We present the framework Omethi, which is aimed at scoring short text responses in a semi-automatic fashion, particularly fit to international large-scale assessments. We evaluate its effectiveness for the massively multilingual PISA tests. Responses are passed through a conditional flow of hierarchically combined scoring components to assign a score. Once a score is assigned, hierarchically lower components are discarded. Models implemented in this study ranged from lexical matching of normalized texts—with excellent accuracy but weak generalizability—to fine-tuned large language models—with lower accuracy but high generalizability. If not scored by any automatic component, responses are passed on to manual scoring. The paper is the first to provide an evaluation of automatic scoring on multilingual PISA data in eleven languages (including Arabic, Finnish, Hebrew, and Kazakh) from three domains (_n_ = 3.8 million responses). On average, results show a manual effort reduction of 71 percent alongside an agreement of _κ_ = .957, when including manual scoring, and _κ_ = .804 for only the automatically scored responses. The evaluation underscores the framework’s effective adaptivity and operational feasibility with its shares of used components varying substantially across domains and languages while maintaining homogeneously high accuracy.

This paper presents our contribution to the BEA 2025 Shared Task on Pedagogical Ability Assessment of AI-Powered Tutors. The objective of this shared task was to assess the quality of conversational feedback provided by LLM-based math tutors to students regarding four facets: whether the tutors 1) identified mistakes, 2) identified the mistake’s location, 3) provided guidance, and whether they 4) provided actionable feedback. To leverage information across all four labels, we approached the problem with FLAN-T5 models, which we fit for this task using a multi-step pipeline involving regular fine-tuning as well as model merging using the DARE-TIES algorithm. We can demonstrate that our pipeline is beneficial to overall model performance compared to regular fine-tuning. With results on the test set ranging from 52.1 to 68.6 in F1 scores and 62.2% to 87.4% in accuracy, our best models placed 11th of 44 teams in Track 1, 8th of 31 teams in Track 2, 11th of 35 teams in Track 3, and 9th of 30 teams in Track 4. Notably, the classifiers’ recall was relatively poor for underrepresented classes, indicating even greater potential for the employed methodology.

This paper describes a contribution to the BEA 2024 Shared Task on Automated Prediction of Item Difficulty and Response Time. The participants in this shared task are to develop models for predicting the difficulty and response time of multiple-choice items in the medical field. These items were taken from the United States Medical Licensing Examination® (USMLE®), a high-stakes medical exam. For this purpose, we evaluated multiple BERT-like pre-trained transformer encoder models, which we combined with Scalar Mixing and two custom 2-layer classification heads using learnable Rational Activations as an activation function, each for predicting one of the two variables of interest in a multi-task setup. Our best models placed first out of 43 for predicting item difficulty and fifth out of 34 for predicting Item Response Time.

In this paper, we present our systems submitted to SemEval-2021 Task 1 on lexical complexity prediction. The aim of this shared task was to create systems able to predict the lexical complexity of word tokens and bigram multiword expressions within a given sentence context, a continuous value indicating the difficulty in understanding a respective utterance. Our approach relies on gradient boosted regression tree ensembles fitted using a heterogeneous feature set combining linguistic features, static and contextualized word embeddings, psycholinguistic norm lexica, WordNet, word- and character bigram frequencies and inclusion in wordlists to create a model able to assign a word or multiword expression a context-dependent complexity score. We can show that especially contextualised string embeddings can help with predicting lexical complexity.

In this paper, we present MultiVitaminBooster, a system implemented for the PARSEME shared task on semi-supervised identification of verbal multiword expressions - edition 1.2. For our approach, we interpret detecting verbal multiword expressions as a token classification task aiming to decide whether a token is part of a verbal multiword expression or not. For this purpose, we train gradient boosting-based models. We encode tokens as feature vectors combining multilingual contextualized word embeddings provided by the XLM-RoBERTa language model with a more traditional linguistic feature set relying on context windows and dependency relations. Our system was ranked 7th in the official open track ranking of the shared task evaluations with an encoding-related bug distorting the results. For this reason we carry out further unofficial evaluations. Unofficial versions of our systems would have achieved higher ranks.