Translating knowledge-intensive and entity-rich text between English and Korean requires transcreation to preserve language-specific and cultural nuances beyond literal, phonetic or word-for-word conversion. We evaluate 13 models (LLMs and MT models) using automatic metrics and human assessment by bilingual annotators. Our findings show LLMs outperform traditional MT systems but struggle with entity translation requiring cultural adaptation. By constructing an error taxonomy, we identify incorrect responses and entity name errors as key issues, with performance varying by entity type and popularity level. This work exposes gaps in automatic evaluation metrics and hope to enable future work in completing culturally-nuanced machine translation.
Currently, Large Language Models (LLMs) have achieved remarkable results in machine translation. However, their performance in multi-domain translation (MDT) is less satisfactory, the meanings of words can vary across different domains, highlighting the significant ambiguity inherent in MDT. Therefore, evaluating the disambiguation ability of LLMs in MDT, remains an open problem. To this end, we present an evaluation and analysis of LLMs on disambiguation in multi-domain translation (DMDTEval), our systematic evaluation framework consisting of three critical aspects: (1) we construct a translation test set with multi-domain ambiguous word annotation, (2) we curate a diverse set of disambiguation prompt strategies, and (3) we design precise disambiguation metrics, and study the efficacy of various prompt strategies on multiple state-of-the-art LLMs. We conduct comprehensive experiments across 4 language pairs and 13 domains, our extensive experiments reveal a number of crucial findings that we believe will pave the way and also facilitate further research in the critical area of improving the disambiguation of LLMs.
A frequently observed problem with LLMs is their tendency to generate output that is nonsensical, illogical, or factually incorrect, often referred to broadly as hallucination. Building on the recently proposed HalluciGen task for hallucination detection and generation, we evaluate a suite of open-access LLMs on their ability to detect intrinsic hallucinations in two conditional generation tasks: translation and paraphrasing. We study how model performance varies across tasks and language and we investigate the impact of model size, instruction tuning, and prompt choice. We find that performance varies across models but is consistent across prompts. Finally, we find that NLI models perform comparably well, suggesting that LLM-based detectors are not the only viable option for this specific task.
Conventional retrieval-augmented neural machine translation (RANMT) systems leverage bilingual corpora, e.g., translation memories (TMs). Yet, in many settings, in-domain monolingual target-side corpora are often available. This work explores ways to take advantage of such resources by retrieving relevant segments directly in the target language, based on a source-side query. For this, we design improved cross-lingual retrieval systems, trained with both sentence level and word-level matching objectives. In our experiments with two RANMT architectures, we first demonstrate the benefits of such cross-lingual objectives in a controlled setting, obtaining translation performances that surpass standard TM-based models. We then showcase our method on a real-world set-up, where the target monolingual resources far exceed the amount of parallel data and observe large improvements of our new techniques, which outperform both the baseline setting, and general-purpose cross-lingual retrievers.
Arabic text diacritization remains a persistent challenge in natural language processing due to the language's morphological richness. In this paper, we introduce Sadeed, a novel approach based on a fine-tuned decoder-only language model adapted from Kuwain 1.5B Hennara et al. [2025], a compact model originally trained on diverse Arabic corpora. Sadeed is fine-tuned on carefully curated, high-quality diacritized datasets, constructed through a rigorous data-cleaning and normalization pipeline. Despite utilizing modest computational resources, Sadeed achieves competitive results compared to proprietary large language models and outperforms traditional models trained on similar domains. Additionally, we highlight key limitations in current benchmarking practices for Arabic diacritization. To address these issues, we introduce SadeedDiac-25, a new benchmark designed to enable fairer and more comprehensive evaluation across diverse text genres and complexity levels. Together, Sadeed and SadeedDiac-25 provide a robust foundation for advancing Arabic NLP applications, including machine translation, text-to-speech, and language learning tools.
In this paper,we explore the application of Back translation (BT) as a semi-supervised technique to enhance Neural Machine Translation(NMT) models for the English-Luganda language pair, specifically addressing the challenges faced by low-resource languages. The purpose of our study is to demonstrate how BT can mitigate the scarcity of bilingual data by generating synthetic data from monolingual corpora. Our methodology involves developing custom NMT models using both publicly available and web-crawled data, and applying Iterative and Incremental Back translation techniques. We strategically select datasets for incremental back translation across multiple small datasets, which is a novel element of our approach. The results of our study show significant improvements, with translation performance for the English-Luganda pair exceeding previous benchmarks by more than 10 BLEU score units across all translation directions. Additionally, our evaluation incorporates comprehensive assessment metrics such as SacreBLEU, ChrF2, and TER, providing a nuanced understanding of translation quality. The conclusion drawn from our research confirms the efficacy of BT when strategically curated datasets are utilized, establishing new performance benchmarks and demonstrating the potential of BT in enhancing NMT models for low-resource languages.
