{"url":"/method/macaw","slug":"macaw","name":"Macaw","full_name":"Macaw","full_name_withheld":false,"description_markdown":"**Macaw** is a generative question-answering (QA) system that is built on UnifiedQA, itself built on [T5](https://paperswithcode.com/method/t5). Macaw has three interesting features. First, it often produces high-quality answers to questions far outside the domain it was trained on, sometimes surprisingly so. Second, Macaw allows different permutations (“an gles”) of inputs and outputs to be used. For example, we can give it a question and get an answer; or give it an answer and get a question; or give it a question and answer and get a set of multiple-choice (MC) options for that question. This multi-angle QA capability allows versatility in the way Macaw can be used, include recursively using outputs as new inputs to the system. Finally, Macaw also generates explanations as an optional output (or even input) element.","description_state":"present","introduced_year":null,"introduced_by":{"title":"General-Purpose Question-Answering with Macaw","paper":"/paper/general-purpose-question-answering-with-macaw","first_author":"Oyvind Tafjord","n_authors":2,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/general-purpose-question-answering-with-macaw"},"source":{"url":"https://arxiv.org/abs/2109.02593v1","title":"General-Purpose Question-Answering with Macaw","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Question Answering Models","url":"/methods/category/question-answering-models","pwc_aliases":[]}],"n_papers_tagged":5,"archive_num_papers":5,"papers_newest_first":[{"paper":null,"title":"Empowering LLMs with Logical Reasoning: A Comprehensive Survey","date":"2025-02-21","arxiv_id":"2502.15652","n_code_links":0,"syntology":null},{"paper":"/paper/do-language-models-have-coherent-mental","title":"Do language models have coherent mental models of everyday things?","date":"2022-12-20","arxiv_id":"2212.10029","n_code_links":1,"syntology":{"ran":0,"of":5,"unverified":5,"pointer_only":0}},{"paper":null,"title":"Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference","date":"2022-11-21","arxiv_id":"2211.11875","n_code_links":0,"syntology":null},{"paper":"/paper/dream-uncovering-mental-models-behind","title":"DREAM: Improving Situational QA by First Elaborating the Situation","date":"2021-12-16","arxiv_id":"2112.08656","n_code_links":1,"syntology":{"ran":3,"of":3,"unverified":0,"pointer_only":0}},{"paper":"/paper/general-purpose-question-answering-with-macaw","title":"General-Purpose Question-Answering with Macaw","date":"2021-09-06","arxiv_id":"2109.02593","n_code_links":2,"syntology":null}],"papers_shown":5,"tasks":[{"task":"/task/question-answering","name":"Question Answering","papers":4},{"task":"/task/generative-question-answering","name":"Generative Question Answering","papers":1},{"task":"/task/logical-reasoning","name":"Logical Reasoning","papers":1},{"task":"/task/multiple-choice","name":"Multiple-choice","papers":1},{"task":"/task/natural-language-inference","name":"Natural Language Inference","papers":1},{"task":"/task/negation","name":"Negation","papers":1},{"task":"/task/survey","name":"Survey","papers":1},{"task":"/task/visual-question-answering","name":"Visual Question Answering (VQA)","papers":1}],"tasks_shown":8,"n_tasks":8,"usage_by_year":[{"year":"2021","papers":2},{"year":"2022","papers":2},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/macaw"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}