Brain and Mind Institute, The Chinese University of Hong Kong, Hong Kong, Hong Kong SAR, China. Correspondence should be addressed to Zhenguang G. Cai, Department of Linguistics and Modern Languages, Leung Kau Kui Building, The Chinese University of Hong Kong, Shatin, Hong Kong SAR; zhenguangcai@cuhk.edu.hk. Abstract: Large l anguage m odels have achieved impressive progress in multilingual translation, yet they continue to face challenges with certain language pairs --particularly those with limited training data or significant linguistic divergence from English. This study systematically investigates how training data, language proximity, and language family affect information loss in multilingual translation . We evaluate two large language model s, GPT - 4 and Llama 2, by performing round-trip translation s . Translation quality was assessed using BLEU scores and BERT similarity metrics. Our results reveal a robust interaction between training data size and language distance: while abundant training data can mitigate the effects of linguistic divergence, languages structurally closer to English consistently yield higher translation quality in low - resource conditions. Among various distance metrics, orthographic, phylogenetic, syntactic, and geographical distances emerge as strong predictors of translation performance. L anguage family also exert s an independent influence. These findings contribute to a deeper understanding of the linguistic constraints shaping multilingual translation in large language models, emphasizing that translation quality is shaped not only by data volume but also by structural and typological relationships between languages. 1 INTRODUCTION Large Language Models (LLMs) demonstrated advanced multilingual capabilities.

We argue that viewing AI as a simple reduction in input costs overlooks two critical dynamics: (a) the inherent trade-offs among generality, accuracy, and simplicity, and (b) the redistribution of complexity across stakeholders. While LLMs appear to defy the traditional trade-off by offering high generality and accuracy through simple interfaces, this user-facing simplicity masks a significant shift of complexity to infrastructure, compliance, and specialized personnel. The GAS trade-off, therefore, does not disappear but is relocated from the user to the organization, creating new managerial challenges, particularly around accuracy in high-stakes applications. We contend that competitive advantage no longer stems from mere AI adoption, but from mastering this redistributed complexity through the design of abstraction layers, workflow alignment, and complementary expertise.

This study explores Machine Translationese (MTese) -- the linguistic peculiarities of machine translation outputs -- focusing on the under-researched English-to-Chinese language pair in news texts. We construct a large dataset consisting of 4 sub-corpora and employ a comprehensive five-layer feature set. Then, a chi-square ranking algorithm is applied for feature selection in both classification and clustering tasks. Our findings confirm the presence of MTese in both Neural Machine Translation systems (NMTs) and Large Language Models (LLMs). Original Chinese texts are nearly perfectly distinguishable from both LLM and NMT outputs. Notable linguistic patterns in MT outputs are shorter sentence lengths and increased use of adversative conjunctions. Comparing LLMs and NMTs, we achieve approximately 70% classification accuracy, with LLMs exhibiting greater lexical diversity and NMTs using more brackets. Additionally, translation-specific LLMs show lower lexical diversity but higher usage of causal conjunctions compared to generic LLMs. Lastly, we find no significant differences between LLMs developed by Chinese firms and their foreign counterparts.

This study focuses on evaluating the performance of machine translations (MTs) compared to human translations (HTs) in English-to-Chinese children's literature translation (CLT) from a stylometric perspective. The research constructs a Peter Pan corpus, comprising 21 translations: 7 human translations (HTs), 7 large language model translations (LLMs), and 7 neural machine translation outputs (NMTs). The analysis employs a generic feature set (including lexical, syntactic, readability, and n-gram features) and a creative text translation (CTT-specific) feature set, which captures repetition, rhythm, translatability, and miscellaneous levels, yielding 447 linguistic features in total. Using classification and clustering techniques in machine learning, we conduct a stylometric analysis of these translations. Results reveal that in generic features, HTs and MTs exhibit significant differences in conjunction word distributions and the ratio of 1-word-gram-YiYang, while NMTs and LLMs show significant variation in descriptive words usage and adverb ratios. Regarding CTT-specific features, LLMs outperform NMTs in distribution, aligning more closely with HTs in stylistic characteristics, demonstrating the potential of LLMs in CLT.

Backtranslation BT is widely used in low resource machine translation MT to generate additional synthetic training data using monolingual corpora. While this approach has shown strong improvements for many language pairs, its effectiveness in high quality, low resource settings remains unclear. In this work, we explore the effectiveness of backtranslation for English Gujarati translation using the multilingual pretrained MBART50 model. Our baseline system, trained on a high quality parallel corpus of approximately 50,000 sentence pairs, achieves a BLEU score of 43.8 on a validation set. We augment this data with carefully filtered backtranslated examples generated from monolingual Gujarati text. Surprisingly, adding this synthetic data does not improve translation performance and, in some cases, slightly reduces it. We evaluate our models using multiple metrics like BLEU, ChrF++, TER, BLEURT and analyze possible reasons for this saturation. Our findings suggest that backtranslation may reach a point of diminishing returns in certain low-resource settings and we discuss implications for future research.

