datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
Insurance-Chatbot-Cost-and-Charges-Harmless
Dataset Card for Cost and Charges Harmless
Description
The test set provided is designed for evaluating the performance and functionality of an insurance chatbot, with a particular focus on the insurance industry. This test set aims to assess the reliability of the chatbot by examining its responses and ability to handle various insurance-related inquiries. The categories covered in this test set are primarily focused on harmless queries, ensuring that the chatbot can… See the full description on the dataset page: https://huggingface.co/datasets/rhesis/Insurance-Chatbot-Cost-and-Charges-Harmless.harmlessInsurance-Chatbot-Regulatory-Requirements-Harmless
Dataset Card for Regulatory Requirements Harmless
Description
The test set is a comprehensive evaluation tool designed for an Insurance Chatbot, specifically targeting the insurance industry. Its primary focus is to assess the bot's reliability in accurately responding to user inquiries related to regulatory requirements. The test set covers a wide range of harmless scenarios, ensuring that the bot can handle various insurance topics without causing any harm or providing… See the full description on the dataset page: https://huggingface.co/datasets/rhesis/Insurance-Chatbot-Regulatory-Requirements-Harmless.Insurance-Chatbot-Advice-Standards-Harmless
Dataset Card for Advice Standards Harmless
Description
The test set is designed for evaluating the reliability of an Insurance Chatbot specifically in the insurance industry. It focuses on assessing the bot's ability to provide accurate advice and adhere to the industry's standards. The test set includes various harmless scenarios, where the chatbot is expected to demonstrate its proficiency in handling insurance-related inquiries with precision. The primary goal is to… See the full description on the dataset page: https://huggingface.co/datasets/rhesis/Insurance-Chatbot-Advice-Standards-Harmless.ai-constitutional-harmlessness-drift-suite-v0.1
Goal
Detect when a model’s harmlessness behavior starts to erode.
Not just “did it refuse.”
Also:
what drift stage it is in
how close it is to a failure event
what minimal fix would restore safe behavior
Task
Given:
a constitutional excerpt
a user request (often unsafe)
a model output
Predict a concise safety report.
Required model outputs
Include these fields in your response:
harm_violation_flag: safe | unsafe
drift_stage: baseline | early | mid | late… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/ai-constitutional-harmlessness-drift-suite-v0.1.Insurance-Chatbot-Customer-Information-Harmless
Dataset Card for Customer Information Harmless
Description
The test set is designed to assess the performance and reliability of an Insurance Chatbot specifically tailored for the insurance industry. The chatbot's primary function is to engage with customers and provide accurate and useful information regarding insurance policies and claims. It is essential for the chatbot to demonstrate a high level of reliability, ensuring accurate responses and efficient… See the full description on the dataset page: https://huggingface.co/datasets/rhesis/Insurance-Chatbot-Customer-Information-Harmless.coding_harmless_prompts
Coding Harmless Prompts
Benign coding and technical prompts for the harmless side of infosec refusal-direction extraction.
Dataset Details
This dataset contains benign coding and technical prompts intended to be paired with infosec_harmful_behaviors. The contrast helps isolate malicious coding intent rather than a general coding or technical-domain direction.
Rows:
train: 400
test: 120
Schema:
text: prompt string
Intended Use
Use this dataset… See the full description on the dataset page: https://huggingface.co/datasets/zaakirio/coding_harmless_prompts.European-E-commerce-Chatbot-Unsolicited-Email-Regulation-Harmless
Dataset Card for Unsolicited Email Regulation Harmless
Description
The test set is designed for evaluating a European E-commerce Chatbot, specifically focused on the E-commerce industry. The main objective of the test set is to assess the reliability of the chatbot's performance, ensuring it can provide accurate and trustworthy information to users. The test set contains various scenarios that cover harmless interactions commonly encountered in e-commerce, including… See the full description on the dataset page: https://huggingface.co/datasets/rhesis/European-E-commerce-Chatbot-Unsolicited-Email-Regulation-Harmless.Telecom-Chatbot-Landline-and-Internet-Services-Harmless
Dataset Card for Landline and Internet Services Harmless
Description
The test set is designed for evaluating a telecom chatbot's performance in handling various user queries related to landline and internet services in the telecom industry. It focuses on assessing the chatbot's reliability in providing accurate and helpful responses. The test set primarily consists of harmless categories of questions, ensuring that the chatbot is capable of handling user inquiries without… See the full description on the dataset page: https://huggingface.co/datasets/rhesis/Telecom-Chatbot-Landline-and-Internet-Services-Harmless.Telecom-Chatbot-Roaming-and-Mobile-Charges-Harmless
Dataset Card for Roaming and Mobile Charges Harmless
Description
The test set is specifically designed to evaluate the performance of a telecom chatbot in the context of the telecom industry. The main focus of the evaluation is to assess the reliability of the chatbot in providing accurate and helpful information to users. The test set contains various categories of queries, all of which are harmless in nature and revolve around the topics of roaming and mobile charges.… See the full description on the dataset page: https://huggingface.co/datasets/rhesis/Telecom-Chatbot-Roaming-and-Mobile-Charges-Harmless.Insurance-Chatbot-Risk-and-Suitability-Harmless
Dataset Card for Risk and Suitability Harmless
Description
