Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387687911> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4387687911 abstract "Recently, large language models (LLMs), including notable models such as GPT-4 and burgeoning community models, have showcased significant general language understanding abilities. However, there has been a scarcity of attempts to assess the logical reasoning capacities of these LLMs, an essential facet of natural language understanding. To encourage further investigation in this area, we introduce GLoRE, a meticulously assembled General Logical Reasoning Evaluation benchmark comprised of 12 datasets that span three different types of tasks. Our experimental results show that compared to the performance of human and supervised fine-tuning, the logical reasoning capabilities of open LLM models necessitate additional improvement; ChatGPT and GPT-4 show a strong capability of logical reasoning, with GPT-4 surpassing ChatGPT by a large margin. We propose a self-consistency probing method to enhance the accuracy of ChatGPT and a fine-tuned method to boost the performance of an open LLM. We release the datasets and evaluation programs to facilitate future research." @default.
- W4387687911 created "2023-10-17" @default.
- W4387687911 creator A5001312197 @default.
- W4387687911 creator A5010776860 @default.
- W4387687911 creator A5012543243 @default.
- W4387687911 creator A5071444362 @default.
- W4387687911 creator A5080838462 @default.
- W4387687911 creator A5081383763 @default.
- W4387687911 date "2023-10-13" @default.
- W4387687911 modified "2023-10-18" @default.
- W4387687911 title "GLoRE: Evaluating Logical Reasoning of Large Language Models" @default.
- W4387687911 doi "https://doi.org/10.48550/arxiv.2310.09107" @default.
- W4387687911 hasPublicationYear "2023" @default.
- W4387687911 type Work @default.
- W4387687911 citedByCount "0" @default.
- W4387687911 crossrefType "posted-content" @default.
- W4387687911 hasAuthorship W4387687911A5001312197 @default.
- W4387687911 hasAuthorship W4387687911A5010776860 @default.
- W4387687911 hasAuthorship W4387687911A5012543243 @default.
- W4387687911 hasAuthorship W4387687911A5071444362 @default.
- W4387687911 hasAuthorship W4387687911A5080838462 @default.
- W4387687911 hasAuthorship W4387687911A5081383763 @default.
- W4387687911 hasBestOaLocation W43876879111 @default.
- W4387687911 hasConcept C109747225 @default.
- W4387687911 hasConcept C119857082 @default.
- W4387687911 hasConcept C127413603 @default.
- W4387687911 hasConcept C13280743 @default.
- W4387687911 hasConcept C134752490 @default.
- W4387687911 hasConcept C137293760 @default.
- W4387687911 hasConcept C154945302 @default.
- W4387687911 hasConcept C162324750 @default.
- W4387687911 hasConcept C175444787 @default.
- W4387687911 hasConcept C185798385 @default.
- W4387687911 hasConcept C195324797 @default.
- W4387687911 hasConcept C195344581 @default.
- W4387687911 hasConcept C204321447 @default.
- W4387687911 hasConcept C205649164 @default.
- W4387687911 hasConcept C2776436953 @default.
- W4387687911 hasConcept C2779439875 @default.
- W4387687911 hasConcept C41008148 @default.
- W4387687911 hasConcept C43971567 @default.
- W4387687911 hasConcept C539667460 @default.
- W4387687911 hasConcept C774472 @default.
- W4387687911 hasConceptScore W4387687911C109747225 @default.
- W4387687911 hasConceptScore W4387687911C119857082 @default.
- W4387687911 hasConceptScore W4387687911C127413603 @default.
- W4387687911 hasConceptScore W4387687911C13280743 @default.
- W4387687911 hasConceptScore W4387687911C134752490 @default.
- W4387687911 hasConceptScore W4387687911C137293760 @default.
- W4387687911 hasConceptScore W4387687911C154945302 @default.
- W4387687911 hasConceptScore W4387687911C162324750 @default.
- W4387687911 hasConceptScore W4387687911C175444787 @default.
- W4387687911 hasConceptScore W4387687911C185798385 @default.
- W4387687911 hasConceptScore W4387687911C195324797 @default.
- W4387687911 hasConceptScore W4387687911C195344581 @default.
- W4387687911 hasConceptScore W4387687911C204321447 @default.
- W4387687911 hasConceptScore W4387687911C205649164 @default.
- W4387687911 hasConceptScore W4387687911C2776436953 @default.
- W4387687911 hasConceptScore W4387687911C2779439875 @default.
- W4387687911 hasConceptScore W4387687911C41008148 @default.
- W4387687911 hasConceptScore W4387687911C43971567 @default.
- W4387687911 hasConceptScore W4387687911C539667460 @default.
- W4387687911 hasConceptScore W4387687911C774472 @default.
- W4387687911 hasLocation W43876879111 @default.
- W4387687911 hasOpenAccess W4387687911 @default.
- W4387687911 hasPrimaryLocation W43876879111 @default.
- W4387687911 hasRelatedWork W1482728761 @default.
- W4387687911 hasRelatedWork W1510214531 @default.
- W4387687911 hasRelatedWork W2071098659 @default.
- W4387687911 hasRelatedWork W2250460949 @default.
- W4387687911 hasRelatedWork W2351976579 @default.
- W4387687911 hasRelatedWork W2487444950 @default.
- W4387687911 hasRelatedWork W2811486295 @default.
- W4387687911 hasRelatedWork W2948107571 @default.
- W4387687911 hasRelatedWork W3019688513 @default.
- W4387687911 hasRelatedWork W3113264705 @default.
- W4387687911 isParatext "false" @default.
- W4387687911 isRetracted "false" @default.
- W4387687911 workType "article" @default.