Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385571412> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4385571412 abstract "Long-form question answering (LFQA) enables answering a wide range of questions, but its flexibility poses enormous challenges for evaluation. We perform the first targeted study of the evaluation of long-form answers, covering both human and automatic evaluation practices. We hire domain experts in seven areas to provide preference judgments over pairs of answers, along with free-form justifications for their choices. We present a careful analysis of experts’ evaluation, which focuses on new aspects such as the comprehensiveness of the answer. Next, we examine automatic text generation metrics, finding that no existing metrics are predictive of human preference judgments. However, some metrics correlate with fine-grained aspects of answers (e.g., coherence). We encourage future work to move away from a single “overall score” of the answer and adopt a multi-faceted evaluation, targeting aspects such as factuality and completeness. We publicly release all of our annotations and code to spur future work into LFQA evaluation." @default.
- W4385571412 created "2023-08-05" @default.
- W4385571412 creator A5022637213 @default.
- W4385571412 creator A5030631856 @default.
- W4385571412 creator A5035142405 @default.
- W4385571412 creator A5082767919 @default.
- W4385571412 date "2023-01-01" @default.
- W4385571412 modified "2023-10-16" @default.
- W4385571412 title "A Critical Evaluation of Evaluations for Long-form Question Answering" @default.
- W4385571412 doi "https://doi.org/10.18653/v1/2023.acl-long.181" @default.
- W4385571412 hasPublicationYear "2023" @default.
- W4385571412 type Work @default.
- W4385571412 citedByCount "0" @default.
- W4385571412 crossrefType "proceedings-article" @default.
- W4385571412 hasAuthorship W4385571412A5022637213 @default.
- W4385571412 hasAuthorship W4385571412A5030631856 @default.
- W4385571412 hasAuthorship W4385571412A5035142405 @default.
- W4385571412 hasAuthorship W4385571412A5082767919 @default.
- W4385571412 hasBestOaLocation W43855714121 @default.
- W4385571412 hasConcept C105795698 @default.
- W4385571412 hasConcept C121332964 @default.
- W4385571412 hasConcept C134306372 @default.
- W4385571412 hasConcept C154945302 @default.
- W4385571412 hasConcept C162324750 @default.
- W4385571412 hasConcept C17231256 @default.
- W4385571412 hasConcept C175444787 @default.
- W4385571412 hasConcept C23123220 @default.
- W4385571412 hasConcept C2522767166 @default.
- W4385571412 hasConcept C2780598303 @default.
- W4385571412 hasConcept C2781181686 @default.
- W4385571412 hasConcept C2781249084 @default.
- W4385571412 hasConcept C33923547 @default.
- W4385571412 hasConcept C36503486 @default.
- W4385571412 hasConcept C41008148 @default.
- W4385571412 hasConcept C44291984 @default.
- W4385571412 hasConcept C62520636 @default.
- W4385571412 hasConceptScore W4385571412C105795698 @default.
- W4385571412 hasConceptScore W4385571412C121332964 @default.
- W4385571412 hasConceptScore W4385571412C134306372 @default.
- W4385571412 hasConceptScore W4385571412C154945302 @default.
- W4385571412 hasConceptScore W4385571412C162324750 @default.
- W4385571412 hasConceptScore W4385571412C17231256 @default.
- W4385571412 hasConceptScore W4385571412C175444787 @default.
- W4385571412 hasConceptScore W4385571412C23123220 @default.
- W4385571412 hasConceptScore W4385571412C2522767166 @default.
- W4385571412 hasConceptScore W4385571412C2780598303 @default.
- W4385571412 hasConceptScore W4385571412C2781181686 @default.
- W4385571412 hasConceptScore W4385571412C2781249084 @default.
- W4385571412 hasConceptScore W4385571412C33923547 @default.
- W4385571412 hasConceptScore W4385571412C36503486 @default.
- W4385571412 hasConceptScore W4385571412C41008148 @default.
- W4385571412 hasConceptScore W4385571412C44291984 @default.
- W4385571412 hasConceptScore W4385571412C62520636 @default.
- W4385571412 hasLocation W43855714121 @default.
- W4385571412 hasOpenAccess W4385571412 @default.
- W4385571412 hasPrimaryLocation W43855714121 @default.
- W4385571412 hasRelatedWork W15319282 @default.
- W4385571412 hasRelatedWork W2351286801 @default.
- W4385571412 hasRelatedWork W2356380379 @default.
- W4385571412 hasRelatedWork W2361152157 @default.
- W4385571412 hasRelatedWork W2368388617 @default.
- W4385571412 hasRelatedWork W2371931538 @default.
- W4385571412 hasRelatedWork W2547211351 @default.
- W4385571412 hasRelatedWork W271441005 @default.
- W4385571412 hasRelatedWork W2805599431 @default.
- W4385571412 hasRelatedWork W4382202848 @default.
- W4385571412 isParatext "false" @default.
- W4385571412 isRetracted "false" @default.
- W4385571412 workType "article" @default.