Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285106084> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4285106084 abstract "Current QA systems can generate reasonable-sounding yet false answers without explanation or evidence for the generated answer, which is especially problematic when humans cannot readily check the model’s answers. This presents a challenge for building trust in machine learning systems. We take inspiration from real-world situations where difficult questions are answered by considering opposing sides (see Irving et al., 2018). For multiple-choice QA examples, we build a dataset of single arguments for both a correct and incorrect answer option in a debate-style set-up as an initial step in training models to produce explanations for two candidate answers. We use long contexts—humans familiar with the context write convincing explanations for pre-selected correct and incorrect answers, and we test if those explanations allow humans who have not read the full context to more accurately determine the correct answer. We do not find that explanations in our set-up improve human accuracy, but a baseline condition shows that providing human-selected text snippets does improve accuracy. We use these findings to suggest ways of improving the debate set up for future data collection efforts." @default.
- W4285106084 created "2022-07-14" @default.
- W4285106084 creator A5013626682 @default.
- W4285106084 creator A5025500234 @default.
- W4285106084 creator A5044118544 @default.
- W4285106084 creator A5047763717 @default.
- W4285106084 creator A5067390670 @default.
- W4285106084 creator A5082569485 @default.
- W4285106084 creator A5091112967 @default.
- W4285106084 date "2022-01-01" @default.
- W4285106084 modified "2023-10-11" @default.
- W4285106084 title "Single-Turn Debate Does Not Help Humans Answer Hard Reading-Comprehension Questions" @default.
- W4285106084 doi "https://doi.org/10.18653/v1/2022.lnls-1.3" @default.
- W4285106084 hasPublicationYear "2022" @default.
- W4285106084 type Work @default.
- W4285106084 citedByCount "0" @default.
- W4285106084 crossrefType "proceedings-article" @default.
- W4285106084 hasAuthorship W4285106084A5013626682 @default.
- W4285106084 hasAuthorship W4285106084A5025500234 @default.
- W4285106084 hasAuthorship W4285106084A5044118544 @default.
- W4285106084 hasAuthorship W4285106084A5047763717 @default.
- W4285106084 hasAuthorship W4285106084A5067390670 @default.
- W4285106084 hasAuthorship W4285106084A5082569485 @default.
- W4285106084 hasAuthorship W4285106084A5091112967 @default.
- W4285106084 hasBestOaLocation W42851060841 @default.
- W4285106084 hasConcept C119857082 @default.
- W4285106084 hasConcept C138885662 @default.
- W4285106084 hasConcept C151730666 @default.
- W4285106084 hasConcept C154945302 @default.
- W4285106084 hasConcept C166957645 @default.
- W4285106084 hasConcept C177264268 @default.
- W4285106084 hasConcept C199360897 @default.
- W4285106084 hasConcept C204321447 @default.
- W4285106084 hasConcept C23123220 @default.
- W4285106084 hasConcept C2522767166 @default.
- W4285106084 hasConcept C2776445246 @default.
- W4285106084 hasConcept C2777267654 @default.
- W4285106084 hasConcept C2779343474 @default.
- W4285106084 hasConcept C41008148 @default.
- W4285106084 hasConcept C41895202 @default.
- W4285106084 hasConcept C511192102 @default.
- W4285106084 hasConcept C51632099 @default.
- W4285106084 hasConcept C554936623 @default.
- W4285106084 hasConcept C86803240 @default.
- W4285106084 hasConcept C95457728 @default.
- W4285106084 hasConceptScore W4285106084C119857082 @default.
- W4285106084 hasConceptScore W4285106084C138885662 @default.
- W4285106084 hasConceptScore W4285106084C151730666 @default.
- W4285106084 hasConceptScore W4285106084C154945302 @default.
- W4285106084 hasConceptScore W4285106084C166957645 @default.
- W4285106084 hasConceptScore W4285106084C177264268 @default.
- W4285106084 hasConceptScore W4285106084C199360897 @default.
- W4285106084 hasConceptScore W4285106084C204321447 @default.
- W4285106084 hasConceptScore W4285106084C23123220 @default.
- W4285106084 hasConceptScore W4285106084C2522767166 @default.
- W4285106084 hasConceptScore W4285106084C2776445246 @default.
- W4285106084 hasConceptScore W4285106084C2777267654 @default.
- W4285106084 hasConceptScore W4285106084C2779343474 @default.
- W4285106084 hasConceptScore W4285106084C41008148 @default.
- W4285106084 hasConceptScore W4285106084C41895202 @default.
- W4285106084 hasConceptScore W4285106084C511192102 @default.
- W4285106084 hasConceptScore W4285106084C51632099 @default.
- W4285106084 hasConceptScore W4285106084C554936623 @default.
- W4285106084 hasConceptScore W4285106084C86803240 @default.
- W4285106084 hasConceptScore W4285106084C95457728 @default.
- W4285106084 hasLocation W42851060841 @default.
- W4285106084 hasLocation W42851060842 @default.
- W4285106084 hasOpenAccess W4285106084 @default.
- W4285106084 hasPrimaryLocation W42851060841 @default.
- W4285106084 hasRelatedWork W2357241418 @default.
- W4285106084 hasRelatedWork W2377222960 @default.
- W4285106084 hasRelatedWork W2792951589 @default.
- W4285106084 hasRelatedWork W2961085424 @default.
- W4285106084 hasRelatedWork W3201070945 @default.
- W4285106084 hasRelatedWork W4285260836 @default.
- W4285106084 hasRelatedWork W4286629047 @default.
- W4285106084 hasRelatedWork W4306321456 @default.
- W4285106084 hasRelatedWork W4306674287 @default.
- W4285106084 hasRelatedWork W4224009465 @default.
- W4285106084 isParatext "false" @default.
- W4285106084 isRetracted "false" @default.
- W4285106084 workType "article" @default.