Accurately evaluating machine-translated text remains a long-standing challenge, particularly for long documents. Recent work has shown that large language models (LLMs) can serve as reliable and interpretable sentence-level translation evaluators via MQM error span annotations. With modern LLMs supporting larger context windows, a natural question arises: can we feed entire document translations into an LLM for quality assessment? Ideally, evaluation should be invariant to text length, producing consistent error spans regardless of input granularity. However, our analysis shows that text length significantly impacts evaluation: longer texts lead to fewer error spans and reduced system ranking accuracy. To address this limitation, we evaluate several strategies, including granularity-aligned prompting, Focus Sentence Prompting (FSP), and a fine-tuning approach to better align LLMs with the evaluation task. The latter two methods largely mitigate this length bias, making LLMs more reliable for long-form translation evaluation.
Large language models (LLMs) and multi-agent orchestration are touted as the next leap in machine translation (MT), but their benefits relative to conventional neural MT (NMT) remain unclear. This paper offers an empirical reality check. We benchmark five paradigms, Google Translate (strong NMT baseline), GPT-4o (general-purpose LLM), o1-preview (reasoning-enhanced LLM), and two GPT-4o-powered agentic workflows (sequential three-stage and iterative refinement), on test data drawn from a legal contract and news prose in three English-source pairs: Spanish, Catalan and Turkish. Automatic evaluation is performed with COMET, BLEU, chrF2 and TER; human evaluation is conducted with expert ratings of adequacy and fluency; efficiency with total input-plus-output token counts mapped to April 2025 pricing. Automatic scores still favour the mature NMT system, which ranks first in seven of twelve metric-language combinations; o1-preview ties or places second in most remaining cases, while both multi-agent workflows trail. Human evaluation reverses part of this narrative: o1-preview produces the most adequate and fluent output in five of six comparisons, and the iterative agent edges ahead once, indicating that reasoning layers capture semantic nuance undervalued by surface metrics. Yet these qualitative gains carry steep costs. The sequential agent consumes roughly five times, and the iterative agent fifteen times, the tokens used by NMT or single-pass LLMs. We advocate multidimensional, cost-aware evaluation protocols and highlight research directions that could tip the balance: leaner coordination strategies, selective agent activation, and hybrid pipelines combining single-pass LLMs with targeted agent intervention.
State-of-the-art approaches for conditional human body rendering via Gaussian splatting typically focus on simple body motions captured from many views. This is often in the context of dancing or walking. However, for more complex use cases, such as sign language, we care less about large body motion and more about subtle and complex motions of the hands and face. The problems of building high fidelity models are compounded by the complexity of capturing multi-view data of sign. The solution is to make better use of sequence data, ensuring that we can overcome the limited information from only a few views by exploiting temporal variability. Nevertheless, learning from sequence-level data requires extremely accurate and consistent model fitting to ensure that appearance is consistent across complex motions. We focus on how to achieve this, constraining mesh parameters to build an accurate Gaussian splatting framework from few views capable of modelling subtle human motion. We leverage regularization techniques on the Gaussian parameters to mitigate overfitting and rendering artifacts. Additionally, we propose a new adaptive control method to densify Gaussians and prune splat points on the mesh surface. To demonstrate the accuracy of our approach, we render novel sequences of sign language video, building on neural machine translation approaches to sign stitching. On benchmark datasets, our approach achieves state-of-the-art performance; and on highly articulated and complex sign language motion, we significantly outperform competing approaches.
Large Language Models (LLMs) are increasingly leveraged for translation tasks but often fall short when translating inclusive language -- such as texts containing the singular 'they' pronoun or otherwise reflecting fair linguistic protocols. Because these challenges span both computational and societal domains, it is imperative to critically evaluate how well LLMs handle inclusive translation with a well-founded framework. This paper presents FairTranslate, a novel, fully human-annotated dataset designed to evaluate non-binary gender biases in machine translation systems from English to French. FairTranslate includes 2418 English-French sentence pairs related to occupations, annotated with rich metadata such as the stereotypical alignment of the occupation, grammatical gender indicator ambiguity, and the ground-truth gender label (male, female, or inclusive). We evaluate four leading LLMs (Gemma2-2B, Mistral-7B, Llama3.1-8B, Llama3.3-70B) on this dataset under different prompting procedures. Our results reveal substantial biases in gender representation across LLMs, highlighting persistent challenges in achieving equitable outcomes in machine translation. These findings underscore the need for focused strategies and interventions aimed at ensuring fair and inclusive language usage in LLM-based translation systems. We make the FairTranslate dataset publicly available on Hugging Face, and disclose the code for all experiments on GitHub.
