In this era of rapid technological advancements, communication continues to evolve as new linguistic phenomena emerge. Among these is Arabizi, a hybrid form of Arabic that incorporates Latin characters and numbers to represent the spoken dialects of Arab communities. Arabizi is widely used on social media and allows people to communicate in an informal and dynamic way, but it poses significant challenges for machine translation due to its lack of formal structure and deeply embedded cultural nuances. This case study arises from a growing need to translate Arabizi for gisting purposes. It evaluates the capacity of different LLMs to decode and translate Arabizi, focusing on multiple Arabic dialects that have rarely been studied up until now. Using a combination of human evaluators and automatic metrics, this research project investigates the model's performance in translating Arabizi into both Modern Standard Arabic and English. Key questions explored include which dialects are translated most effectively and whether translations into English surpass those into Arabic.
The rapid evolution of artificial intelligence (AI) has introduced AI agents as a disruptive paradigm across various industries, yet their application in machine translation (MT) remains underexplored. This paper describes and analyses the potential of single- and multi-agent systems for MT, reflecting on how they could enhance multilingual digital communication. While single-agent systems are well-suited for simpler translation tasks, multi-agent systems, which involve multiple specialized AI agents collaborating in a structured manner, may offer a promising solution for complex scenarios requiring high accuracy, domain-specific knowledge, and contextual awareness. To demonstrate the feasibility of multi-agent workflows in MT, we are conducting a pilot study in legal MT. The study employs a multi-agent system involving four specialized AI agents for (i) translation, (ii) adequacy review, (iii) fluency review, and (iv) final editing. Our findings suggest that multi-agent systems may have the potential to significantly improve domain-adaptability and contextual awareness, with superior translation quality to traditional MT or single-agent systems. This paper also sets the stage for future research into multi-agent applications in MT, integration into professional translation workflows, and shares a demo of the system analyzed in the paper.
Tokenization is a crucial step in NLP, especially with the rise of large language models (LLMs), impacting downstream performance, computational cost, and efficiency. Existing LLMs rely on the classical Byte-pair Encoding (BPE) algorithm for subword tokenization that greedily merges frequent character bigrams. This often leads to segmentation that does not align with linguistically meaningful units. To address this, we propose morphology-aware segmentation as a pre-tokenization step prior to applying BPE. To facilitate morphology-aware segmentation, we create a novel dataset for Hindi and Marathi, incorporating sandhi splitting to enhance the subword tokenization. Experiments on downstream tasks show that morphologically grounded tokenization improves performance for machine translation and language modeling. Additionally, to handle the ambiguity in the Unicode characters for diacritics, particularly dependent vowels in syllable-based writing systems, we introduce Constrained BPE (CBPE), an extension to the traditional BPE algorithm that incorporates script-specific constraints. Specifically, CBPE handles dependent vowels. Our results show that CBPE achieves a 1.68\% reduction in fertility scores while maintaining comparable or improved downstream performance in machine translation, offering a computationally efficient alternative to standard BPE. Moreover, to evaluate segmentation across different tokenization algorithms, we introduce a new human evaluation metric, \textit{EvalTok}, enabling more human-grounded assessment.
Large-scale reinforcement learning (RL) methods have proven highly effective in enhancing the reasoning abilities of large language models (LLMs), particularly for tasks with verifiable solutions such as mathematics and coding. However, applying this idea to machine translation (MT), where outputs are flexibly formatted and difficult to automatically evaluate with explicit rules, remains underexplored. In this work, we introduce MT-R1-Zero, the first open-source adaptation of the R1-Zero RL framework for MT without supervised fine-tuning or cold-start. We propose a rule-metric mixed reward mechanism to guide LLMs towards improved translation quality via emergent reasoning. On the WMT 24 English-Chinese benchmark, our MT-R1-Zero-3B-Mix achieves competitive performance, surpassing TowerInstruct-7B-v0.2 by an average of 1.26 points. Meanwhile, our MT-R1-Zero-7B-Mix attains a high average score of 62.25 across all metrics, placing it on par with advanced proprietary models such as GPT-4o and Claude-3.5-Sonnet, while the MT-R1-Zero-7B-Sem variant achieves state-of-the-art scores on semantic metrics. Moreover, our work exhibits strong generalization capabilities on out-of-distribution MT tasks, robustly supporting multilingual and low-resource settings. Extensive analysis of model behavior across different initializations and reward metrics offers pioneering insight into the critical role of reward design, LLM adaptability, training dynamics, and emergent reasoning patterns within the R1-Zero paradigm for MT. Our code is available at https://github.com/fzp0424/MT-R1-Zero.
