This study investigates whether human–LLM interaction in academic writing exhibits cross-cultural variation. Using NLP-informed corpus methods, we analyze nine semi-structured student interviews from three national contexts (Romania, Bulgaria, Switzerland) to examine how AI use is linguistically constructed across three dimensions of epistemic positioning: agency strength, authority dynamics, and discourse-level stance. Results show a strong predominance of distancing and hedging strategies, with AI consistently framed as a functional writing support tool rather than an epistemic authority. At the same time, modest but systematic cross-country differences indicate culturally embedded variation in how students discursively negotiate epistemic responsibility and evaluation in AI-assisted writing practices.

Translation can systematically alter text difficulty, particularly when moving into morphologically rich languages. This study examines whether readability-constrained Large Language Models (LLMs) can mitigate difficulty shifts observed in English–Romanian translation of children’s literature. We construct a paired four-condition corpus comprising English originals, published Romanian translations, readability-constrained LLM translations, and human readability adaptations (12 aligned passages; approx. 23,000 words). Readability is assessed using a Romanian grade-level index (LEMI) designed to be educationally comparable to Flesch–Kincaid Grade Level (FKGL), the cross-linguistic LIX metric, and morphologically informed measures derived from spaCy. Published Romanian translations are significantly more difficult than their English originals, showing higher LIX scores, grade-level estimates, and increased morphological variation. Readability-constrained LLM translation substantially reduces difficulty relative to the published versions (median delta approx. −1.46 grade levels), with significant decreases in LIX, morphological feature density, and lexical diversity (MTLD). Human adaptation yields a smaller reduction (median delta approx. −0.26). Although the direct comparison between LLM and human adaptation is marginal (p = .055, r = 0.64), LLM outputs generally produce larger reductions. These findings demonstrate that translation-induced difficulty shifts are measurable and that controllable LLM translation can modulate readability across structural, lexical, and morphological dimensions in multilingual educational contexts.

Access to age-appropriate texts is critical for young readers’ literacy acquisition. For limited-resourced languages, such as Romanian, this area remains under-researched. As such, we present ongoing work on improving readability for old Romanian texts by applying Large Language Models (LLMs). First, we compiled and cleaned a comprehensive list of archaic and regional terms from lexicographic sources, including DEX online and printed dictionaries. The cleaning process involved duplicate removal, orthographic normalization, context-based filtering, and manual review. Key challenges included distinguishing archaic forms from rare or poetic ones, resolving polysemous entries, and managing inconsistent labeling across sources. Second, LLMs were utilized to validate the archaic and regional nature of identified terms and replace them with modern equivalents, while also determining the appropriate reading level for both original and modified versions. Results show that through the replacement of archaic and regional terms, the appropriate age for the modified texts decreases by approximately 0.5 years for texts extracted from textbooks and canonical writings.

This paper presents a data-driven analysis of Romanian secondary school textbooks through the lens of Bloom’s Taxonomy, focusing on the promotion of critical thinking in instructional design. Using the ROTEX corpus, we extract and annotate almost 2 million words of Romanian Language and Literature textbooks (grades 5-8) with Bloom-aligned labels for verbs associated with pedagogical tasks. Our annotation pipeline combines automatic verb extraction, human filtering based on syntactic form and task relevance, and manual assignment of Bloom labels supported by in-text concordance checks. The resulting dataset enables fine-grained analysis of task complexity both across and within textbooks and grade levels. Our findings reveal a general lack of structured cognitive progression across most textbook series. We also propose a multi-dimensional framework combining cognitive-level and linguistic evaluation to assess instructional design quality. This work contributes annotated resources and reproducible methods for NLP-based educational content analysis in low-resource languages.

