CALaMo: a Constructionist Assessment of Language Models
It provides a novel evaluation method for language models, potentially benefiting linguists and AI researchers, but appears incremental as it builds on existing constructionist approaches.
The paper introduces CALaMo, a constructionist framework for evaluating neural language models' linguistic abilities, emphasizing meaning as a determinant factor in analysis.
This paper presents a novel framework for evaluating Neural Language Models' linguistic abilities using a constructionist approach. Not only is the usage-based model in line with the underlying stochastic philosophy of neural architectures, but it also allows the linguist to keep meaning as a determinant factor in the analysis. We outline the framework and present two possible scenarios for its application.