Saved in:
Bibliographic Details
Main Authors: Edgell, James, Kennedy, Wm. Matthew, Pattis, Isaac, Knight, Ben, Carvalho, Danielle, Wonnacott, Elizabeth
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.20088
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911708988047360
author Edgell, James
Kennedy, Wm. Matthew
Pattis, Isaac
Knight, Ben
Carvalho, Danielle
Wonnacott, Elizabeth
author_facet Edgell, James
Kennedy, Wm. Matthew
Pattis, Isaac
Knight, Ben
Carvalho, Danielle
Wonnacott, Elizabeth
contents 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 describe the iteration of the methodology we developed to build L2-Bench, a novel, context-specific 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 = 4.23/5], 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
format Preprint
id arxiv_https___arxiv_org_abs_2603_20088
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Towards an Evaluation Methodology for AI in Second Language Education: Lessons Learned from Developing L2-Bench
Edgell, James
Kennedy, Wm. Matthew
Pattis, Isaac
Knight, Ben
Carvalho, Danielle
Wonnacott, Elizabeth
Computers and Society
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 describe the iteration of the methodology we developed to build L2-Bench, a novel, context-specific 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 = 4.23/5], 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
title Towards an Evaluation Methodology for AI in Second Language Education: Lessons Learned from Developing L2-Bench
topic Computers and Society
url https://arxiv.org/abs/2603.20088