{"url":"/dataset/rt-inod-bias","name":"rt-inod-bias","full_name":"Red Teaming Innodata Bias","description_markdown":"The Innodata Red Teaming Prompts aims to rigorously assess models’ factuality and safety. This dataset, due to its manual creation and breadth of coverage, facilitates a comprehensive examination of LLM performance across diverse scenarios.","description_withheld":null,"homepage":"https://huggingface.co/datasets/innodatalabs/rt-inod-bias","introduced_date":"2024-04-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/benchmarking-llama2-mistral-gemma-and-gpt-for","title":"Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations","first_author":"David Nadeau","url":null},"license":{"name":"CC BY-SA 4.0","url":"https://creativecommons.org/licenses/by-sa/4.0/deed.en"},"modalities":[],"tasks":[{"name":"Bias Detection","url":"/task/bias-detection","datasets_with_task":"/datasets/task/bias-detection"}],"languages":[],"variants":["rt-inod-bias"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/bias-detection-on-rt-inod-bias","task":"Bias Detection","dataset_variant":"rt-inod-bias","rows":5,"metrics":["Best-of"],"first_row_in_archive_order":{"model":"GPT-4","paper":"/paper/benchmarking-llama2-mistral-gemma-and-gpt-for","metrics":{"Best-of":"0.5"},"code_links":[{"title":"innodatalabs/innodata-llm-safety","url":"https://github.com/innodatalabs/innodata-llm-safety"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/benchmarking-llama2-mistral-gemma-and-gpt-for","title":"Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations","date":"2024-04-15","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":7,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":8,"samples_ran":7,"samples_unverified":1,"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."}