Matches in SemOpenAlex for { <https://semopenalex.org/work/W4324134461> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4324134461 abstract "Generative large language models (LLMs), e.g., ChatGPT, have demonstrated remarkable proficiency across several NLP tasks such as machine translation, question answering, text summarization, and natural language understanding. Recent research has shown that utilizing ChatGPT for assessing the quality of machine translation (MT) achieves state-of-the-art performance at the system level but performs poorly at the segment level. To further improve the performance of LLMs on MT quality assessment, we conducted an investigation into several prompting methods. Our results indicate that by combining Chain-of-Thoughts and Error Analysis, a new prompting method called Error Analysis Prompting, LLMs like ChatGPT can textit{generate human-like MT evaluations at both the system and segment level}. Additionally, we discovered some limitations of ChatGPT as an MT evaluator, such as unstable scoring and biases when provided with multiple translations in a single query. Our findings aim to provide a preliminary experience for appropriately evaluating translation quality on ChatGPT while offering a variety of tricks in designing prompts for in-context learning. We anticipate that this report will shed new light on advancing the field of translation evaluation with LLMs by enhancing both the accuracy and reliability of metrics. The project can be found at https://github.com/Coldmist-Lu/ErrorAnalysis_Prompt." @default.
- W4324134461 created "2023-03-15" @default.
- W4324134461 creator A5053159289 @default.
- W4324134461 creator A5057303109 @default.
- W4324134461 creator A5065438419 @default.
- W4324134461 creator A5074103823 @default.
- W4324134461 creator A5086939495 @default.
- W4324134461 date "2023-03-14" @default.
- W4324134461 modified "2023-10-10" @default.
- W4324134461 title "Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models: A Case Study on ChatGPT" @default.
- W4324134461 doi "https://doi.org/10.20944/preprints202303.0255.v1" @default.
- W4324134461 hasPublicationYear "2023" @default.
- W4324134461 type Work @default.
- W4324134461 citedByCount "3" @default.
- W4324134461 countsByYear W43241344612023 @default.
- W4324134461 crossrefType "posted-content" @default.
- W4324134461 hasAuthorship W4324134461A5053159289 @default.
- W4324134461 hasAuthorship W4324134461A5057303109 @default.
- W4324134461 hasAuthorship W4324134461A5065438419 @default.
- W4324134461 hasAuthorship W4324134461A5074103823 @default.
- W4324134461 hasAuthorship W4324134461A5086939495 @default.
- W4324134461 hasBestOaLocation W43241344611 @default.
- W4324134461 hasConcept C104317684 @default.
- W4324134461 hasConcept C105580179 @default.
- W4324134461 hasConcept C111472728 @default.
- W4324134461 hasConcept C121332964 @default.
- W4324134461 hasConcept C136197465 @default.
- W4324134461 hasConcept C138885662 @default.
- W4324134461 hasConcept C149364088 @default.
- W4324134461 hasConcept C151730666 @default.
- W4324134461 hasConcept C154945302 @default.
- W4324134461 hasConcept C163258240 @default.
- W4324134461 hasConcept C170858558 @default.
- W4324134461 hasConcept C185592680 @default.
- W4324134461 hasConcept C203005215 @default.
- W4324134461 hasConcept C204321447 @default.
- W4324134461 hasConcept C2779343474 @default.
- W4324134461 hasConcept C2779530757 @default.
- W4324134461 hasConcept C41008148 @default.
- W4324134461 hasConcept C43214815 @default.
- W4324134461 hasConcept C55493867 @default.
- W4324134461 hasConcept C62520636 @default.
- W4324134461 hasConcept C86803240 @default.
- W4324134461 hasConceptScore W4324134461C104317684 @default.
- W4324134461 hasConceptScore W4324134461C105580179 @default.
- W4324134461 hasConceptScore W4324134461C111472728 @default.
- W4324134461 hasConceptScore W4324134461C121332964 @default.
- W4324134461 hasConceptScore W4324134461C136197465 @default.
- W4324134461 hasConceptScore W4324134461C138885662 @default.
- W4324134461 hasConceptScore W4324134461C149364088 @default.
- W4324134461 hasConceptScore W4324134461C151730666 @default.
- W4324134461 hasConceptScore W4324134461C154945302 @default.
- W4324134461 hasConceptScore W4324134461C163258240 @default.
- W4324134461 hasConceptScore W4324134461C170858558 @default.
- W4324134461 hasConceptScore W4324134461C185592680 @default.
- W4324134461 hasConceptScore W4324134461C203005215 @default.
- W4324134461 hasConceptScore W4324134461C204321447 @default.
- W4324134461 hasConceptScore W4324134461C2779343474 @default.
- W4324134461 hasConceptScore W4324134461C2779530757 @default.
- W4324134461 hasConceptScore W4324134461C41008148 @default.
- W4324134461 hasConceptScore W4324134461C43214815 @default.
- W4324134461 hasConceptScore W4324134461C55493867 @default.
- W4324134461 hasConceptScore W4324134461C62520636 @default.
- W4324134461 hasConceptScore W4324134461C86803240 @default.
- W4324134461 hasLocation W43241344611 @default.
- W4324134461 hasLocation W43241344612 @default.
- W4324134461 hasOpenAccess W4324134461 @default.
- W4324134461 hasPrimaryLocation W43241344611 @default.
- W4324134461 hasRelatedWork W1512718085 @default.
- W4324134461 hasRelatedWork W2058999950 @default.
- W4324134461 hasRelatedWork W2129683077 @default.
- W4324134461 hasRelatedWork W4200317407 @default.
- W4324134461 hasRelatedWork W4281385036 @default.
- W4324134461 hasRelatedWork W4284703357 @default.
- W4324134461 hasRelatedWork W4360585598 @default.
- W4324134461 hasRelatedWork W4361804203 @default.
- W4324134461 hasRelatedWork W4368755732 @default.
- W4324134461 hasRelatedWork W2610387714 @default.
- W4324134461 isParatext "false" @default.
- W4324134461 isRetracted "false" @default.
- W4324134461 workType "article" @default.