Language models (LMs) have demonstrated remarkable capabilities in NLP, yet adapting them efficiently and robustly to specific tasks remains challenging. As their scale and complexity grow, fine-tuning LMs on labelled data often underutilizes available unlabelled data, leads to overfitting on small task-specific sets, and imposes significant computational costs. These limitations hamper their application to the open-ended landscape of real-world language tasks. This thesis proposes a series of methods to better adapt LMs to downstream applications. First, we explore strategies for extracting task-relevant knowledge from unlabelled data, introducing a novel continued pre-training technique that outperforms state-of-the-art semi-supervised approaches. Next, we present a parameter-efficient fine-tuning method that substantially reduces memory and compute costs while maintaining competitive performance. We also introduce improved supervised fine-tuning methods that enable LMs to better follow instructions, especially when labelled data is scarce, enhancing their performance across a range of NLP tasks, including open-ended generation. Finally, we develop new evaluation methods and benchmarks, such as multi-hop spatial reasoning tasks, to assess LM capabilities and adaptation more comprehensively. Through extensive empirical studies across diverse NLP tasks, our results demonstrate that these approaches substantially improve LM robustness, efficiency, and generalization, making them more adaptable to a broad range of applications. These advances mark a significant step towards more robust and efficient LMs, bringing us closer to the goal of artificial general intelligence.

Multi-lingual competence in large language models is often evaluated via static data benchmarks such as Belebele, M-MMLU and M-GSM. However, these evaluations often fail to provide an adequate understanding of the practical performance and robustness of models across multi-lingual settings. In response, we create multi-lingual functional benchmarks -- Cross-Lingual Grade School Math Symbolic (CL-GSM Symbolic) and Cross-Lingual Instruction-Following Eval (CL-IFEval)-- by translating existing functional benchmark templates from English to five additional languages that span the range of resources available for NLP: French, Spanish, Hindi, Arabic and Yoruba. Our results reveal that some static multi-lingual benchmarks capture functional performance much more closely than others (i.e. across models, there is a 24%, 17% and 18% decrease in performance between M-GSM and CL-GSM Symbolic in English, French and Spanish respectively; similarly there's a 15 - 24% performance drop across languages between Belebele and CL-IFEval, and only a 0.5% to 3% performance drop between M-MMLU and CL-IFEval). Similarly, we find that model robustness across languages varies significantly, with certain languages (eg. Arabic, English) being the most consistently well performing across evaluation iterations.

In this work, we introduce skLEP, the first comprehensive benchmark specifically designed for evaluating Slovak natural language understanding (NLU) models. We have compiled skLEP to encompass nine diverse tasks that span token-level, sentence-pair, and document-level challenges, thereby offering a thorough assessment of model capabilities. To create this benchmark, we curated new, original datasets tailored for Slovak and meticulously translated established English NLU resources. Within this paper, we also present the first systematic and extensive evaluation of a wide array of Slovak-specific, multilingual, and English pre-trained language models using the skLEP tasks. Finally, we also release the complete benchmark data, an open-source toolkit facilitating both fine-tuning and evaluation of models, and a public leaderboard at https://github.com/slovak-nlp/sklep in the hopes of fostering reproducibility and drive future research in Slovak NLU.

In this paper, we compare Czech-specific and multilingual sentence embedding models through intrinsic and extrinsic evaluation paradigms. For intrinsic evaluation, we employ Costra, a complex sentence transformation dataset, and several Semantic Textual Similarity (STS) benchmarks to assess the ability of the embeddings to capture linguistic phenomena such as semantic similarity, temporal aspects, and stylistic variations. In the extrinsic evaluation, we fine-tune each embedding model using COMET-based metrics for machine translation evaluation. Our experiments reveal an interesting disconnect: models that excel in intrinsic semantic similarity tests do not consistently yield superior performance on downstream translation evaluation tasks. Conversely, models with seemingly over-smoothed embedding spaces can, through fine-tuning, achieve excellent results. These findings highlight the complex relationship between semantic property probes and downstream task, emphasizing the need for more research into 'operationalizable semantics' in sentence embeddings, or more in-depth downstream tasks datasets (here translation evaluation)

In Machine Translation (MT) evaluation, metric performance is assessed based on agreement with human judgments. In recent years, automatic metrics have demonstrated increasingly high levels of agreement with humans. To gain a clearer understanding of metric performance and establish an upper bound, we incorporate human baselines in the MT meta-evaluation, that is, the assessment of MT metrics' capabilities. Our results show that human annotators are not consistently superior to automatic metrics, with state-of-the-art metrics often ranking on par with or higher than human baselines. Despite these findings suggesting human parity, we discuss several reasons for caution. Finally, we explore the broader implications of our results for the research field, asking: Can we still reliably measure improvements in MT evaluation? With this work, we aim to shed light on the limits of our ability to measure progress in the field, fostering discussion on an issue that we believe is crucial to the entire MT evaluation community.