Reflection is essential for fostering metacognitive development. However, many learners struggle to engage in meaningful, structured reflection without further support. To support learners in reflective practices, we developed MindBuddy, a learner-centered tutor that guides students individually through reflective writing tasks and provides adaptive feedback. After an iterative user-centered development process (two pilot studies, n=81), we conducted a longitudinal field-experimental classroom study with n=34 undergraduates over a six-week period to compare two different tutoring modalities in MindBuddy (1) interactive conversational tutoring (TG1) with (2) constructive feedback-only (TG2). No significant differences in perceived skills were found, suggesting that the conversational interactions may enhance students’ confidence in their reflective abilities, similarly to adaptive feedback interaction. While differences were found for formal reflective structure, our findings suggest that conversational tutoring has the potential to increase learners’ engagement with reflective writing. Future research on whether such engagement translates into measurable performance gains is necessary.

LLM-based agents improve upon standalone LLMs, which are optimized for immediate intent-satisfaction, by allowing the pursuit of more extended objectives, such as helping users over the long term. To do so, LLM-based agents need to reason before responding. For complex tasks like personalized coaching, this reasoning can be informed by adding relevant information at key moments, shifting it in the desired direction. However, the pursuit of objectives beyond interaction quality may compromise this very quality. Moreover, as the depth and informativeness of reasoning increase, so do the number of tokens required, leading to higher latency and cost. This study investigates how an LLM-based coaching agent can adjust its reasoning depth using a discrepancy mechanism that signals how much reasoning effort to allocate based on how well the objective is being met. Our discrepancy-based mechanism constrains reasoning to better align with alternative objectives, reducing cost roughly tenfold while minimally impacting interaction quality.

Student peer review writing is prevalent and important in education for fostering critical thinking and learning motivation. However, it often entails challenges such as high effort and writer’s block. Leaving students unsupported may thus diminish the efficacy of the process. Large Language Models (LLMs) offer a potential remedy, but their utility hinges on user-centered design. Guided by design-determining constructs from the Cognitive Process Theory of Writing, we developed an intelligent writing support tool to alleviate these challenges, aiding 1) ideation and 2) evaluation. A randomized experiment (n=120) confirmed users were less inclined to utilize the tool’s intelligent features when offered pre-supplied ideas or evaluations, validating our approach. Moreover, students engaged not less but more with their writing if support was available, indicating an enhanced experience. Our research illuminates design choices for enhancing LLM-based tools’ usability and user experience, specifically optimizing intelligent writing support tools to facilitate student peer review.

While writing peer reviews resembles an important task in science, education, and large organizations, providing fruitful suggestions to peers is not a straightforward task, as different user interaction designs of text suggestion interfaces can have diverse effects on user behaviors when writing the review text. Generative language models might be able to support humans in formulating reviews with textual suggestions. Previous systems use two designs for providing text suggestions, but do not empirically evaluate them: inline and list of suggestions. To investigate the effects of embedding NLP text generation models in the two designs, we collected user requirements to implement Hamta as an example of assistants providing reviewers with text suggestions. Our experiment on comparing the two designs on 31 participants indicates that people using the inline interface provided longer reviews on average, while participants using the list of suggestions experienced more ease of use in using our tool. The results shed light on important design findings for embedding text generation models in user-centered assistants.

Natural Language Processing (NLP) has become increasingly utilized to provide adaptivity in educational applications. However, recent research has highlighted a variety of biases in pre-trained language models. While existing studies investigate bias in different domains, they are limited in addressing fine-grained analysis on educational corpora and text that is not English. In this work, we analyze bias across text and through multiple architectures on a corpus of 9,165 German peer-reviews collected from university students over five years. Notably, our corpus includes labels such as helpfulness, quality, and critical aspect ratings from the peer-review recipient as well as demographic attributes. We conduct a Word Embedding Association Test (WEAT) analysis on (1) our collected corpus in connection with the clustered labels, (2) the most common pre-trained German language models (T5, BERT, and GPT-2) and GloVe embeddings, and (3) the language models after fine-tuning on our collected data-set. In contrast to our initial expectations, we found that our collected corpus does not reveal many biases in the co-occurrence analysis or in the GloVe embeddings. However, the pre-trained German language models find substantial conceptual, racial, and gender bias and have significant changes in bias across conceptual and racial axes during fine-tuning on the peer-review data. With our research, we aim to contribute to the fourth UN sustainability goal (quality education) with a novel dataset, an understanding of biases in natural language education data, and the potential harms of not counteracting biases in language models for educational tasks.

Peer feedback in online education becomes increasingly important to meet the demand for feedback in large scale classes, such as e.g. Massive Open Online Courses (MOOCs). However, students are often not experts in how to write helpful feedback to their fellow students. In this paper, we introduce a corpus compiled from university students’ peer feedback to be able to detect suggestions on how to improve the students’ work and therefore being able to capture peer feedback helpfulness. To the best of our knowledge, this corpus is the first student peer feedback corpus in German which additionally was labelled with a new annotation scheme. The corpus consists of more than 600 written feedback (about 7,500 sentences). The utilisation of the corpus is broadly ranged from Dependency Parsing to Sentiment Analysis to Suggestion Mining, etc. We applied the latter to empirically validate the utility of the new corpus. Suggestion Mining is the extraction of sentences that contain suggestions from unstructured text. In this paper, we present a new annotation scheme to label sentences for Suggestion Mining. Two independent annotators labelled the corpus and achieved an inter-annotator agreement of 0.71. With the help of an expert arbitrator a gold standard was created. An automatic classification using BERT achieved an accuracy of 75.3%.