Related papers: One-Topic-Doesn't-Fit-All: Transcreating Reading C…
Adapting questionnaires to new languages is a resource-intensive process often requiring the hiring of multiple independent translators, which limits the ability of researchers to conduct cross-cultural research and effectively creates…
Existing incentive solutions for traditional Federated Learning (FL) focus on individual contributions to a single global objective, neglecting the nuances of clustered personalization with multiple cluster-level models and the non-monetary…
Students are increasingly relying on Generative AI (GAI) to support their writing-a key pedagogical practice in education. In GAI-assisted writing, students can delegate core cognitive tasks (e.g., generating ideas and turning them into…
Long-context modeling presents a significant challenge for transformer-based large language models (LLMs) due to the quadratic complexity of the self-attention mechanism and issues with length extrapolation caused by pretraining exclusively…
Large language models' (LLMs) abilities are drawn from their pretraining data, and model development begins with data curation. However, decisions around what data is retained or removed during this initial stage are under-scrutinized. In…
Learning is most effective when it's connected to relevant, relatable examples that resonate with learners on a personal level. However, existing educational AI tools don't focus on generating examples or adapting to learners' changing…
Suggested questions (SQs) provide an effective initial interface for users to engage with their documents in AI-powered reading applications. In practical reading sessions, users have diverse backgrounds and reading goals, yet current SQ…
Query-specific article generation is the task of, given a search query, generate a single article that gives an overview of the topic. We envision such articles as an alternative to presenting a ranking of search results. While generative…
Personalized federated learning (PFL) studies effective model personalization to address the data heterogeneity issue among clients in traditional federated learning (FL). Existing PFL approaches mainly generate personalized models by…
The integration of generative AI in education is expanding, yet empirical analyses of large-scale, real-world interactions between students and AI systems still remain limited. In this study, we present ChEDDAR, ChatGPT & EFL Learner's…
Automated question generation is an important approach to enable personalisation of English comprehension assessment. Recently, transformer-based pretrained language models have demonstrated the ability to produce appropriate questions from…
In the realm of education, student evaluation holds equal significance to imparting knowledge. To be evaluated, students usually need to go through text-based academic assessment methods. Instructors need to make a diverse set of questions…
This study examined intermittent discontinuance in AI-mediated informal digital learning of English (AI-IDLE) through the cognition-affect-conation framework. Survey data were collected from 632 Chinese university EFL learners with prior…
This work contributes to the scarce empirical literature on LLM-based interactive homework in real-world educational settings and offers a practical, scalable solution for improving homework in schools. Homework is an important part of…
Pre-trained Language Models (PLMs) have achieved great success on Machine Reading Comprehension (MRC) over the past few years. Although the general language representation learned from large-scale corpora does benefit MRC, the poor support…
"Explain in Plain English" (EiPE) questions are widely used to assess code comprehension skills but are challenging to grade automatically. Recent approaches like Code Generation Based Grading (CGBG) leverage large language models (LLMs) to…
In real-world federated learning scenarios, participants could have their own personalized labels which are incompatible with those from other clients, due to using different label permutations or tackling completely different tasks or…
Recent advancements in Natural Language Processing (NLP) have led to the development of NLP-based recommender systems that have shown superior performance. However, current models commonly treat items as mere IDs and adopt discriminative…
Tackling non-IID data is an open challenge in federated learning research. Existing FL methods, including robust FL and personalized FL, are designed to improve model performance without consideration of interpreting non-IID across clients.…
Computational understanding of humor is an important topic under creative language understanding and modeling. It can play a key role in complex human-AI interactions. The challenge here is that human perception of humorous content is…