Machine Translation

Also known as MT

Overview

Machine translation studies how to produce useful translations across languages, including low-resource languages, specialized domains, dialects, and long or multimodal content. Common approaches include Transformer-based neural systems and large language models, adapted with parallel or synthetic data, retrieval, preference optimization, and reinforcement learning; speech and image translation also combine language models with audio or visual information. Evaluation uses automatic metrics and human review, with newer benchmarks testing terminology, context, cultural meaning, style, bias, and instruction following. A central tension is that gains on standard scores do not always mean translations are faithful or appropriate, while broad language coverage, low latency, privacy, and limited data remain practical challenges.

Latest papers

283 papers34 papers in the last four weeks, level with the four weeks before. 0.2% of all new papers.

Nov 13, 2026

Toward Universal Translatability: On the Statistical Ontology of Generative AI

This paper argues that the problem of translation functions both as a point of origin and as a normative horizon for contemporary generative AI. In current discourse around ''world models,'' their attainment is framed as the achievement of internal consistency, cross-modal alignment, and physical grounding. Taken together, these demands converge on an ideal of the model as a universal translation machine capable of establishing lossless correspondences across linguistic, visual, and physical representation spaces. I show that this ideal presupposes a metaphysical commitment that I call a statistical ontology: the belief that reality has an underlying, computable statistical structure that can be recovered through sufficient data and modeling, rather than being shaped and accessed through situated human interpretation and labor. Tracing this commitment back to Warren Weaver's 1949 Memorandum on machine translation, I outline how translation was historically recast as code deciphering and, later, as the alignment of probability distributions across structured outputs. Finally, I contrast this paradigm with approaches in Translation Studies that foreground opacity, power asymmetries, and the translator's positionality. I argue that generative AI's statistical ontology is pre-Kantian, pre-critical and obscures the infrastructures and human labor that make machine translatability---as alignment---possible in the first place.
Nov 10, 2026

MITRA-Swarm: Injecting Explicit Linguistic Structure into Foundation Models for Classical Machine Translation

Classical Sanskrit poses three challenges unresolved by single-call monolithic models: morphophonemic fusion Sandhi, dense nominal compounding Samāsa, and discourse-level zero-anaphora forced by poetic meter. We present MITRA-Swarm, a multi-agent architecture injecting explicit linguistic structure into an otherwise monolithic pipeline: a Sandhi-splitting agent, a parallel array of generalist gemma-4-26B-A4B-it and domain-specialized gemma-2-mitra-it translators, and a discourse-aware Ellipsis Restorer that consults corpus-derived register tags to avoid inventing active-voice subjects in impersonal legal and philosophical registers. Two separated judges evaluate quality: a routing judge (JrouteJ_{\text{route}}, same model family as the generators) driving an internal critique loop, and an independent reporting judge (Jreport=J_{\text{report}}=gpt-4o-mini, no shared vendor lineage) scoring every output exactly once. On a stratified benchmark of 1,000 verses across five registers (23,990 scored verdicts, 12-condition pre-registered ablation), the full swarm reaches 85.9085.90 MQM against a monolithic baseline of 85.2785.27 (Δ=+0.63Δ=+0.63, padj=0.0018p_{\text{adj}}=0.0018, 95% CI [+0.30,+0.97][+0.30,+0.97]), and isolated discourse restoration alone accounts for +0.44+0.44 MQM (padj=0.0288p_{\text{adj}}=0.0288), outperforming a call-count-matched self-refinement baseline by +0.51+0.51 MQM (padj=0.0288p_{\text{adj}}=0.0288). Severe per-verse failures (MQM<80<80) fall from 9.0%9.0\% to 7.6%7.6\%, at roughly 9×9\times the per-verse inference cost of the baseline. Additionally, JrouteJ_{\text{route}} scores its own family's outputs 22-77 MQM higher than JreportJ_{\text{report}} on every one of the 12 conditions, empirically motivating the two-judge split; and a preflight screen of a 192,151-entry retrieval index against all 12 evaluation works verifies 0 reference leaks across 269 runtime checks. These are small gains on a metric saturating near 85-86.
Nov 9, 2026

A Large-Scale Dataset for Cross-Lingual Multi-Jurisdiction Patent Drafting from Patent Cooperation Treaty Applications

Securing patent protection across countries requires drafting claims separately for each national patent office, in the relevant language and according to its legal and stylistic conventions. Patent claims can therefore differ across languages and jurisdictions because of translation, target-office drafting practices, and prosecution-stage changes. We formulate cross-lingual patent drafting as generating plausible candidate claim sets for a specified target language, jurisdiction, and prosecution stage from a source claim set in another language. The task models jurisdiction- and stage-specific transformations beyond content-preserving translation. We construct a large-scale Japanese-English dataset by linking Japan Patent Office (JPO) and United States Patent and Trademark Office (USPTO) records through 884,179 Patent Cooperation Treaty (PCT)-derived patent families. Across six released configurations, these families yield 4,067,168 directional claim-set instances; four core configurations form the main benchmark. Commercial machine translation and zero- and few-shot prompting capture part of the task, while supervised adaptation provides the strongest overall baseline, showing that task-specific patterns can be learned from linked cross-jurisdictional claim sets.
Nov 8, 2026

