Tag
This paper proposes a multi-agent embodied conversational system that generates level-appropriate dialogue for English learners using a generate-evaluate-regenerate loop with LLMs and a CEFR classifier. A pilot study with Japanese university students showed improved level appropriateness but no statistically significant reduction in foreign language anxiety.
Introduces ComplexityMT, a benchmark for evaluating the interaction between text complexity and machine translation across six languages using CEFR levels, showing that higher complexity makes translation harder and that MT shifts complexity levels.