L2-Bench is a new context-specific benchmark for AI in L2 education grounded in a validated language learning experience designer construct, with a pilot study (N=39) showing high task authenticity but poor inter-annotator agreement.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Towards an Evaluation Methodology for AI in Second Language Education: Lessons Learned from Developing L2-Bench
L2-Bench is a new context-specific benchmark for AI in L2 education grounded in a validated language learning experience designer construct, with a pilot study (N=39) showing high task authenticity but poor inter-annotator agreement.