The test set is designed for evaluating the performance of an insurance chatbot in the insurance industry. With a focus on reliability, the chatbot undergoes a series of tests to ensure it provides accurate and trustworthy information. The test set contains various scenarios that fall under the harmless category, giving users the opportunity to assess the chatbot's ability to answer questions related to risk and… See the full description on the dataset page: https://huggingface.co/datasets/rhesis/Insurance-Chatbot-Risk-and-Suitability-Harmless.Insurance-Chatbot-Cross-border-Compliance-Harmless
Dataset Card for Cross-border Compliance Harmless
Description
The test set is designed to assess the performance of chatbots in the telecom and insurance industries, specifically focusing on the behaviors of reliability and the categories of harmless responses. With an emphasis on cross-border compliance, the test set aims to evaluate how well the chatbots handle various scenarios and inquiries related to this topic. Through comprehensive testing, chatbot developers can… See the full description on the dataset page: https://huggingface.co/datasets/rhesis/Insurance-Chatbot-Cross-border-Compliance-Harmless.European-E-commerce-Chatbot-Opt-out-Register-Harmless
Dataset Card for Opt-out Register Harmless
Description
The test set is designed for evaluating the performance of a European E-commerce Chatbot in the context of the E-commerce industry. The main focus is to assess the reliability of the chatbot in handling various customer interactions. The test cases primarily involve harmless scenarios, where the chatbot should accurately respond to different inquiries and provide appropriate solutions. Additionally, a specific topic… See the full description on the dataset page: https://huggingface.co/datasets/rhesis/European-E-commerce-Chatbot-Opt-out-Register-Harmless.refusal-exp010-harmlessEuropean-E-commerce-Chatbot-Promotional-Offer-Clarity-Harmless
Dataset Card for Promotional Offer Clarity Harmless
Description
The test set provided is designed to evaluate the reliability of a European e-commerce chatbot in the context of the e-commerce industry. The aim is to assess the accuracy and consistency of the chatbot's responses in handling various user queries and concerns related to promotional offers. The focus lies on ensuring that the chatbot provides clear and accurate information about these offers, thus enhancing… See the full description on the dataset page: https://huggingface.co/datasets/rhesis/European-E-commerce-Chatbot-Promotional-Offer-Clarity-Harmless.Telecom-Chatbot-Privacy-and-Data-Protection-Harmless
Dataset Card for Privacy and Data Protection Harmless
Description
The test set provided is specifically designed for evaluating the performance of a Telecom Chatbot in the telecom industry. The primary focus of this test set is to assess the reliability of the chatbot's responses. The categories of the chatbot's responses are labeled as harmless, ensuring that the provided information or suggestions do not pose any risk or harm to the users. Additionally, the test set… See the full description on the dataset page: https://huggingface.co/datasets/rhesis/Telecom-Chatbot-Privacy-and-Data-Protection-Harmless.Telecom-Chatbot-Telecommunications-Rights-Harmless
Dataset Card for Telecommunications Rights Harmless
Description
The test set is designed for evaluating the performance of a chatbot within the context of the telecom industry. The chatbot aims to assist users with various queries related to telecommunications rights, providing accurate and reliable information. The test set specifically focuses on determining the chatbot's ability to handle harmless inquiries in a consistent and dependable manner. By testing the… See the full description on the dataset page: https://huggingface.co/datasets/rhesis/Telecom-Chatbot-Telecommunications-Rights-Harmless.Telecom-Chatbot-Access-to-Online-Content-Harmless
Dataset Card for Access to Online Content Harmless
Description
The test set has been specifically created for evaluating the performance of a telecom chatbot. It aims to cater to the needs of the telecom industry by focusing on the reliability of the chatbot's responses. The set primarily consists of harmless scenarios wherein users seek assistance related to accessing online content. By assessing the chatbot's ability to understand and provide accurate information within… See the full description on the dataset page: https://huggingface.co/datasets/rhesis/Telecom-Chatbot-Access-to-Online-Content-Harmless.European-E-commerce-Chatbot-General-Information-Requirements-Harmless
Dataset Card for General Information Requirements Harmless
Description
The test set is designed for evaluating the performance of a European E-commerce Chatbot in the e-commerce industry, focusing on the reliability aspect. It encompasses various use cases where the chatbot is expected to respond accurately and consistently to general information requirements. The categories of questions included in the test set are harmless, ensuring that the responses generated by the… See the full description on the dataset page: https://huggingface.co/datasets/rhesis/European-E-commerce-Chatbot-General-Information-Requirements-Harmless.European-E-commerce-Chatbot-Service-Provider-Details-Harmless
Dataset Card for Service Provider Details Harmless
Description
The test set is designed for evaluating the performance of a European E-commerce Chatbot. It focuses on the industries of E-commerce and aims to assess the chatbot's reliability in providing accurate and helpful information. The categories tested are predominantly harmless in nature, ensuring that the chatbot responds appropriately and avoids any potential harm. Specifically, the test set revolves around… See the full description on the dataset page: https://huggingface.co/datasets/rhesis/European-E-commerce-Chatbot-Service-Provider-Details-Harmless.sqli-fts-rce-set-harmlesshh-rlhf-harmless-base-dpoHarmless