The rise of Large Language Models (LLMs) has reshaped machine translation (MT), but multilingual MT still relies heavily on parallel data for supervised fine-tuning (SFT), facing challenges like data scarcity for low-resource languages and catastrophic forgetting. To address these issues, we propose TRANS-ZERO, a self-play framework that leverages only monolingual data and the intrinsic multilingual knowledge of LLM. TRANS-ZERO combines Genetic Monte-Carlo Tree Search (G-MCTS) with preference optimization, achieving strong translation performance that rivals supervised methods. Experiments demonstrate that this approach not only matches the performance of models trained on large-scale parallel data but also excels in non-English translation directions. Further analysis reveals that G-MCTS itself significantly enhances translation quality by exploring semantically consistent candidates through iterative translations, providing a robust foundation for the framework's succuss.
This is the first in a series of papers exploring the rapidly expanding new opportunities arising from recent progress in language technologies for individual translators and language service providers with modest resources. The advent of advanced neural machine translation systems, large language models, and their integration into workflows via computer-assisted translation tools and translation management systems have reshaped the translation landscape. These advancements enable not only translation but also quality evaluation, error spotting, glossary generation, and adaptation to domain-specific needs, creating new technical opportunities for freelancers. In this series, we aim to empower translators with actionable methods to harness these advancements. Our approach emphasizes Translation Analytics, a suite of evaluation techniques traditionally reserved for large-scale industry applications but now becoming increasingly available for smaller-scale users. This first paper introduces a practical framework for adapting automatic evaluation metrics -- such as BLEU, chrF, TER, and COMET -- to freelancers' needs. We illustrate the potential of these metrics using a trilingual corpus derived from a real-world project in the medical domain and provide statistical analysis correlating human evaluations with automatic scores. Our findings emphasize the importance of proactive engagement with emerging technologies to not only adapt but thrive in the evolving professional environment.
There are many ways to describe, name, and group objects when captioning an image. Differences are evident when speakers come from diverse cultures due to the unique experiences that shape perception. Machine translation of captions has pushed multilingual capabilities in vision-language models (VLMs), but data comes mainly from English speakers, indicating a perceptual bias and lack of model flexibility. In this work, we address this challenge and outline a data-efficient framework to instill multilingual VLMs with greater understanding of perceptual diversity. We specifically propose an LLM-based, multimodal recaptioning strategy that alters the object descriptions of English captions before translation. The greatest benefits are demonstrated in a targeted multimodal mechanism guided by native speaker data. By adding produced rewrites as augmentations in training, we improve on German and Japanese text-image retrieval cases studies (up to +3.5 mean recall overall, +4.7 on non-native error cases). We further propose a mechanism to analyze the specific object description differences across datasets, and we offer insights into cross-dataset and cross-language generalization.
With the rapid development of deep learning technologies, the field of machine translation has witnessed significant progress, especially with the advent of large language models (LLMs) that have greatly propelled the advancement of document-level translation. However, accurately evaluating the quality of document-level translation remains an urgent issue. This paper first introduces the development status of document-level translation and the importance of evaluation, highlighting the crucial role of automatic evaluation metrics in reflecting translation quality and guiding the improvement of translation systems. It then provides a detailed analysis of the current state of automatic evaluation schemes and metrics, including evaluation methods with and without reference texts, as well as traditional metrics, Model-based metrics and LLM-based metrics. Subsequently, the paper explores the challenges faced by current evaluation methods, such as the lack of reference diversity, dependence on sentence-level alignment information, and the bias, inaccuracy, and lack of interpretability of the LLM-as-a-judge method. Finally, the paper looks ahead to the future trends in evaluation methods, including the development of more user-friendly document-level evaluation methods and more robust LLM-as-a-judge methods, and proposes possible research directions, such as reducing the dependency on sentence-level information, introducing multi-level and multi-granular evaluation approaches, and training models specifically for machine translation evaluation. This study aims to provide a comprehensive analysis of automatic evaluation for document-level translation and offer insights into future developments.
How can a monolingual English speaker determine whether an automatic translation in French is good enough to be shared? Existing MT error detection and quality estimation (QE) techniques do not address this practical scenario. We introduce AskQE, a question generation and answering framework designed to detect critical MT errors and provide actionable feedback, helping users decide whether to accept or reject MT outputs even without the knowledge of the target language. Using ContraTICO, a dataset of contrastive synthetic MT errors in the COVID-19 domain, we explore design choices for AskQE and develop an optimized version relying on LLaMA-3 70B and entailed facts to guide question generation. We evaluate the resulting system on the BioMQM dataset of naturally occurring MT errors, where AskQE has higher Kendall's Tau correlation and decision accuracy with human ratings compared to other QE metrics.
