Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387074787> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W4387074787 abstract "Large Language Models (LLMs) have emerged as one of the most important breakthroughs in natural language processing (NLP) for their impressive skills in language generation and other language-specific tasks. Though LLMs have been evaluated in various tasks, mostly in English, they have not yet undergone thorough evaluation in under-resourced languages such as Bengali (Bangla). In this paper, we evaluate the performance of LLMs for the low-resourced Bangla language. We select various important and diverse Bangla NLP tasks, such as abstractive summarization, question answering, paraphrasing, natural language inference, text classification, and sentiment analysis for zero-shot evaluation with ChatGPT, LLaMA-2, and Claude-2 and compare the performance with state-of-the-art fine-tuned models. Our experimental results demonstrate an inferior performance of LLMs for different Bangla NLP tasks, calling for further effort to develop better understanding of LLMs in low-resource languages like Bangla." @default.
- W4387074787 created "2023-09-27" @default.
- W4387074787 creator A5034756201 @default.
- W4387074787 creator A5058398007 @default.
- W4387074787 creator A5059021174 @default.
- W4387074787 creator A5068544743 @default.
- W4387074787 creator A5069546450 @default.
- W4387074787 creator A5088296414 @default.
- W4387074787 date "2023-09-22" @default.
- W4387074787 modified "2023-09-28" @default.
- W4387074787 title "BenLLMEval: A Comprehensive Evaluation into the Potentials and Pitfalls of Large Language Models on Bengali NLP" @default.
- W4387074787 doi "https://doi.org/10.48550/arxiv.2309.13173" @default.
- W4387074787 hasPublicationYear "2023" @default.
- W4387074787 type Work @default.
- W4387074787 citedByCount "0" @default.
- W4387074787 crossrefType "posted-content" @default.
- W4387074787 hasAuthorship W4387074787A5034756201 @default.
- W4387074787 hasAuthorship W4387074787A5058398007 @default.
- W4387074787 hasAuthorship W4387074787A5059021174 @default.
- W4387074787 hasAuthorship W4387074787A5068544743 @default.
- W4387074787 hasAuthorship W4387074787A5069546450 @default.
- W4387074787 hasAuthorship W4387074787A5088296414 @default.
- W4387074787 hasBestOaLocation W43870747871 @default.
- W4387074787 hasConcept C138885662 @default.
- W4387074787 hasConcept C154945302 @default.
- W4387074787 hasConcept C170858558 @default.
- W4387074787 hasConcept C19235068 @default.
- W4387074787 hasConcept C204321447 @default.
- W4387074787 hasConcept C2776214188 @default.
- W4387074787 hasConcept C41008148 @default.
- W4387074787 hasConcept C41895202 @default.
- W4387074787 hasConceptScore W4387074787C138885662 @default.
- W4387074787 hasConceptScore W4387074787C154945302 @default.
- W4387074787 hasConceptScore W4387074787C170858558 @default.
- W4387074787 hasConceptScore W4387074787C19235068 @default.
- W4387074787 hasConceptScore W4387074787C204321447 @default.
- W4387074787 hasConceptScore W4387074787C2776214188 @default.
- W4387074787 hasConceptScore W4387074787C41008148 @default.
- W4387074787 hasConceptScore W4387074787C41895202 @default.
- W4387074787 hasLocation W43870747871 @default.
- W4387074787 hasOpenAccess W4387074787 @default.
- W4387074787 hasPrimaryLocation W43870747871 @default.
- W4387074787 hasRelatedWork W1628967614 @default.
- W4387074787 hasRelatedWork W2772341632 @default.
- W4387074787 hasRelatedWork W2997227274 @default.
- W4387074787 hasRelatedWork W2997947588 @default.
- W4387074787 hasRelatedWork W3105168542 @default.
- W4387074787 hasRelatedWork W3126195334 @default.
- W4387074787 hasRelatedWork W3192589309 @default.
- W4387074787 hasRelatedWork W3204019825 @default.
- W4387074787 hasRelatedWork W4297791020 @default.
- W4387074787 hasRelatedWork W4313156585 @default.
- W4387074787 isParatext "false" @default.
- W4387074787 isRetracted "false" @default.
- W4387074787 workType "article" @default.