Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366559971> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4366559971 abstract "Large Language Models (LLMs) have demonstrated a remarkable ability to generalize zero-shot to various language-related tasks. This paper focuses on the study of exploring generative LLMs such as ChatGPT and GPT-4 for relevance ranking in Information Retrieval (IR). Surprisingly, our experiments reveal that properly instructed ChatGPT and GPT-4 can deliver competitive, even superior results than supervised methods on popular IR benchmarks. Notably, GPT-4 outperforms the fully fine-tuned monoT5-3B on MS MARCO by an average of 2.7 nDCG on TREC datasets, an average of 2.3 nDCG on eight BEIR datasets, and an average of 2.7 nDCG on ten low-resource languages Mr.TyDi. Subsequently, we delve into the potential for distilling the ranking capabilities of ChatGPT into a specialized model. Our small specialized model that trained on 10K ChatGPT generated data outperforms monoT5 trained on 400K annotated MS MARCO data on BEIR. The code to reproduce our results is available at www.github.com/sunnweiwei/RankGPT" @default.
- W4366559971 created "2023-04-22" @default.
- W4366559971 creator A5013794758 @default.
- W4366559971 creator A5030933492 @default.
- W4366559971 creator A5041848845 @default.
- W4366559971 creator A5046700486 @default.
- W4366559971 creator A5050161084 @default.
- W4366559971 creator A5081922458 @default.
- W4366559971 date "2023-04-19" @default.
- W4366559971 modified "2023-10-16" @default.
- W4366559971 title "Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agent" @default.
- W4366559971 doi "https://doi.org/10.48550/arxiv.2304.09542" @default.
- W4366559971 hasPublicationYear "2023" @default.
- W4366559971 type Work @default.
- W4366559971 citedByCount "0" @default.
- W4366559971 crossrefType "posted-content" @default.
- W4366559971 hasAuthorship W4366559971A5013794758 @default.
- W4366559971 hasAuthorship W4366559971A5030933492 @default.
- W4366559971 hasAuthorship W4366559971A5041848845 @default.
- W4366559971 hasAuthorship W4366559971A5046700486 @default.
- W4366559971 hasAuthorship W4366559971A5050161084 @default.
- W4366559971 hasAuthorship W4366559971A5081922458 @default.
- W4366559971 hasBestOaLocation W43665599711 @default.
- W4366559971 hasConcept C119857082 @default.
- W4366559971 hasConcept C137293760 @default.
- W4366559971 hasConcept C154945302 @default.
- W4366559971 hasConcept C158154518 @default.
- W4366559971 hasConcept C177264268 @default.
- W4366559971 hasConcept C17744445 @default.
- W4366559971 hasConcept C189430467 @default.
- W4366559971 hasConcept C199360897 @default.
- W4366559971 hasConcept C199539241 @default.
- W4366559971 hasConcept C204321447 @default.
- W4366559971 hasConcept C206345919 @default.
- W4366559971 hasConcept C23123220 @default.
- W4366559971 hasConcept C2776760102 @default.
- W4366559971 hasConcept C31258907 @default.
- W4366559971 hasConcept C41008148 @default.
- W4366559971 hasConcept C51632099 @default.
- W4366559971 hasConcept C86037889 @default.
- W4366559971 hasConceptScore W4366559971C119857082 @default.
- W4366559971 hasConceptScore W4366559971C137293760 @default.
- W4366559971 hasConceptScore W4366559971C154945302 @default.
- W4366559971 hasConceptScore W4366559971C158154518 @default.
- W4366559971 hasConceptScore W4366559971C177264268 @default.
- W4366559971 hasConceptScore W4366559971C17744445 @default.
- W4366559971 hasConceptScore W4366559971C189430467 @default.
- W4366559971 hasConceptScore W4366559971C199360897 @default.
- W4366559971 hasConceptScore W4366559971C199539241 @default.
- W4366559971 hasConceptScore W4366559971C204321447 @default.
- W4366559971 hasConceptScore W4366559971C206345919 @default.
- W4366559971 hasConceptScore W4366559971C23123220 @default.
- W4366559971 hasConceptScore W4366559971C2776760102 @default.
- W4366559971 hasConceptScore W4366559971C31258907 @default.
- W4366559971 hasConceptScore W4366559971C41008148 @default.
- W4366559971 hasConceptScore W4366559971C51632099 @default.
- W4366559971 hasConceptScore W4366559971C86037889 @default.
- W4366559971 hasLocation W43665599711 @default.
- W4366559971 hasOpenAccess W4366559971 @default.
- W4366559971 hasPrimaryLocation W43665599711 @default.
- W4366559971 hasRelatedWork W104148947 @default.
- W4366559971 hasRelatedWork W1528738305 @default.
- W4366559971 hasRelatedWork W2041353081 @default.
- W4366559971 hasRelatedWork W2116930689 @default.
- W4366559971 hasRelatedWork W2118669775 @default.
- W4366559971 hasRelatedWork W2188714255 @default.
- W4366559971 hasRelatedWork W2967976110 @default.
- W4366559971 hasRelatedWork W3035103838 @default.
- W4366559971 hasRelatedWork W3107474891 @default.
- W4366559971 hasRelatedWork W3199233695 @default.
- W4366559971 isParatext "false" @default.
- W4366559971 isRetracted "false" @default.
- W4366559971 workType "article" @default.