Related papers: BD at BEA 2025 Shared Task: MPNet Ensembles for Pe…

This paper presents our system for Track 1: Mistake Identification in the BEA 2025 Shared Task on Pedagogical Ability Assessment of AI-powered Tutors. The task involves evaluating whether a tutor's response correctly identifies a mistake in…

This shared task has aimed to assess pedagogical abilities of AI tutors powered by large language models (LLMs), focusing on evaluating the quality of tutor responses aimed at student's mistake remediation within educational dialogues. The…

We present MSA-MathEval, our submission to the BEA 2025 Shared Task on evaluating AI tutor responses across four instructional dimensions: Mistake Identification, Mistake Location, Providing Guidance, and Actionability. Our approach uses a…

This paper describes the results of the first shared task on the generation of teacher responses in educational dialogues. The goal of the task was to benchmark the ability of generative language models to act as AI teachers, replying to a…

This paper presents the ADAIO team's system entry in the Building Educational Applications (BEA) 2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues. The task aims to assess the performance of state-of-the-art…

Evaluating AI tutor responses requires more than factual correctness: tutors must identify mistakes, locate errors, provide guidance, and offer actionable next steps. We present GRADE, a systematic study of open-source models for…

Evaluating the pedagogical quality of AI tutors remains challenging: standard NLG metrics do not determine whether responses identify mistakes, scaffold reasoning, or avoid revealing the answers. For the task of mistake remediation, we…

In this paper, we investigate whether current state-of-the-art large language models (LLMs) are effective as AI tutors and whether they demonstrate pedagogical abilities necessary for good AI tutoring in educational dialogues. Previous…

With the rapid development of ICT Custom Services (ICT CS) in power industries, the deployed power ICT CS systems mainly rely on the experience of customer service staff for fault type recognition, questioning, and answering, which makes it…

Timely and accurate identification of student misconceptions is key to improving learning outcomes and pre-empting the compounding of student errors. However, this task is highly dependent on the effort and intuition of the teacher. In this…

K-12 classrooms consistently integrate collaboration as part of their learning experiences. However, owing to large classroom sizes, teachers do not have the time to properly assess each student and give them feedback. In this paper we…

This paper introduces the Budding Ensemble Architecture (BEA), a novel reduced ensemble architecture for anchor-based object detection models. Object detection models are crucial in vision-based tasks, particularly in autonomous systems.…

In this work, we study computational approaches to detect online dialogic instructions, which are widely used to help students understand learning materials, and build effective study habits. This task is rather challenging due to the…

Intelligent tutoring systems increasingly provide automated feedback on student work, but robust feedback requires assessing reasoning, not only final answers. We study a failure mode we call the correct answer trap (CAT): models…

Evaluating the pedagogical capabilities of AI-based tutoring models is critical for making guided progress in the field. Yet, we lack a reliable, easy-to-use, and simple-to-run evaluation that reflects the pedagogical abilities of models.…

Identifying breakdowns in ongoing dialogues helps to improve communication effectiveness. Most prior work on this topic relies on human annotated data and data augmentation to learn a classification model. While quality labeled dialogue…

The Circuit Localization track of the Mechanistic Interpretability Benchmark (MIB) evaluates methods for localizing circuits within large language models (LLMs), i.e., subnetworks responsible for specific task behaviors. In this work, we…

Adaptive scaffolding enhances learning, yet the field lacks robust methods for measuring it within authentic tutoring dialogue. This gap has become more pressing with the rise of remote human tutoring and large language model-based systems.…

We present an empirical study of how both experienced tutors and non-tutors judge the correctness of tutor praise responses under different Artificial Intelligence (AI)-assisted interfaces, types of explanation (textual explanations vs.…

People use search engines for various topics and items, from daily essentials to more aspirational and specialized objects. Therefore, search engines have taken over as peoples preferred resource. The How To prefix has become familiar and…