AALA Student Committee Webinar in May 2026
AI and Language Assessment
The AALA Student Committee warmly invites you to its second webinar of AALA 2026, focusing on AI and Language Assessment. This webinar features two invited speakers, Dr. Olena Rossi, independent assessment consultant, and Dr. Sha Liu, Test Development Researcher at the British Council. Drawing on their research and professional experience, the speakers will discuss current opportunities and unresolved challenges in the use of generative AI in language assessment, with particular attention to AI-assisted item writing, AI-mediated speaking assessment, prompt design, construct realisation, and the continuing role of human expert judgement in responsible assessment practice
Mode
Online
Date & Time
Tuesday, May 26, 2026
04:00 am EDT
09:00 am BST, England
01:30 pm IST, India
03:00 pm ICT, Thailand / Jakarta
04:00 pm China / Malaysia / Singapore
05:00 pm Japan / South Korea
06:00 pm Melbourne / Sydney
Location
Speakers
Dr. Olena Rossi
Independent Assessment Consultant
Generative AI for item writing: outstanding questions and future directions
Abstract:
The presentation will examine key challenges in the use of generative AI for language test item writing as well as future directions for AI use. It will first address two unresolved and seldom discussed issues that impact on the quality of AI-produced items: the lack of high-quality training data for fine-tuning large language models, and the absence of valid automated item evaluation metrics capable of replacing human judgement. It will then explore ways to enhance AI performance, arguing that improving output quality will increasingly depend on redesigning item-generation workflows rather than on refining prompts alone.
Olena Rossi holds a PhD in Language Testing from Lancaster University (UK) and works as an independent assessment consultant, based in Italy. She specialises in item writing for language assessment and regularly delivers item-writing workshops as well as provides consultancy support to organisations involved in test development worldwide. Olena’s current research interests centre on the applications of AI to the language test development process. Olena is a founding convenor of the AI for Language Assessment Special Interest Group within the European Association for Language Testing and Assessment (EALTA). Her work and publications can be accessed from her website https://itemwriting.co
Dr. Sha Liu
Test Development Researcher, British Council
When the chatbot says "um": Prompting, construct realisation, and the human-in-the-loop in AI-mediated L2 speaking
Abstract:
Generative AI-powered chatbots are increasingly positioned as speaking partners in L2 practice and assessment. This raises a question with consequences for what we measure: can a prompted chatbot serve as an authentic interlocutor? And on whose judgement? This talk pursues two aims. First, it sketches what is currently known about human–AI interaction patterns and the prompting strategies that shape them. Second, it shares hands-on insights from real-life speaking assessment design. Through worked examples, the talk shows how small prompting choices can either produce or distort the interactional and fluency features the construct is meant to capture. In each case, human expert judgement is what keeps the prompt-to-construct cycle on track. Reflecting on the key layers of construct alteration in the assessment development process, and on the continuum of construct transformation in the AI-mediated speaking era, the talk argues that prompts are not peripheral tooling but construct-shaping instruments. Responsible AI-mediated speaking assessment therefore depends on keeping the human, equipped with AI literacy, firmly in the loop.
Dr Sha Liu is a Test Development Researcher at the British Council. She holds a PhD in Language Assessment from the University of Bristol, and her research focuses on AI-mediated speaking and writing assessment, with particular emphasis on multimodal speaking assessment using generative AI, automated diagnostic feedback for language learners, and eye-tracking methodologies for understanding learner engagement. Her commitment to inclusive assessment practices centres on developing AI-based systems that provide equitable feedback across diverse learner backgrounds.
Dr Liu is Co-Convenor of the EALTA AI for Language Assessment Special Interest Group, and serves on editorial boards for Language Assessment Quarterly, Assessing Writing, Research Synthesis in Applied Linguistics and Artificial Intelligence in Language Education.
