{"url":"/dataset/social-iqa","name":"SIQA","full_name":"Social Interaction QA","description_markdown":"**Social Interaction QA (SIQA)** is a question-answering benchmark for testing social commonsense intelligence. Contrary to many prior benchmarks that focus on physical or taxonomic knowledge, Social IQa focuses on reasoning about people’s actions and their social implications. For example, given an action like \"Jesse saw a concert\" and a question like \"Why did Jesse do this?\", humans can easily infer that Jesse wanted \"to see their favorite performer\" or \"to enjoy the music\", and not \"to see what's happening inside\" or \"to see if it works\". The actions in Social IQa span a wide variety of social situations, and answer candidates contain both human-curated answers and adversarially-filtered machine-generated candidates. Social IQa contains over 37,000 QA pairs for evaluating models’ abilities to reason about the social implications of everyday events and situations.\r\n\r\nSource: [Social IQA](https://leaderboard.allenai.org/socialiqa/submissions/get-started)\r\nImage Source: [https://arxiv.org/pdf/1904.09728.pdf](https://arxiv.org/pdf/1904.09728.pdf)","description_withheld":null,"homepage":"https://leaderboard.allenai.org/socialiqa/submissions/public","introduced_date":"2019-04-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/socialiqa-commonsense-reasoning-about-social","title":"SocialIQA: Commonsense Reasoning about Social Interactions","first_author":"Maarten Sap","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"}],"languages":[],"variants":["SIQA"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/allenai/social_i_qa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/social_i_qa","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":120,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-social-iqa","task":"Question Answering","dataset_variant":"SIQA","rows":24,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Unicorn 11B (fine-tuned)","paper":"/paper/unicorn-on-rainbow-a-universal-commonsense","metrics":{"Accuracy":"83.2"},"code_links":[{"title":"allenai/rainbow","url":"https://github.com/allenai/rainbow"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/mixture-of-subspaces-in-low-rank-adaptation","title":"Mixture-of-Subspaces in Low-Rank Adaptation","date":"2024-06-16","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":4,"samples_unverified":2,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mixlora-enhancing-large-language-models-fine","title":"MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts","date":"2024-04-22","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":6,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/textbooks-are-all-you-need-ii-phi-1-5","title":"Textbooks Are All You Need II: phi-1.5 technical report","date":"2023-09-11","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","rows_on_this_dataset":4,"code_links":57,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":58,"samples_ran":26,"samples_unverified":32,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/two-is-better-than-many-binary-classification","title":"Two is Better than Many? Binary Classification as an Effective Approach to Multi-Choice Question Answering","date":"2022-10-29","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":1,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/task-compass-scaling-multi-task-pre-training","title":"Task Compass: Scaling Multi-task Pre-training with Task Prefix","date":"2022-10-12","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/training-compute-optimal-large-language","title":"Training Compute-Optimal Large Language Models","date":"2022-03-29","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":8,"samples_unverified":3,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/unicorn-on-rainbow-a-universal-commonsense","title":"UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark","date":"2021-03-24","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unifiedqa-crossing-format-boundaries-with-a","title":"UnifiedQA: Crossing Format Boundaries With a Single QA System","date":"2020-05-02","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":4,"samples_unverified":3,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","rows_on_this_dataset":1,"code_links":67,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":48,"samples_ran":22,"samples_unverified":26,"pointer_only_for_licence":23,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/socialiqa-commonsense-reasoning-about-social","title":"SocialIQA: Commonsense Reasoning about Social Interactions","date":"2019-04-22","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":0,"samples_unverified":10,"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":9,"samples_harvested":163,"samples_ran":71,"samples_unverified":92,"pointer_only_for_licence":38,"papers_with_no_sample_that_ran":2,"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."}