We present FourierNAT, a novel non-autoregressive Transformer (NAT) architecture that employs Fourier-based mixing in the decoder to generate output sequences in parallel. While traditional NAT approaches often face challenges with capturing global dependencies, our method leverages a discrete Fourier transform to mix token embeddings across the entire sequence dimension, coupled with learned frequency-domain gating. This allows the model to efficiently propagate context without explicit autoregressive steps. Empirically, FourierNAT achieves competitive results against leading NAT baselines on standard benchmarks like WMT machine translation and CNN/DailyMail summarization, providing significant speed advantages over autoregressive Transformers. We further demonstrate that learned frequency-domain parameters allow the model to adaptively focus on long-range or short-range dependencies, partially mitigating the well-known coherence gaps in one-pass NAT generation. Overall, FourierNAT highlights the potential of integrating spectral-domain operations to accelerate and improve parallel text generation. This approach can potentially provide great computational and time savings in inference tasks LLMs.
A key challenge in MT evaluation is the inherent noise and inconsistency of human ratings. Regression-based neural metrics struggle with this noise, while prompting LLMs shows promise at system-level evaluation but performs poorly at segment level. In this work, we propose ReMedy, a novel MT metric framework that reformulates translation evaluation as a reward modeling task. Instead of regressing on imperfect human ratings directly, ReMedy learns relative translation quality using pairwise preference data, resulting in a more reliable evaluation. In extensive experiments across WMT22-24 shared tasks (39 language pairs, 111 MT systems), ReMedy achieves state-of-the-art performance at both segment- and system-level evaluation. Specifically, ReMedy-9B surpasses larger WMT winners and massive closed LLMs such as MetricX-13B, XCOMET-Ensemble, GEMBA-GPT-4, PaLM-540B, and finetuned PaLM2. Further analyses demonstrate that ReMedy delivers superior capability in detecting translation errors and evaluating low-quality translations.
Large language models (LLMs) have demonstrated strong performance in sentence-level machine translation, but scaling to document-level translation remains challenging, particularly in modeling long-range dependencies and discourse phenomena across sentences and paragraphs. In this work, we propose a method to improve LLM-based long-document translation through targeted fine-tuning on high-quality document-level data, which we curate and introduce as DocBlocks. Our approach supports multiple translation paradigms, including direct document-to-document and chunk-level translation, by integrating instructions both with and without surrounding context. This enables models to better capture cross-sentence dependencies while maintaining strong sentence-level translation performance. Experimental results show that incorporating multiple translation paradigms improves document-level translation quality and inference speed compared to prompting and agent-based methods.
Current sign language machine translation systems rely on recognizing hand movements, facial expressions and body postures, and natural language processing, to convert signs into text. Recent approaches use Transformer architectures to model long-range dependencies via positional encoding. However, they lack accuracy in recognizing fine-grained, short-range temporal dependencies between gestures captured at high frame rates. Moreover, their high computational complexity leads to inefficient training. To mitigate these issues, we propose an Adaptive Transformer (ADAT), which incorporates components for enhanced feature extraction and adaptive feature weighting through a gating mechanism to emphasize contextually relevant features while reducing training overhead and maintaining translation accuracy. To evaluate ADAT, we introduce MedASL, the first public medical American Sign Language dataset. In sign-to-gloss-to-text experiments, ADAT outperforms the encoder-decoder transformer, improving BLEU-4 accuracy by 0.1% while reducing training time by 14.33% on PHOENIX14T and 3.24% on MedASL. In sign-to-text experiments, it improves accuracy by 8.7% and reduces training time by 2.8% on PHOENIX14T and achieves 4.7% higher accuracy and 7.17% faster training on MedASL. Compared to encoder-only and decoder-only baselines in sign-to-text, ADAT is at least 6.8% more accurate despite being up to 12.1% slower due to its dual-stream structure.
Generation capabilities and language coverage of multilingual large language models (mLLMs) are advancing rapidly. However, evaluation practices for generative abilities of mLLMs are still lacking comprehensiveness, scientific rigor, and consistent adoption across research labs, which undermines their potential to meaningfully guide mLLM development. We draw parallels with machine translation (MT) evaluation, a field that faced similar challenges and has, over decades, developed transparent reporting standards and reliable evaluations for multilingual generative models. Through targeted experiments across key stages of the generative evaluation pipeline, we demonstrate how best practices from MT evaluation can deepen the understanding of quality differences between models. Additionally, we identify essential components for robust meta-evaluation of mLLMs, ensuring the evaluation methods themselves are rigorously assessed. We distill these insights into a checklist of actionable recommendations for mLLM research and development.