Large language models (LLMs) pre-trained predominantly on English text exhibit surprising multilingual capabilities, yet the mechanisms driving cross-lingual generalization remain poorly understood. This work investigates how the alignment of representations for text written in different languages correlates with LLM performance on natural language understanding tasks and translation tasks, both at the language and the instance level. For this purpose, we introduce cross-lingual alignment metrics such as the Discriminative Alignment Index (DALI) to quantify the alignment at an instance level for discriminative tasks. Through experiments on three natural language understanding tasks (Belebele, XStoryCloze, XCOPA), and machine translation, we find that while cross-lingual alignment metrics strongly correlate with task accuracy at the language level, the sample-level alignment often fails to distinguish correct from incorrect predictions, exposing alignment as a necessary but insufficient condition for success.
Python is one of the most commonly used programming languages in industry and education. Its English keywords and built-in functions/modules allow it to come close to pseudo-code in terms of its readability and ease of writing. However, those who do not speak English may not experience these advantages. In fact, they may even be hindered in their ability to understand Python code, as the English nature of its terms creates an additional layer of overhead. To that end, we introduce the task of automatically translating Python's natural modality (keywords, error types, identifiers, etc.) into other human languages. This presents a unique challenge, considering the abbreviated nature of these forms, as well as potential untranslatability of advanced mathematical/programming concepts across languages. We therefore create an automated pipeline to translate Python into other human languages, comparing strategies using machine translation and large language models. We then use this pipeline to acquire translations from five common Python libraries (pytorch, pandas, tensorflow, numpy, and random) in seven languages, and do a quality test on a subset of these terms in French, Greek, and Bengali. We hope this will provide a clearer path forward towards creating a universal Python, accessible to anyone regardless of nationality or language background.
For high-quality texts, single-score metrics seldom provide actionable feedback. In contrast, span annotation - pointing out issues in the text by annotating their spans - can guide improvements and provide insights. Until recently, span annotation was limited to human annotators or fine-tuned encoder models. In this study, we automate span annotation with large language models (LLMs). We compare expert or skilled crowdworker annotators with open and proprietary LLMs on three tasks: data-to-text generation evaluation, machine translation evaluation, and propaganda detection in human-written texts. In our experiments, we show that LLMs as span annotators are straightforward to implement and notably more cost-efficient than human annotators. The LLMs achieve moderate agreement with skilled human annotators, in some scenarios comparable to the average agreement among the annotators themselves. Qualitative analysis shows that reasoning models outperform their instruction-tuned counterparts and provide more valid explanations for annotations. We release the dataset of more than 40k model and human annotations for further research.
Reasoning-enabled large language models (LLMs) have recently demonstrated impressive performance in complex logical and mathematical tasks, yet their effectiveness in evaluating natural language generation remains unexplored. This study systematically compares reasoning-based LLMs (DeepSeek-R1 and OpenAI o3) with their non-reasoning counterparts across machine translation (MT) and text summarization (TS) evaluation tasks. We evaluate eight models across three architectural categories, including state-of-the-art reasoning models, their distilled variants (ranging from 8B to 70B parameters), and equivalent conventional, non-reasoning LLMs. Our experiments on WMT23 and SummEval benchmarks reveal that the benefits of reasoning capabilities are highly model and task-dependent: while OpenAI o3-mini models show consistent performance improvements with increased reasoning intensity, DeepSeek-R1 underperforms compared to its non-reasoning variant, with exception to certain aspects of TS evaluation. Correlation analysis demonstrates that increased reasoning token usage positively correlates with evaluation quality in o3-mini models. Furthermore, our results show that distillation of reasoning capabilities maintains reasonable performance in medium-sized models (32B) but degrades substantially in smaller variants (8B). This work provides the first comprehensive assessment of reasoning LLMs for NLG evaluation and offers insights into their practical use.
The globalization of social interactions has heightened the need for machine translation (MT) on Social Network Services (SNS), yet traditional models struggle with culturally nuanced content like memes, slang, and pop culture references. While large language models (LLMs) have advanced general-purpose translation, their performance on SNS-specific content remains limited due to insufficient specialized training data and evaluation benchmarks. This paper introduces RedTrans, a 72B LLM tailored for SNS translation, trained on a novel dataset developed through three innovations: (1) Supervised Finetuning with Dual-LLM Back-Translation Sampling, an unsupervised sampling method using LLM-based back-translation to select diverse data for large-scale finetuning; (2) Rewritten Preference Optimization (RePO), an algorithm that identifies and corrects erroneous preference pairs through expert annotation, building reliable preference corpora; and (3) RedTrans-Bench, the first benchmark for SNS translation, evaluating phenomena like humor localization, emoji semantics, and meme adaptation. Experiments show RedTrans outperforms state-of-the-art LLMs. Besides, RedTrans has already been deployed in a real-world production environment, demonstrating that domain-specific adaptation, effectively bridges the gap between generic and culturally grounded translation systems.
