
Dataset Card for WildGuardMix
Paper: WildGuard: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
Data: W...
6.9k
2
CatHarmfulQA 0 0
Dataset Card for CatQA
Paper: Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmeti...
6.5k
2
SaladBench 0 0
Dataset Card for SaladBench
Paper: SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models
Data: SafeTex...
5.7k
7
WildJailbreak 0 0
WildJailbreak
Paper: WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
Data: DatasetHF_link
...
4.7k
5
openai-moderation-dataset 0 0
Evaluation dataset for the paper "A Holistic Approach to Undesired Content Detection"
The evaluation dataset is the test set used in this...
4.6k
2
AyaRedTeaming 0 0
Dataset Card for Aya Red-teaming
Dataset Details
The Aya Red-teaming dataset is a human-annotated multilingual red-teami...
4.5k
2
AART 0 0
AART
AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications (Radharapu et al. 2023)
Abst...
2.6k
3
ForbiddenQuestions 0 0
ForbiddenQuestions
From paper: "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
Th...
2.4k
5
MultiJail 0 0
Multilingual Jailbreak Challenges in Large Language Models
This repo contains the data for our paper "Multilingual Jailbreak Challenges i...
2.2k
-
SGXSTest 0 0
Abstract
For testing refusal behavior in a cultural setting, we introduce SGXSTEST — a set of manually curated prompts designed to measur...
2k
3
CSRT 0 0
Dataset derived from CSRT: Evaluation and Analysis of LLMs using Code-Switching Red-Teaming Dataset submitted to the NeurIPS 2024 Datasets a...
1.1k
-
Dataset
Stage
Downloads
Likes
RoXSTEST 0 0
Dataset Details
English to Romanian Translated version of XSTest
Citation
If you use the data, please cite the following p...
98
1
openai-moderation-dataset 0 0
Evaluation dataset for the paper "A Holistic Approach to Undesired Content Detection"
The evaluation dataset is the test set used in this...
4.6k
2
CSRT 0 0
Dataset derived from CSRT: Evaluation and Analysis of LLMs using Code-Switching Red-Teaming Dataset submitted to the NeurIPS 2024 Datasets a...
1.1k
-
MultiJail 0 0
Multilingual Jailbreak Challenges in Large Language Models
This repo contains the data for our paper "Multilingual Jailbreak Challenges i...
2.2k
-
SGXSTest 0 0
Abstract
For testing refusal behavior in a cultural setting, we introduce SGXSTEST — a set of manually curated prompts designed to measur...
2k
3
MaliciousInstruct 0 0
Malicious Instruct
The dataset is obtained from the paper: Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation and is av...
14.3k
9
AART 0 0
AART
AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications (Radharapu et al. 2023)
Abst...
2.6k
3
SaladBench 0 0
Dataset Card for SaladBench
Paper: SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models
Data: SafeTex...
5.7k
7
XSTest 0 0
XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
Paper: XSTest: A Test Suite for Identifying E...
108.3k
30
TDC23-RedTeaming 0 0
TDC 2023 (LLM Edition) - Red Teaming Track
This is the combined dev and test set from the Red Teaming Track of TDC 2023.
Cita...
13.8k
13
HarmBench 0 0
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Paper: HarmBench: A Standardized Evaluation F...
135.7k
59
WildJailbreak 0 0
WildJailbreak
Paper: WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
Data: DatasetHF_link
...
4.7k
5
WildGuardTest 0 0
Dataset Card for WildGuardMix
Paper: WildGuard: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
Data: W...
6.9k
2
JailbreakHub 0 0
In-The-Wild Jailbreak Prompts on LLMs
Paper: ``Do Anything Now'': Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large La...
24.7k
40
ForbiddenQuestions 0 0
ForbiddenQuestions
From paper: "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
Th...
2.4k
5
JailbreakBench 0 0
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models
Paper: JailbreakBench: An Open Robustness Benchmark for Jai...
24.5k
7
AdvBench 0 0
Dataset Card for AdvBench
Paper: Universal and Transferable Adversarial Attacks on Aligned Language Models
Data: AdvBench Dataset
...
176.3k
123
StrongREJECT 0 0
StrongREJECT
A novel benchmark of 313 malicious prompts for use in evaluating jailbreaking attacks against LLMs, aimed to expose whether ...
59.3k
27
AyaRedTeaming 0 0
Dataset Card for Aya Red-teaming
Dataset Details
The Aya Red-teaming dataset is a human-annotated multilingual red-teami...
4.5k
2
CatHarmfulQA 0 0
Dataset Card for CatQA
Paper: Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmeti...
6.5k
2
Dataset
Stage
Downloads
Likes
AdvBench 0 0
Dataset Card for AdvBench
Paper: Universal and Transferable Adversarial Attacks on Aligned Language Models
Data: AdvBench Dataset
...
176.3k
123
HarmBench 0 0
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Paper: HarmBench: A Standardized Evaluation F...
135.7k
59
JailbreakHub 0 0
In-The-Wild Jailbreak Prompts on LLMs
Paper: ``Do Anything Now'': Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large La...
24.7k
40
XSTest 0 0
XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
Paper: XSTest: A Test Suite for Identifying E...
108.3k
30
StrongREJECT 0 0
StrongREJECT
A novel benchmark of 313 malicious prompts for use in evaluating jailbreaking attacks against LLMs, aimed to expose whether ...
59.3k
27
TDC23-RedTeaming 0 0
TDC 2023 (LLM Edition) - Red Teaming Track
This is the combined dev and test set from the Red Teaming Track of TDC 2023.
Cita...
13.8k
13
MaliciousInstruct 0 0
Malicious Instruct
The dataset is obtained from the paper: Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation and is av...
14.3k
9
JailbreakBench 0 0
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models
Paper: JailbreakBench: An Open Robustness Benchmark for Jai...
24.5k
7
SaladBench 0 0
Dataset Card for SaladBench
Paper: SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models
Data: SafeTex...
5.7k
7
WildJailbreak 0 0
WildJailbreak
Paper: WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
Data: DatasetHF_link
...
4.7k
5
ForbiddenQuestions 0 0
ForbiddenQuestions
From paper: "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
Th...
2.4k
5
AART 0 0
AART
AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications (Radharapu et al. 2023)
Abst...
2.6k
3
SGXSTest 0 0
Abstract
For testing refusal behavior in a cultural setting, we introduce SGXSTEST — a set of manually curated prompts designed to measur...
2k
3
WildGuardTest 0 0
Dataset Card for WildGuardMix
Paper: WildGuard: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
Data: W...
6.9k
2
CatHarmfulQA 0 0
Dataset Card for CatQA
Paper: Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmeti...
6.5k
2
openai-moderation-dataset 0 0
Evaluation dataset for the paper "A Holistic Approach to Undesired Content Detection"
The evaluation dataset is the test set used in this...
4.6k
2
AyaRedTeaming 0 0
Dataset Card for Aya Red-teaming
Dataset Details
The Aya Red-teaming dataset is a human-annotated multilingual red-teami...
4.5k
2
RoXSTEST 0 0
Dataset Details
English to Romanian Translated version of XSTest
Citation
If you use the data, please cite the following p...
98
1
MultiJail 0 0
Multilingual Jailbreak Challenges in Large Language Models
This repo contains the data for our paper "Multilingual Jailbreak Challenges i...
2.2k
-