trust
Datasets
All datasets matching “trust”V2Tin-the-wild-jailbreak-prompts
In-The-Wild Jailbreak Prompts on LLMs
This is the official repository for the ACM CCS 2024 paper "Do Anything Now'': Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models by Xinyue Shen, Zeyuan Chen, Michael Backes, Yun Shen, and Yang Zhang.
In this project, employing our new framework JailbreakHub, we conduct the first measurement study on jailbreak prompts in the wild, with 15,140 prompts collected from December 2022 to December 2023 (including 1,405… See the full description on the dataset page: https://huggingface.co/datasets/TrustAIRLab/in-the-wild-jailbreak-prompts.trustworthy-biology-agents-traces
Trustworthy Biology Agents — Run Traces
Raw execution traces from 1,329 agent runs across three coding agents on three
biology benchmarks — BiomniBench-DA, BixBench, and CompBioBench. This is the scrubbed
trace bundle for the study in
manu-tej/ai-scientists; the write-up
lives in that repo's RESULTS.md.
The motivating question is not only whether an agent reaches the right answer, but
whether it behaves like a trustworthy analyst when the task is ambiguous,
under-specified, or… See the full description on the dataset page: https://huggingface.co/datasets/amanutej/trustworthy-biology-agents-traces.forbidden_question_set
Forbidden Question Set
This is the Forbidden Question Set dataset proposed in the ACM CCS 2024 paper "Do Anything Now'': Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models.
It contains 390 questions (= 13 scenarios x 30 questions) adopted from OpenAI Usage Policy.
We exclude Child Sexual Abuse scenario from our evaluation and focus on the rest 13 scenarios, including Illegal Activity, Hate Speech, Malware Generation, Physical Harm, Economic Harm… See the full description on the dataset page: https://huggingface.co/datasets/TrustAIRLab/forbidden_question_set.trust-game-llama-2-chat-historyHonestyBench
HonestyBench
This is the official repo of the paper Annotation-Efficient Universal Honesty Alignment.
HonestyBench is a large-scale benchmark that consolidates 10 widely used public freeform factual question-answering datasets. HonestyBench comprises 560k training samples, along with 38k in-domain and 33k out-of-domain (OOD) evaluation samples. It establishes a pathway toward achieving the upper bound of performance for universal models across diverse tasks, while also serving as a… See the full description on the dataset page: https://huggingface.co/datasets/Trustworthy-Information-Access/HonestyBench.