Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378771323> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4378771323 abstract "Chain-of-thought (CoT) prompting with large language models has proven effective in numerous natural language processing tasks, but designing prompts that generalize well to diverse problem types can be challenging, especially in the context of math word problem (MWP) solving. Additionally, it is common to have a large amount of training data that have a better diversity coverage but CoT annotations are not available, which limits the use of supervised learning techniques. To address these issues, we investigate two approaches to leverage the training data in a few-shot prompting scenario: dynamic program prompting and program distillation. Our approach is largely inspired by Gao et al., (2022), where they proposed to replace the CoT with the programs as the intermediate reasoning step. Such a prompting strategy allows us to accurately verify the answer correctness through program execution in MWP solving. Our dynamic program prompting involves annotating the training data by sampling correct programs from a large language model, while program distillation involves adapting a smaller model to the program-annotated training data. Our experiments on three standard MWP datasets demonstrate the effectiveness of these approaches, yielding significant improvements over previous baselines for prompting and fine-tuning. Our results suggest that leveraging a large amount of training data can improve the generalization ability of prompts and boost the performance of fine-tuned small models in MWP solving." @default.
- W4378771323 created "2023-05-31" @default.
- W4378771323 creator A5014235961 @default.
- W4378771323 creator A5060938232 @default.
- W4378771323 date "2023-05-29" @default.
- W4378771323 modified "2023-09-27" @default.
- W4378771323 title "Leveraging Training Data in Few-Shot Prompting for Numerical Reasoning" @default.
- W4378771323 doi "https://doi.org/10.48550/arxiv.2305.18170" @default.
- W4378771323 hasPublicationYear "2023" @default.
- W4378771323 type Work @default.
- W4378771323 citedByCount "0" @default.
- W4378771323 crossrefType "posted-content" @default.
- W4378771323 hasAuthorship W4378771323A5014235961 @default.
- W4378771323 hasAuthorship W4378771323A5060938232 @default.
- W4378771323 hasBestOaLocation W43787713231 @default.
- W4378771323 hasConcept C119857082 @default.
- W4378771323 hasConcept C134306372 @default.
- W4378771323 hasConcept C137293760 @default.
- W4378771323 hasConcept C151730666 @default.
- W4378771323 hasConcept C153083717 @default.
- W4378771323 hasConcept C154945302 @default.
- W4378771323 hasConcept C177148314 @default.
- W4378771323 hasConcept C199360897 @default.
- W4378771323 hasConcept C204321447 @default.
- W4378771323 hasConcept C2779343474 @default.
- W4378771323 hasConcept C33923547 @default.
- W4378771323 hasConcept C41008148 @default.
- W4378771323 hasConcept C51632099 @default.
- W4378771323 hasConcept C55439883 @default.
- W4378771323 hasConcept C86803240 @default.
- W4378771323 hasConceptScore W4378771323C119857082 @default.
- W4378771323 hasConceptScore W4378771323C134306372 @default.
- W4378771323 hasConceptScore W4378771323C137293760 @default.
- W4378771323 hasConceptScore W4378771323C151730666 @default.
- W4378771323 hasConceptScore W4378771323C153083717 @default.
- W4378771323 hasConceptScore W4378771323C154945302 @default.
- W4378771323 hasConceptScore W4378771323C177148314 @default.
- W4378771323 hasConceptScore W4378771323C199360897 @default.
- W4378771323 hasConceptScore W4378771323C204321447 @default.
- W4378771323 hasConceptScore W4378771323C2779343474 @default.
- W4378771323 hasConceptScore W4378771323C33923547 @default.
- W4378771323 hasConceptScore W4378771323C41008148 @default.
- W4378771323 hasConceptScore W4378771323C51632099 @default.
- W4378771323 hasConceptScore W4378771323C55439883 @default.
- W4378771323 hasConceptScore W4378771323C86803240 @default.
- W4378771323 hasLocation W43787713231 @default.
- W4378771323 hasOpenAccess W4378771323 @default.
- W4378771323 hasPrimaryLocation W43787713231 @default.
- W4378771323 hasRelatedWork W142374489 @default.
- W4378771323 hasRelatedWork W1517743118 @default.
- W4378771323 hasRelatedWork W2359001871 @default.
- W4378771323 hasRelatedWork W2363881323 @default.
- W4378771323 hasRelatedWork W2365918773 @default.
- W4378771323 hasRelatedWork W3035051717 @default.
- W4378771323 hasRelatedWork W3046207468 @default.
- W4378771323 hasRelatedWork W3107474891 @default.
- W4378771323 hasRelatedWork W4323363096 @default.
- W4378771323 hasRelatedWork W88325386 @default.
- W4378771323 isParatext "false" @default.
- W4378771323 isRetracted "false" @default.
- W4378771323 workType "article" @default.