Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385570710> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W4385570710 abstract "Large language models have shown impressive abilities to reason over input text, however, they are prone to hallucinations. On the other hand, end-to-end knowledge graph question answering (KGQA) models output responses grounded in facts, but they still struggle with complex reasoning, such as comparison or ordinal questions. In this paper, we propose a new method for complex question answering where we combine a knowledge graph retriever based on an end-to-end KGQA model with a language model that reasons over the retrieved facts to return an answer. We observe that augmenting language model prompts with retrieved KG facts improves performance over using a language model alone by an average of 83%. In particular, we see improvements on complex questions requiring count, intersection, or multi-hop reasoning operations." @default.
- W4385570710 created "2023-08-05" @default.
- W4385570710 creator A5023847886 @default.
- W4385570710 creator A5033705087 @default.
- W4385570710 creator A5079840947 @default.
- W4385570710 date "2023-01-01" @default.
- W4385570710 modified "2023-09-24" @default.
- W4385570710 title "Knowledge Graph-augmented Language Models for Complex Question Answering" @default.
- W4385570710 doi "https://doi.org/10.18653/v1/2023.nlrse-1.1" @default.
- W4385570710 hasPublicationYear "2023" @default.
- W4385570710 type Work @default.
- W4385570710 citedByCount "0" @default.
- W4385570710 crossrefType "proceedings-article" @default.
- W4385570710 hasAuthorship W4385570710A5023847886 @default.
- W4385570710 hasAuthorship W4385570710A5033705087 @default.
- W4385570710 hasAuthorship W4385570710A5079840947 @default.
- W4385570710 hasBestOaLocation W43855707101 @default.
- W4385570710 hasConcept C127413603 @default.
- W4385570710 hasConcept C132525143 @default.
- W4385570710 hasConcept C137293760 @default.
- W4385570710 hasConcept C146978453 @default.
- W4385570710 hasConcept C154945302 @default.
- W4385570710 hasConcept C203776342 @default.
- W4385570710 hasConcept C204321447 @default.
- W4385570710 hasConcept C2987255567 @default.
- W4385570710 hasConcept C41008148 @default.
- W4385570710 hasConcept C44291984 @default.
- W4385570710 hasConcept C54540088 @default.
- W4385570710 hasConcept C64543145 @default.
- W4385570710 hasConcept C80444323 @default.
- W4385570710 hasConceptScore W4385570710C127413603 @default.
- W4385570710 hasConceptScore W4385570710C132525143 @default.
- W4385570710 hasConceptScore W4385570710C137293760 @default.
- W4385570710 hasConceptScore W4385570710C146978453 @default.
- W4385570710 hasConceptScore W4385570710C154945302 @default.
- W4385570710 hasConceptScore W4385570710C203776342 @default.
- W4385570710 hasConceptScore W4385570710C204321447 @default.
- W4385570710 hasConceptScore W4385570710C2987255567 @default.
- W4385570710 hasConceptScore W4385570710C41008148 @default.
- W4385570710 hasConceptScore W4385570710C44291984 @default.
- W4385570710 hasConceptScore W4385570710C54540088 @default.
- W4385570710 hasConceptScore W4385570710C64543145 @default.
- W4385570710 hasConceptScore W4385570710C80444323 @default.
- W4385570710 hasLocation W43855707101 @default.
- W4385570710 hasOpenAccess W4385570710 @default.
- W4385570710 hasPrimaryLocation W43855707101 @default.
- W4385570710 hasRelatedWork W1560657467 @default.
- W4385570710 hasRelatedWork W207304934 @default.
- W4385570710 hasRelatedWork W20999564 @default.
- W4385570710 hasRelatedWork W2359001871 @default.
- W4385570710 hasRelatedWork W3102273025 @default.
- W4385570710 hasRelatedWork W3207693618 @default.
- W4385570710 hasRelatedWork W4229058120 @default.
- W4385570710 hasRelatedWork W4283807154 @default.
- W4385570710 hasRelatedWork W4297199749 @default.
- W4385570710 hasRelatedWork W4377703168 @default.
- W4385570710 isParatext "false" @default.
- W4385570710 isRetracted "false" @default.
- W4385570710 workType "article" @default.