Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385571776> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4385571776 abstract "Evaluation of natural language generation (NLG) is complex and multi-dimensional. Generated text can be evaluated for fluency, coherence, factuality, or any other dimensions of interest. Most frameworks that perform such multi-dimensional evaluation require training on large manually or synthetically generated datasets. In this paper, we study the efficacy of large language models as multi-dimensional evaluators using in-context learning, obviating the need for large training datasets. Our experiments show that in-context learning-based evaluators are competitive with learned evaluation frameworks for the task of text summarization, establishing state-of-the-art on dimensions such as relevance and factual consistency. We then analyze the effects of factors such as the selection and number of in-context examples on performance. Finally, we study the efficacy of in-context learning-based evaluators in evaluating zero-shot summaries written by large language models such as GPT-3." @default.
- W4385571776 created "2023-08-05" @default.
- W4385571776 creator A5022934107 @default.
- W4385571776 creator A5032540004 @default.
- W4385571776 creator A5052828977 @default.
- W4385571776 creator A5055631312 @default.
- W4385571776 creator A5061762931 @default.
- W4385571776 creator A5068811427 @default.
- W4385571776 creator A5074366625 @default.
- W4385571776 date "2023-01-01" @default.
- W4385571776 modified "2023-09-24" @default.
- W4385571776 title "Multi-Dimensional Evaluation of Text Summarization with In-Context Learning" @default.
- W4385571776 doi "https://doi.org/10.18653/v1/2023.findings-acl.537" @default.
- W4385571776 hasPublicationYear "2023" @default.
- W4385571776 type Work @default.
- W4385571776 citedByCount "0" @default.
- W4385571776 crossrefType "proceedings-article" @default.
- W4385571776 hasAuthorship W4385571776A5022934107 @default.
- W4385571776 hasAuthorship W4385571776A5032540004 @default.
- W4385571776 hasAuthorship W4385571776A5052828977 @default.
- W4385571776 hasAuthorship W4385571776A5055631312 @default.
- W4385571776 hasAuthorship W4385571776A5061762931 @default.
- W4385571776 hasAuthorship W4385571776A5068811427 @default.
- W4385571776 hasAuthorship W4385571776A5074366625 @default.
- W4385571776 hasBestOaLocation W43855717761 @default.
- W4385571776 hasConcept C121332964 @default.
- W4385571776 hasConcept C138885662 @default.
- W4385571776 hasConcept C151730666 @default.
- W4385571776 hasConcept C154945302 @default.
- W4385571776 hasConcept C158154518 @default.
- W4385571776 hasConcept C162324750 @default.
- W4385571776 hasConcept C170858558 @default.
- W4385571776 hasConcept C17744445 @default.
- W4385571776 hasConcept C187736073 @default.
- W4385571776 hasConcept C199539241 @default.
- W4385571776 hasConcept C204321447 @default.
- W4385571776 hasConcept C23123220 @default.
- W4385571776 hasConcept C2776436953 @default.
- W4385571776 hasConcept C2777413886 @default.
- W4385571776 hasConcept C2779343474 @default.
- W4385571776 hasConcept C2780451532 @default.
- W4385571776 hasConcept C2781181686 @default.
- W4385571776 hasConcept C41008148 @default.
- W4385571776 hasConcept C41895202 @default.
- W4385571776 hasConcept C62520636 @default.
- W4385571776 hasConcept C81917197 @default.
- W4385571776 hasConcept C86803240 @default.
- W4385571776 hasConceptScore W4385571776C121332964 @default.
- W4385571776 hasConceptScore W4385571776C138885662 @default.
- W4385571776 hasConceptScore W4385571776C151730666 @default.
- W4385571776 hasConceptScore W4385571776C154945302 @default.
- W4385571776 hasConceptScore W4385571776C158154518 @default.
- W4385571776 hasConceptScore W4385571776C162324750 @default.
- W4385571776 hasConceptScore W4385571776C170858558 @default.
- W4385571776 hasConceptScore W4385571776C17744445 @default.
- W4385571776 hasConceptScore W4385571776C187736073 @default.
- W4385571776 hasConceptScore W4385571776C199539241 @default.
- W4385571776 hasConceptScore W4385571776C204321447 @default.
- W4385571776 hasConceptScore W4385571776C23123220 @default.
- W4385571776 hasConceptScore W4385571776C2776436953 @default.
- W4385571776 hasConceptScore W4385571776C2777413886 @default.
- W4385571776 hasConceptScore W4385571776C2779343474 @default.
- W4385571776 hasConceptScore W4385571776C2780451532 @default.
- W4385571776 hasConceptScore W4385571776C2781181686 @default.
- W4385571776 hasConceptScore W4385571776C41008148 @default.
- W4385571776 hasConceptScore W4385571776C41895202 @default.
- W4385571776 hasConceptScore W4385571776C62520636 @default.
- W4385571776 hasConceptScore W4385571776C81917197 @default.
- W4385571776 hasConceptScore W4385571776C86803240 @default.
- W4385571776 hasLocation W43855717761 @default.
- W4385571776 hasOpenAccess W4385571776 @default.
- W4385571776 hasPrimaryLocation W43855717761 @default.
- W4385571776 hasRelatedWork W132250100 @default.
- W4385571776 hasRelatedWork W2093597205 @default.
- W4385571776 hasRelatedWork W2170202678 @default.
- W4385571776 hasRelatedWork W2389846579 @default.
- W4385571776 hasRelatedWork W2392495745 @default.
- W4385571776 hasRelatedWork W2392568419 @default.
- W4385571776 hasRelatedWork W2489740420 @default.
- W4385571776 hasRelatedWork W3165276360 @default.
- W4385571776 hasRelatedWork W4226350330 @default.
- W4385571776 hasRelatedWork W4287166693 @default.
- W4385571776 isParatext "false" @default.
- W4385571776 isRetracted "false" @default.
- W4385571776 workType "article" @default.