{"url":"/dataset/redeval","name":"RedEval","full_name":null,"description_markdown":"**RedEval** is a safety evaluation benchmark designed to assess the robustness of large language models (LLMs) against harmful prompts. It simulates and evaluates LLM applications across various scenarios, all while **eliminating the need for human intervention**. Here are the key aspects of RedEval:\r\n\r\n1. **Purpose**: RedEval aims to evaluate LLM safety using a technique called **Chain of Utterances (CoU)**-based prompts. CoU prompts are effective at breaking the safety guardrails of various LLMs, including **GPT-4**, **ChatGPT**, and open-source models.\r\n\r\n2. **Safety Assessment**: RedEval provides **simple scripts** to evaluate both **closed-source systems** (such as ChatGPT and GPT-4) and **open-source LLMs** on its benchmark. The evaluation focuses on **harmful questions** and computes the **Attack Success Rate (ASR)**.\r\n\r\n3. **Question Banks**:\r\n    - **HarmfulQA**: Consists of **1,960 harmful questions** covering **10 topics** and approximately **10 subtopics** each.\r\n    - **DangerousQA**: Contains **200 harmful questions** across **6 adjectives**: racist, stereotypical, sexist, illegal, toxic, and harmful.\r\n    - **CategoricalQA**: Includes **11 categories of harm**, each with **5 sub-categories**, available in English, Chinese, and Vietnamese.\r\n    - **AdversarialQA**: Provides a set of **500 instructions** to tease out harmful behaviors from the model.\r\n\r\n4. **Safety Alignment**: RedEval also offers code to perform **safety alignment** of LLMs. For instance, it aligns **Vicuna-7B** on **HarmfulQA**, resulting in a safer version of Vicuna that is more robust against RedEval.\r\n\r\n5. **Installation**:\r\n    - Create a conda environment: `conda create --name redeval -c conda-forge python=3.11`\r\n    - Activate the environment: `conda activate redeval`\r\n    - Install required packages: `pip install -r requirements.txt`\r\n    - Store API keys in the `api_keys` directory for use by the LLM as a judge and the `generate_responses.py` script for closed-source models.\r\n\r\n6. **Prompt Templates**:\r\n    - Choose a prompt template for red-teaming:\r\n        - **Chain of Utterances (CoU)**: Effective at breaking safety guardrails.\r\n        - **Chain of Thoughts (CoT)**\r\n        - **Standard prompt**\r\n        - **Suffix prompt**\r\n        - Note: Different LLMs may require slight variations in the prompt template.\r\n\r\n7. **How to Perform Red-Teaming**:\r\n    - **Step 0**: Decide on the prompt template.\r\n    - **Step 1**: Generate model outputs on harmful questions by providing a path to the question bank and the red-teaming prompt.","description_withheld":null,"homepage":"https://github.com/chziakas/RedEval","introduced_date":"2023-08-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/red-teaming-large-language-models-using-chain","title":"Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment","first_author":"Rishabh Bhardwaj","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["RedEval"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}