{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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,"slug":"empowering-llms-with-logical-reasoning-a","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","slug":"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,"n_ran_checked":0,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"0 ran · 5 unverified","official":{"repos":["allenai/everyday-things"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":[]}}},{"paper":null,"slug":"enhancing-self-consistency-and-performance-of","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","slug":"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,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["allenai/dream"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/general-purpose-question-answering-with-macaw","slug":"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,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":5,"with_a_code_link":3,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":5,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/method/macaw/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/macaw/papers/ran/1","json":"/method/macaw/papers/ran/1.json","rows":1}],"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":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Macaw","read_at":"2026-10-05T00:58:51+00:00","query":"Macaw","kind":"method","have":"verified_code","tier":null,"verified_implementation":true,"level":3,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"Meta-Actor Critic with Advantage Weighting (MACAW)","origin_arxiv_id":"2008.06043"},"resolution":"alias","resolved_name_differs":true,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"different_paper","archive_paper_arxiv_id":"2109.02593","repositories":{"listed":null,"in_graph":2,"list_truncated":null,"strongest_link":null},"retrieve_with":"get_reference_implementation(name='Meta-Actor Critic with Advantage Weighting (MACAW)')","name_competition":{"verdict":"contested","may_be_wrong_sense":false,"bearers_found":2,"served":{"arxiv_id":"2008.06043","citations":126},"leading_other_bearer":{"arxiv_id":"openreview_eYW037oqQ4","title":"MACAW: A Causal Generative Model for Medical Imaging","citations":null,"named_by":["title_prefix"],"bearer_name":"MACAW: A Causal Generative Model for Medical Imaging","ask_with":"have('openreview_eYW037oqQ4')"},"n_other_bearers_listed":1,"note":"1 other thing(s) here are also called 'Macaw', and none of them is cited more than the paper this answer is about. They are listed in `also_named` -- check `served.arxiv_id` is the paper you meant."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2008.06043","page":"/paper/offline-meta-reinforcement-learning-with","syntology_url":"https://syntology.ai/paper/2008.06043","in_graph_layer":true,"samples":5,"ran":2,"n_ran_checked":2,"n_instrument":0,"unverified":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"about another paper, arXiv:2008.06043: verified reference implementation at level V3. The lookup matched a different name in Syntology's graph, 'Meta-Actor Critic with Advantage Weighting (MACAW)' (resolution: alias); this answer is about that name. About another paper: this answer is about arXiv:2008.06043, while the archive credits arXiv:2109.02593.","level_legend":{"state":"quoted","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","card_sha256":"479785a84658dd682a11b10237b3620d651d7f87799f5dc7add970aaa83f6d39","note":"Syntology's served verification levels, quoted verbatim from its MCP server card; a row is split where the card separates clauses with a double hyphen, and the separator is not reproduced","levels":[{"level":"V0","quoted":["imports"]},{"level":"V1","quoted":["executes against a synthesized fixture and returns a value of the recorded type"]},{"level":"V2","quoted":["two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs","neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)"]},{"level":"V3","quoted":["paper-derived property tests pass on both of those same two generations."]}],"no_rung":"No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results."}},"syntology_have_state":"loaded","record_sha256":"1d0f5961cbe808ee86a4dc33f36bb9134755459f1c9105c43dfa95a3f1b94e24","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}