Despite the steady progress in machine translation evaluation, existing automatic metrics struggle to capture how well meaning is preserved beyond sentence boundaries. We posit that reliance on a single intrinsic quality score, trained to mimic human judgments, might be insufficient for evaluating translations of long, complex passages, and a more ``pragmatic'' approach that assesses how accurately key information is conveyed by a translation in context is needed. We introduce TREQA (Translation Evaluation via Question-Answering), a framework that extrinsically evaluates translation quality by assessing how accurately candidate translations answer reading comprehension questions that target key information in the original source or reference texts. In challenging domains that require long-range understanding, such as literary texts, we show that TREQA is competitive with and, in some cases, outperforms state-of-the-art neural and LLM-based metrics in ranking alternative paragraph-level translations, despite never being explicitly optimized to correlate with human judgments. Furthermore, the generated questions and answers offer interpretability: empirical analysis shows that they effectively target translation errors identified by experts in evaluated datasets. Our code is available at https://github.com/deep-spin/treqa
This paper explores the potential of context-aware monolingual human evaluation for assessing machine translation (MT) when no source is given for reference. To this end, we compare monolingual with bilingual evaluations (with source text), under two scenarios: the evaluation of a single MT system, and the comparative evaluation of pairwise MT systems. Four professional translators performed both monolingual and bilingual evaluations by assigning ratings and annotating errors, and providing feedback on their experience. Our findings suggest that context-aware monolingual human evaluation achieves comparable outcomes to human bilingual evaluations, and suggest the feasibility and potential of monolingual evaluation as an efficient approach to assessing MT.
Large Language Models (LLMs) have revolutionized artificial intelligence, driving advancements in machine translation, summarization, and conversational agents. However, their increasing integration into critical societal domains has raised concerns about embedded biases, which can perpetuate stereotypes and compromise fairness. These biases stem from various sources, including historical inequalities in training data, linguistic imbalances, and adversarial manipulation. Despite mitigation efforts, recent studies indicate that LLMs remain vulnerable to adversarial attacks designed to elicit biased responses. This work proposes a scalable benchmarking framework to evaluate LLM robustness against adversarial bias elicitation. Our methodology involves (i) systematically probing models with a multi-task approach targeting biases across various sociocultural dimensions, (ii) quantifying robustness through safety scores using an LLM-as-a-Judge approach for automated assessment of model responses, and (iii) employing jailbreak techniques to investigate vulnerabilities in safety mechanisms. Our analysis examines prevalent biases in both small and large state-of-the-art models and their impact on model safety. Additionally, we assess the safety of domain-specific models fine-tuned for critical fields, such as medicine. Finally, we release a curated dataset of bias-related prompts, CLEAR-Bias, to facilitate systematic vulnerability benchmarking. Our findings reveal critical trade-offs between model size and safety, aiding the development of fairer and more robust future language models.
Post-editing machine translation (MT) for creative texts, such as literature, requires balancing efficiency with the preservation of creativity and style. While neural MT systems struggle with these challenges, large language models (LLMs) offer improved capabilities for context-aware and creative translation. This study evaluates the feasibility of post-editing literary translations generated by LLMs. Using a custom research tool, we collaborated with professional literary translators to analyze editing time, quality, and creativity. Our results indicate that post-editing LLM-generated translations significantly reduces editing time compared to human translation while maintaining a similar level of creativity. The minimal difference in creativity between PE and MT, combined with substantial productivity gains, suggests that LLMs may effectively support literary translators working with high-resource languages.
Multilingual speech translation (ST) in the medical domain enhances patient care by enabling efficient communication across language barriers, alleviating specialized workforce shortages, and facilitating improved diagnosis and treatment, particularly during pandemics. In this work, we present the first systematic study on medical ST, to our best knowledge, by releasing MultiMed-ST, a large-scale ST dataset for the medical domain, spanning all translation directions in five languages: Vietnamese, English, German, French, Traditional Chinese and Simplified Chinese, together with the models. With 290,000 samples, our dataset is the largest medical machine translation (MT) dataset and the largest many-to-many multilingual ST among all domains. Secondly, we present the most extensive analysis study in ST research to date, including: empirical baselines, bilingual-multilingual comparative study, end-to-end vs. cascaded comparative study, task-specific vs. multi-task sequence-to-sequence (seq2seq) comparative study, code-switch analysis, and quantitative-qualitative error analysis. All code, data, and models are available online: https://github.com/leduckhai/MultiMed-ST.
