Paper
Beyond Accuracy: Towards a Robust Evaluation Methodology for AI Systems for Language Education
Authors
James Edgell, Wm. Matthew Kennedy, Isaac Pattis, Ben Knight, Danielle Carvalho, Elizabeth Wonnacott
Abstract
The rapid adoption of large language models in AI-powered language education has created an urgent need for evaluations that assess pedagogical effectiveness, particularly in language learning--one of the most common LLM use cases (Tamkin et al. 2024, Costa-Gomes et al. 2025). With only narrowly defined task-specific evaluations of AI system capabilities in second language (L2) education existing in the literature, we require more holistic approaches in this AI for education space. To address this gap, we introduce L2-Bench, a novel evaluation benchmark grounded in a validated "language learning experience designer" construct to assess AI capabilities across L2 education contexts. Our methodology integrates pedagogical theory, sociotechnical AI evaluation methods, and operationalizes a hierarchical taxonomy to structure an expert-curated dataset of over 1,000 authentic rubric-scored task-response pairs with measurement and scoring pipeline. We report the results of a pilot validation exercise (N = 39) on an initial sample of our dataset (tasks were validated as authentic [M = 4.23 out of 5], but criteria scores were lower [M = 3.94], with universally poor inter-annotator agreement despite good internal consistency), alongside the experimental design for our follow-up practitioner data validation study as we iterate and scale to the full dataset. Ultimately, this research not only offers methodological lessons towards a more context-specific AI evaluations ecosystem, but also works towards better design of reproducible evaluations for AI systems deployed to educational contexts.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.20088v1</id>\n <title>Beyond Accuracy: Towards a Robust Evaluation Methodology for AI Systems for Language Education</title>\n <updated>2026-03-20T16:13:03Z</updated>\n <link href='https://arxiv.org/abs/2603.20088v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.20088v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>The rapid adoption of large language models in AI-powered language education has created an urgent need for evaluations that assess pedagogical effectiveness, particularly in language learning--one of the most common LLM use cases (Tamkin et al. 2024, Costa-Gomes et al. 2025). With only narrowly defined task-specific evaluations of AI system capabilities in second language (L2) education existing in the literature, we require more holistic approaches in this AI for education space. To address this gap, we introduce L2-Bench, a novel evaluation benchmark grounded in a validated \"language learning experience designer\" construct to assess AI capabilities across L2 education contexts. Our methodology integrates pedagogical theory, sociotechnical AI evaluation methods, and operationalizes a hierarchical taxonomy to structure an expert-curated dataset of over 1,000 authentic rubric-scored task-response pairs with measurement and scoring pipeline. We report the results of a pilot validation exercise (N = 39) on an initial sample of our dataset (tasks were validated as authentic [M = 4.23 out of 5], but criteria scores were lower [M = 3.94], with universally poor inter-annotator agreement despite good internal consistency), alongside the experimental design for our follow-up practitioner data validation study as we iterate and scale to the full dataset. Ultimately, this research not only offers methodological lessons towards a more context-specific AI evaluations ecosystem, but also works towards better design of reproducible evaluations for AI systems deployed to educational contexts.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CY'/>\n <published>2026-03-20T16:13:03Z</published>\n <arxiv:primary_category term='cs.CY'/>\n <author>\n <name>James Edgell</name>\n </author>\n <author>\n <name>Wm. Matthew Kennedy</name>\n </author>\n <author>\n <name>Isaac Pattis</name>\n </author>\n <author>\n <name>Ben Knight</name>\n </author>\n <author>\n <name>Danielle Carvalho</name>\n </author>\n <author>\n <name>Elizabeth Wonnacott</name>\n </author>\n </entry>"
}