Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208581628> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3208581628 abstract "Many real-world problems require the combined application of multiple reasoning abilities employing suitable abstractions, commonsense knowledge, and creative synthesis of problem-solving strategies. To help advance AI systems towards such capabilities, we propose a new reasoning challenge, namely Fermi Problems (FPs), which are questions whose answers can only be approximately estimated because their precise computation is either impractical or impossible. For example, How much would the sea level rise if all ice in the world melted? FPs are commonly used in quizzes and interviews to bring out and evaluate the creative reasoning abilities of humans. To do the same for AI systems, we present two datasets: 1) A collection of 1k real-world FPs sourced from quizzes and olympiads; and 2) a bank of 10k synthetic FPs of intermediate complexity to serve as a sandbox for the harder real-world challenge. In addition to question answer pairs, the datasets contain detailed solutions in the form of an executable program and supporting facts, helping in supervision and evaluation of intermediate steps. We demonstrate that even extensively fine-tuned large scale language models perform poorly on these datasets, on average making estimates that are off by two orders of magnitude. Our contribution is thus the crystallization of several unsolved AI problems into a single, new challenge that we hope will spur further advances in building systems that can reason." @default.
- W3208581628 created "2021-11-08" @default.
- W3208581628 creator A5016636015 @default.
- W3208581628 creator A5070776545 @default.
- W3208581628 creator A5077407640 @default.
- W3208581628 creator A5077726785 @default.
- W3208581628 creator A5081635691 @default.
- W3208581628 date "2021-10-27" @default.
- W3208581628 modified "2023-09-27" @default.
- W3208581628 title "How Much Coffee Was Consumed During EMNLP 2019? Fermi Problems: A New Reasoning Challenge for AI" @default.
- W3208581628 cites W2252136820 @default.
- W3208581628 cites W2276364082 @default.
- W3208581628 cites W2752099845 @default.
- W3208581628 cites W2889787757 @default.
- W3208581628 cites W2890894339 @default.
- W3208581628 cites W2912007050 @default.
- W3208581628 cites W2950339735 @default.
- W3208581628 cites W2951939640 @default.
- W3208581628 cites W2962800603 @default.
- W3208581628 cites W2962817854 @default.
- W3208581628 cites W2963341956 @default.
- W3208581628 cites W2995359496 @default.
- W3208581628 cites W3082274269 @default.
- W3208581628 cites W3105643199 @default.
- W3208581628 cites W3125833936 @default.
- W3208581628 cites W3134642945 @default.
- W3208581628 cites W3159959439 @default.
- W3208581628 cites W3100879603 @default.
- W3208581628 hasPublicationYear "2021" @default.
- W3208581628 type Work @default.
- W3208581628 sameAs 3208581628 @default.
- W3208581628 citedByCount "0" @default.
- W3208581628 crossrefType "posted-content" @default.
- W3208581628 hasAuthorship W3208581628A5016636015 @default.
- W3208581628 hasAuthorship W3208581628A5070776545 @default.
- W3208581628 hasAuthorship W3208581628A5077407640 @default.
- W3208581628 hasAuthorship W3208581628A5077726785 @default.
- W3208581628 hasAuthorship W3208581628A5081635691 @default.
- W3208581628 hasConcept C115903868 @default.
- W3208581628 hasConcept C121332964 @default.
- W3208581628 hasConcept C1276947 @default.
- W3208581628 hasConcept C140843580 @default.
- W3208581628 hasConcept C154945302 @default.
- W3208581628 hasConcept C160145156 @default.
- W3208581628 hasConcept C167981075 @default.
- W3208581628 hasConcept C199360897 @default.
- W3208581628 hasConcept C2522767166 @default.
- W3208581628 hasConcept C2778755073 @default.
- W3208581628 hasConcept C41008148 @default.
- W3208581628 hasConcept C62520636 @default.
- W3208581628 hasConcept C70352696 @default.
- W3208581628 hasConceptScore W3208581628C115903868 @default.
- W3208581628 hasConceptScore W3208581628C121332964 @default.
- W3208581628 hasConceptScore W3208581628C1276947 @default.
- W3208581628 hasConceptScore W3208581628C140843580 @default.
- W3208581628 hasConceptScore W3208581628C154945302 @default.
- W3208581628 hasConceptScore W3208581628C160145156 @default.
- W3208581628 hasConceptScore W3208581628C167981075 @default.
- W3208581628 hasConceptScore W3208581628C199360897 @default.
- W3208581628 hasConceptScore W3208581628C2522767166 @default.
- W3208581628 hasConceptScore W3208581628C2778755073 @default.
- W3208581628 hasConceptScore W3208581628C41008148 @default.
- W3208581628 hasConceptScore W3208581628C62520636 @default.
- W3208581628 hasConceptScore W3208581628C70352696 @default.
- W3208581628 hasLocation W32085816281 @default.
- W3208581628 hasOpenAccess W3208581628 @default.
- W3208581628 hasPrimaryLocation W32085816281 @default.
- W3208581628 hasRelatedWork W1968607146 @default.
- W3208581628 hasRelatedWork W1991304154 @default.
- W3208581628 hasRelatedWork W2013070077 @default.
- W3208581628 hasRelatedWork W205043379 @default.
- W3208581628 hasRelatedWork W2070183171 @default.
- W3208581628 hasRelatedWork W2101341561 @default.
- W3208581628 hasRelatedWork W2201056133 @default.
- W3208581628 hasRelatedWork W2295985662 @default.
- W3208581628 hasRelatedWork W268049212 @default.
- W3208581628 hasRelatedWork W2740883175 @default.
- W3208581628 hasRelatedWork W2763463375 @default.
- W3208581628 hasRelatedWork W2770581177 @default.
- W3208581628 hasRelatedWork W2896292898 @default.
- W3208581628 hasRelatedWork W3011540878 @default.
- W3208581628 hasRelatedWork W3099059787 @default.
- W3208581628 hasRelatedWork W3121294630 @default.
- W3208581628 hasRelatedWork W3198206023 @default.
- W3208581628 hasRelatedWork W3198230652 @default.
- W3208581628 hasRelatedWork W580074167 @default.
- W3208581628 hasRelatedWork W2740071853 @default.
- W3208581628 isParatext "false" @default.
- W3208581628 isRetracted "false" @default.
- W3208581628 magId "3208581628" @default.
- W3208581628 workType "article" @default.