We introduce a new dataset for machine translation of Guinea-Bissau Creole (Kiriol), comprising around 40 thousand parallel sentences to English and Portuguese. This dataset is made up of predominantly religious data (from the Bible and texts from the Jehovah's Witnesses), but also a small amount of general domain data (from a dictionary). This mirrors the typical resource availability of many low resource languages. We train a number of transformer-based models to investigate how to improve domain transfer from religious data to a more general domain. We find that adding even 300 sentences from the target domain when training substantially improves the translation performance, highlighting the importance and need for data collection for low-resource languages, even on a small-scale. We additionally find that Portuguese-to-Kiriol translation models perform better on average than other source and target language pairs, and investigate how this relates to the morphological complexity of the languages involved and the degree of lexical overlap between creoles and lexifiers. Overall, we hope our work will stimulate research into Kiriol and into how machine translation might better support creole languages in general.
Subword tokenization requires balancing computational efficiency and vocabulary coverage, which often leads to suboptimal performance on languages and scripts not prioritized during training. We propose to augment pretrained language models with a vocabulary-free encoder that generates input embeddings from text rendered as pixels. Through experiments on English-centric language models, we demonstrate that our approach substantially improves machine translation performance and facilitates effective cross-lingual transfer, outperforming tokenizer-based methods. Furthermore, we find that pixel-based representations outperform byte-level approaches and standard vocabulary expansion. Our approach enhances the multilingual capabilities of monolingual language models without extensive retraining and reduces decoding latency via input compression.
Evaluating the quality of generated text automatically remains a significant challenge. Conventional reference-based metrics have been shown to exhibit relatively weak correlation with human evaluations. Recent research advocates the use of large language models (LLMs) as source-based metrics for natural language generation (NLG) assessment. While promising, LLM-based metrics, particularly those using smaller models, still fall short in aligning with human judgments. In this work, we introduce ContrastScore, a contrastive evaluation metric designed to enable higher-quality, less biased, and more efficient assessment of generated text. We evaluate ContrastScore on two NLG tasks: machine translation and summarization. Experimental results show that ContrastScore consistently achieves stronger correlation with human judgments than both single-model and ensemble-based baselines. Notably, ContrastScore based on Qwen 3B and 0.5B even outperforms Qwen 7B, despite having only half as many parameters, demonstrating its efficiency. Furthermore, it effectively mitigates common evaluation biases such as length and likelihood preferences, resulting in more robust automatic evaluation.
The advent of Large Language Models (LLMs) has significantly reshaped the landscape of machine translation (MT), particularly for low-resource languages and domains that lack sufficient parallel corpora, linguistic tools, and computational infrastructure. This survey presents a comprehensive overview of recent progress in leveraging LLMs for MT. We analyze techniques such as few-shot prompting, cross-lingual transfer, and parameter-efficient fine-tuning that enable effective adaptation to under-resourced settings. The paper also explores synthetic data generation strategies using LLMs, including back-translation and lexical augmentation. Additionally, we compare LLM-based translation with traditional encoder-decoder models across diverse language pairs, highlighting the strengths and limitations of each. We discuss persistent challenges such as hallucinations, evaluation inconsistencies, and inherited biases while also evaluating emerging LLM-driven metrics for translation quality. This survey offers practical insights and outlines future directions for building robust, inclusive, and scalable MT systems in the era of large-scale generative models.
Code-switching, the act of alternating between languages, emerged as a prevalent global phenomenon that needs to be addressed for building user-friendly language technologies. A main bottleneck in this pursuit is data scarcity, motivating research in the direction of code-switched data augmentation. However, current literature lacks comprehensive studies that enable us to understand the relation between the quality of synthetic data and improvements on NLP tasks. We extend previous research conducted in this direction on machine translation (MT) with results on automatic speech recognition (ASR) and cascaded speech translation (ST) to test generalizability of findings. Our experiments involve a wide range of augmentation techniques, covering lexical replacements, linguistic theories, and back-translation. Based on the results of MT, ASR, and ST, we draw conclusions and insights regarding the efficacy of various augmentation techniques and the impact of quality on performance.
This article reports on the third iteration of a survey of computerized tools and technologies taught as part of postgraduate translation training programmes. While the survey was carried out under the aegis of the EMT Network, more than half of responses are from outside that network. The results show the responsiveness of programmes to innovations in translation technology, with increased compulsory inclusion of machine translation, post-editing, and quality evaluation, and a rapid response to the release of generative tools. The flexibility required during the Covid-19 pandemic has also led to some lasting changes to programmes. While the range of tools being taught has continued to expand, programmes seem to be consolidating their core offering around cloud-based software with cost-free academic access. There has also been an increase in the embedding of professional contexts and workflows associated with translation technology. Generic file management and data security skills have increased in perceived importance, and legal and ethical issues related to translation data have also become more prominent. In terms of course delivery the shift away from conventional labs identified in EMT2017 has accelerated markedly, no doubt partly driven by the pandemic, accompanied by a dramatic expansion in the use of students' personal devices.