This paper seeks to quantify and analyse the progress that ChatGPT has made from its GPT-3.5 (2022) to its GPT-4.5 (2025) version when it comes to answering prompts in a selection of differently-resourced languages: English, Bulgarian, Greek, French, Hebrew, Japanese and Russian. Factual correctness, textual quality and an answer’s linguistic and cultural independence from an English baseline are evaluated in the process. Each response is marked positively or negatively for each of the three metrics based on a set of defined criteria and careful humanbased analysis. In addition, three categories of questions are experimented with: general (e.g. communication assistance or request for jokes), perception-related (e.g. creative writing or explanation of physical processes) and geography-/culture-sensitive (questions in a specific language that address a particular, slightly sensitive topic related to the implied audience e.g. ’Why do French people eat snails?’). As hypothesised, the recent GPT-4.5 version demonstrates significant progress in all evaluated categories, thereby resolving past issues such as decreased textual quality of low-resourced languages and, notably, very limited variety in answers to the same question across languages. The metric ’Independence from the (English) Baseline’ receives 80.95% of positive marks in the GPT-4.5 version as opposed to 26.19% for GPT-3.5. Lingering problems include ChatGPT’s incomplete ability to generate relevant and culturally-sensitive jokes and poems.

This is a short paper describing the process of derivation of synthetic Judeo-French text. Judeo-French is one of a number of rare languages used in speaking and writing by Jewish communities as confined to a particular temporal and geographical frame (in this case, 11th- to 14th-century France). The number of resources in the language is very limited and its involvement in the contemporary domain of Natural Language Processing (NLP) is practically non-existent. This work outlines the compilation of a synthetic Judeo-French corpus. For the purpose, a pipeline of transformations is applied to Old French text belonging to the same general time period, leading to the derivation of text that is as reliable as possible in terms of phonological, morphological and lexical characteristics as witnessed in Judeo-French. Ultimately, the goal is for this synthetic corpus to be used in standard NLP tasks, such as Neural Machine Translation (NMT), as an instance of data augmentation.

Within the framework of this study, several contemporary Large Language Models (ChatGPT, Gemini Pro, Mistral-Instruct and BgGPT) are evaluated in relation to their ability to generate abridged versions of literary texts. The analysis is based on ’The Ugly Duckling’ by H. C. Andersen as translated into English, French and Bulgarian. The different scenarios of abridgement experimented with include zero-shot, one-shot, division into chunks and crosslingual (including chain-of-thought) abridgement. The resulting texts are evaluated both automatically and via human evaluation. The automatic analysis includes ROUGE and BERTScore as well as the ratios of a selection of readability-related textual features (e.g. number of words, type-to-token ratio) as pertaining to the original versus automatically abridged texts. Professionally composed abridged versions are regarded as gold standard. Following the automatic analysis, six selected best candidate texts per language are then evaluated by volunteers with university education in terms of textual characteristics of a more qualitative nature, such as coherence, consistency and aesthetic appeal.

Psycholinguistics speaks of a fine-tuning process used by parents as they address children, in which complex vocabulary is introduced with additional context (Leung et al., 2021). This somewhat counterintuitive lengthening of text in order to aid one’s interlocutor in the process of language acquisition also comes in accord with Harris (1988)’s notion that for every complex sentence, there is an equivalent longer (non-contracted) yet simpler one that contains the same amount of information. Within the proposed work, a corpus of eight renowned literary works (e.g. Alice’s Adventures in Wonderland, The Adventures of Tom Sawyer, Les Misérables) in four distinct languages (English, French, Russian and Spanish) is gathered: both the original (or translated) versions and up to four abridged versions for various audiences (e.g. children of a defined age or foreign language learners of a defined level) are present. The contexts of the first appearance of complex words (as determined based on word frequency) in pairs of original and abridged works are compared, and the cases in which the abridged texts offer longer context are investigated. The discovered transformations are consequently classified into three separate categories: addition of vocabulary items from the same lexical field as the complex word, simplification of grammar and insertion of a definition. Context extensions are then statistically analysed as associated with different languages and reader audiences.