Methods › Natural Language Processing › Question Answering Models › Macaw
Macaw
Introduced by Oyvind Tafjord et al. in General-Purpose Question-Answering with Macaw
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Macaw is a generative question-answering (QA) system that is built on UnifiedQA, itself built on 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.
Papers archive 2025-07-28
5 shown of 5, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Empowering LLMs with Logical Reasoning: A Comprehensive Survey 21 Feb 2025 · 0 repositories · arXiv:2502.15652
-
Do language models have coherent mental models of everyday things? 20 Dec 2022 · 1 repository · arXiv:2212.10029Syntology ran 0 of 5 samples · 5 unverified
-
Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference 21 Nov 2022 · 0 repositories · arXiv:2211.11875
-
DREAM: Improving Situational QA by First Elaborating the Situation 16 Dec 2021 · 1 repository · arXiv:2112.08656Syntology ran 3 of 3 samples · 0 unverified
-
General-Purpose Question-Answering with Macaw 6 Sep 2021 · 2 repositories · arXiv:2109.02593
Tasks archive 2025-07-28
8 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Question Answering | 4 |
| Generative Question Answering | 1 |
| Logical Reasoning | 1 |
| Multiple-choice | 1 |
| Natural Language Inference | 1 |
| Negation | 1 |
| Survey | 1 |
| Visual Question Answering (VQA) | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections