Scale: Scaling up the complexity for advanced language model evaluation
Recent strides in Large Language Models (LLMs) have saturated many NLP benchmarks
(even professional domain-specific ones), emphasizing the need for novel, more …
(even professional domain-specific ones), emphasizing the need for novel, more …
Prompting strategies for citation classification
Citation classification aims to identify the purpose of the cited article in the citing article.
Previous citation classification methods rely largely on supervised approaches. The models …
Previous citation classification methods rely largely on supervised approaches. The models …
A First Step towards Measuring Interdisciplinary Engagement in Scientific Publications: A Case Study on NLP+ CSS Research
With the rise in the prevalence of cross-disciplinary research, there is a need to develop
methods to characterize its practices. Current computational methods to evaluate …
methods to characterize its practices. Current computational methods to evaluate …
[PDF][PDF] On the use of language models for function identification of citations in scholarly papers
T Ikoma, S Matsubara - Proceedings of the Second Workshop on …, 2023 - aclanthology.org
Citation graphs represent the citation relations between papers, and they are commonly
used by researchers to identify relevant papers. However, citation graphs do not always …
used by researchers to identify relevant papers. However, citation graphs do not always …
Micro Citation Importance Identification and Its Application to Literature Evaluation
W Nie, S Ou - International Conference on Information, 2024 - Springer
We present our approach for identifying the importance of citing sentences, where the
importance of citing sentences is termed “micro citation importance” in our research. This …
importance of citing sentences is termed “micro citation importance” in our research. This …
Prompting Strategies for Citation Classification
Citation classification aims to identify the purpose of the cited article in the citing article.
Previous citation classification methods rely largely on supervised approaches. The models …
Previous citation classification methods rely largely on supervised approaches. The models …
[CITATION][C] SciConBERT: A Dynamic Citation Context Extraction Model Using Siamese BERT
LM Jantsch, J Lee, J Thomas, J Cheong… - 한국정보과학회 학술발표 …, 2024 - dbpia.co.kr
Despite the fundamental role of citations in the scientific literature, the analysis of the text
span associated with a citation, the so-called citation context, is poorly researched and …
span associated with a citation, the so-called citation context, is poorly researched and …