LLMs’ performance on machine translation (MT) tasks is often dependent on the data availability in the specific domains and language pairs that they are trained upon. To examine if multiword expressions (MWEs) still present a bottleneck for LLMs regarding language understanding and translation, we report the performance of systems from the WMT 2026 Test Suites shared task, using portions of the publicly available multilingual parallel corpus AlphaMWE as test suites. We received 31 MT systems’ outputs covering English to Chinese (zh), Polish (pl), German (de), and Arabic (ar) including Modern Standard Arabic (MSA) and two dialectal ones (Egyptian and Tunisian Arabic). We carried out automatic evaluations using BLEU, ChrF, and BERT-score to select the top 3 systems per language pair, followed up with human evaluations on the selected systems. Our findings show that figurative and MWE-related phenomena remain challenging for contemporary MT systems, automatic metrics sometimes disagree in system ranking, and human evaluation uncovers language-specific errors that remain hidden by aggregate scores. Inter-annotator analysis further reveals challenges in consistently identifying and calibrating linguistically subtle translation errors, highlighting the need for explicit evaluation guidelines and careful annotator calibration.

This paper reports on the outcomes of the shared tasks organized as part of the 23rd International Workshop on Spoken Language Translation (IWSLT). The workshop covered ten major challenges in spoken language translation, including speech-to-text translation for both high-resource and low-resource language pairs, customized speech translation, speech generation, instruction-following speech processing, and the evaluation of speech translation systems. The shared tasks received strong participation, with more than 30 teams submitting runs. This year’s edition broadened the range of tasks, placing particular emphasis on speech generation and evaluation metrics.

Speech translation for low-resource languages is constrained by the scarcity of high-quality parallel speech data, which is particularly pronounced in African linguistic contexts. To address this, we introduce , a parallel speech translation dataset covering Igbo, Hausa, , and Nigerian Pidgin paired with English. The dataset contains more than 40 hours of speech per language and includes several speaker and accent variations to reflect realistic settings. Using NaijaS2ST, we benchmark cascaded, end-to-end (E2E), and AudioLLM-based approaches across bidirectional translation directions (XX↔English). Our results show that few-shot audio LLMs are more effective than cascaded and E2E methods finetuned for speech-to-text translation. For speech-to-speech translation, however, cascaded and audio LLM paradigms perform comparatively, highlighting the need for stronger task-specific models. offers a strong foundation towards advancing research on low-resource multilingual speech translation. We open source the dataset here: [NaijaS2ST Huggingface Dataset](https://huggingface.co/datasets/McGill-NLP/NaijaS2ST); and the code here: [NaijaS2ST Code](https://github.com/McGill-NLP/naijas2st).

Automatic speech translation (AST) promotes seamless communication among speakers of different languages. While current state-of-the-art models excel with high-resource languages, their performance on low-resource languages (LRLs) is not well-established. We investigate this by evaluating state-of-the-art models on 10 LRLs with varying data amounts (10-30+ hours). Through six finetuning strategies and experimenting with three main AST paradigms, we observe that: (1) The latest Large Language Models (LLMs) may struggle with LRLs. (2) Comprehensive experiments suggest that for LRLs, more AST finetuning data is not always beneficial. (3) Our 2-Stage with ASR corrector finetuning recipe can substantially improve AST performance on LRLs, achieving up to a 5.8x BLEU score boost on translating related languages to English, while on par with the best monolingual finetuning in BLEU score when translating the target language to English. (4) We share effective engineering practices, including how to effectively adapt AST models to unseen languages.

Data scarcity is a crucial issue for the development of highly multilingual NLP systems. Yet for many under-represented languages (ULs) — languages for which NLP research is particularly far behind in meeting user needs — it is feasible to annotate small amounts of data. Motivated by this, we propose XTREME-UP, a benchmark defined by: its focus on the scarce-data scenario rather than zero-shot; its focus on user-centric tasks — tasks with broad adoption by speakers of high-resource languages; and its focus on under-represented languages where this scarce-data scenario tends to be most realistic. XTREME-UP evaluates the capabilities of language models across 88 under-represented languages over 9 key user-centric technologies including ASR, OCR, MT, and information access tasks that are of general utility. We create new datasets for OCR, autocomplete, semantic parsing, and transliteration, and build on and refine existing datasets for other tasks. XTREME-UP provides methodology for evaluating many modeling scenarios including text only, multi-modal (vision, audio, and text), supervised parameter tuning, and in-context learning. We evaluate commonly used models on the benchmark. We release all code and scripts to train and evaluate models.