Readability is a crucial characteristic of texts, greatly influencing comprehension and reading efficacy. Unfortunately, limited research is available for less-resourced languages, especially for young populations where its impact is even higher. This paper introduces a new readability tool for children’s literature in the Romanian language, explicitly targeting primary school students aged 7-11. The tool consists of a digital repository of school reading texts (self-compiled corpus) and a text analysis interface that generates automatic readability reports for uploaded short texts. The methodology involves extracting, testing, and calibrating a readability formula for Romanian using the children’s literature corpus. Related work on readability and readability tools is discussed, followed by a description of the children’s literature corpus and the platform functionalities. The first steps are presented towards validating the readability formula for children’s literature in Romanian using the ReaderBench framework, while calibration variables relevant to the Romanian language and children’s literature are examined. Currently, no existing platform integrates a research-based readability formula for the Romanian language, making this tool unique. Overall, this research contributes to applied corpus linguistics and Digital Humanities studies and offers a valuable resource for educators, parents, and children in accessing age-appropriate and readable texts.

The lack of NLP based research studies on academic writing in Romania results in an unbalanced development of automatic support tools in Romanian compared to other languages, such as English. For this study, we use Romanian subsets of two bilingual academic writing corpora: the ROGER corpus, consisting of university student papers, and the EXPRES corpus, composed of expert research articles. Working with the Romanian Academic Word List / RoAWL, we present two phrase extraction phases: (i) use Ro-AWL words as node words to extract collocations according to the thresholds of statistical measures and (ii) classify extracted phrases into general versus domain-specific multi-word units. We show how manual rhetorical function annotation of resulting phrases can be combined with automatic function detection. The comparison between academic phrases in ROGER and EXPRES validates the final phrase list. The Romanian phrasal academic lexicon (ROPAL), similar to the Oxford Phrasal Academic Lexicon (OPAL), is a written academic phrase lexicon for Romanian language made available for academic use and further research or applications.

This paper presents the methodology and data used for the automatic extraction of the Romanian Academic Word List (Ro-AWL). Academic Word Lists are useful in both L2 and L1 teaching contexts. For the Romanian language, no such resource exists so far. Ro-AWL has been generated by combining methods from corpus and computational linguistics with L2 academic writing approaches. We use two types of data: (a) existing data, such as the Romanian Frequency List based on the ROMBAC corpus, and (b) self-compiled data, such as the expert academic writing corpus EXPRES. For constructing the academic word list, we follow the methodology for building the Academic Vocabulary List for the English language. The distribution of Ro-AWL features (general distribution, POS distribution) into four disciplinary datasets is in line with previous research. Ro-AWL is freely available and can be used for teaching, research and NLP applications.

The present paper aims to describe the collection of ParlaMint-RO corpus and to analyse several trends in parliamentary debates (plenary sessions of the Lower House) held in between 2000 and 2020). After a short description of the data collection (of existing transcripts), the workflow of data processing (text extraction, conversion, encoding, linguistic annotation), and an overview of the corpus, the paper will move on to a multi-layered linguistic analysis to validate interdisciplinary perspectives. We use computational methods and corpus linguistics approaches to scrutinize the future tense forms used by Romanian speakers, in order to create a data-supported profile of the parliamentary group strategies and planning.

Field Specific Expert Scientific Writing in English as a Lingua Franca is essential for the effective research networking and dissemination worldwide. Extracting the linguistic profile of the research articles written in L2 English can help young researchers and expert scholars in various disciplines adapt to the scientific writing norms of their communities of practice. In this exploratory study, we present and test an automated linguistic assessment model that includes features relevant for the cross-disciplinary second language framework: Text Complexity Analysis features, such as Syntactic and Lexical Complexity, and Field Specific Academic Word Lists. We analyse how these features vary across four disciplinary fields (Economics, IT, Linguistics and Political Science) in a corpus of L2-English Expert Scientific Writing, part of the EXPRES corpus (Corpus of Expert Writing in Romanian and English). The variation in field specific writing is also analysed in groups of linguistic features extracted from the higher visibility (Hv) versus lower visibility (Lv) journals. After applying lexical sophistication, lexical variation and syntactic complexity formulae, significant differences between disciplines were identified, mainly that research articles from Lv journals have higher lexical complexity, but lower syntactic complexity than articles from Hv journals; while academic vocabulary proved to have discipline specific variation.