Out of Parameters, Saved by Syntax: UD-PrMPT for Parser Augmented Low Resource Machine Translation

Recent work advancing machine translation quality using LLMs for very low resource languages has relied on the injection of lexicon-based prompt components to expose vocabulary to models. However, these approaches run into a ceiling when models must guess sentence meaning purely from plausible combinations of possible word senses mapped to strings. In this paper we test UD-PrMPT, an approach using syntactic analyses in the Universal Dependencies formalism as prompt components to improve MT in five diverse low resource languages: Beja, Chintang, Chukchi, Coptic, and Xibe. Our results show additive improvements which stack on top of the lexicon based approach which are stronger for higher quality manual analyses but consistent for predicted parses as well.
Nov 7, 2026

Pole or Vector? Encoders Capture Bangla Compound Verbs, but LLMs Read Them Literally

In Bangla, a main verb is often followed by one of a small set of vector verbs. These verbs lose their own meaning and add a shade of meaning instead, such as completion. For example, likhe phello means that someone finished writing, not that they wrote and threw something. The same two verbs can also describe two separate events, so only the context shows which meaning is meant. This makes compound verbs a hard test of how language models handle multiword expressions. We present BanglaCV-Probe, a benchmark of 17 vector verbs with 1,044 minimal pairs, 204 entailment items and 197 pairs of correct and incorrect combinations, all checked by native speakers. We test 26 models (encoders, LLMs and translation systems) on four skills: telling the two meanings apart internally, understanding what a vector adds, preferring correct combinations and keeping the vector's meaning in translation. Probes on five encoders tell the two meanings apart and still reach up to 93% accuracy when trained on pairs without surface cues. Prompted models rarely use this knowledge. Entailment accuracy stays between 59% and 81%. Several LLMs answer Yes or No to almost every item, and nine of ten models miss that someone who ate up the rice left none. Most instruction-tuned LLMs translate vectors literally in 15-20% of vector sentences and in up to 55% for mora (die). On correct combinations, a small Bangla-only model (88%) matches BLOOM-7B1 (87%) and both beat Qwen2.5-7B (74%). Data and code: https://github.com/ashuvo25/Pole_OR_Vector
Nov 7, 2026

YRC-Bench: Benchmarking Culturally Aware Machine Translation for Historical Heritage via Tri-Level Semantic Bridging

Translating historical cultural heritage poses profound challenges for machine translation systems due to the acute semantic asymmetry across eras and cultures, where terse classical syntax frequently obscures domain-specific cultural knowledge. While Large Language Models have demonstrated remarkable prowess in generic translation benchmarks, they struggle to negotiate Culturally-Specific Items and diachronic shifts in domain-rich historical texts, such as Yellow River cultural records. To bridge this critical gap, we introduce YRC-Bench, the first human-curated, multi-parallel benchmark dedicated to historical heritage translation across Classical Chinese, Modern Chinese, and nine target foreign languages. YRC-Bench establishes a tri-level parallel corpus incorporating modern explanatory glosses as explicit semantic bridges and operationalizes translation strategies through paired conserved versus substituted CSI variants categorized by cultural translatability. Systematic evaluations of nine leading LLMs across bidirectional translation directions reveal that leveraging modern Chinese glosses - especially human-curated ones - dramatically elevates both lexical fidelity and semantic adequacy. Furthermore, multidimensional human preference audits by native experts unveil distinct cross-cultural preferences between Sinographic-tradition and non-Sinographic language groups.
Nov 6, 2026

Are These Programmers Ripe Enough to Eat? Evaluating How LLMs Handle Lexical Knowledge Conflicts in Translation

External lexical resources can help large language models (LLMs) translate texts in low-resource languages and specialized domains, but these resources may conflict with models' prior lexical knowledge. To isolate this conflict, we construct a controlled Mandarin-to-English translation task in which familiar source words are assigned new meanings within and across semantic categories. We treat these prompt-supplied meanings as contextual knowledge (CK) and systematically evaluate the effects of word frequency, sentence context, and prompt framing on the translated outputs. Across nine models, CK reliance is greater for less frequent source words and in sentence contexts that support the supplied meanings. Prompt framing can reduce CK reliance, but seven of nine models favor CK even when explicitly instructed to ignore the supplied meanings. Within model families, larger models are more likely than smaller models to utilize CK in their outputs. Three follow-up experiments further show that modal weakening lowers CK reliance, the effect of repetition depends on prompt layout, and the effect of reasoning varies across models. Overall, our controlled study reveals how CK reliance varies across conditions and models, motivating new methods to detect and evaluate lexical conflicts and guide models' lexical choices in LLM-based translation.
Nov 5, 2026

Dataset Collection and Fine-Tuning of NLLB for German--English Translation

This paper describes the curation of a high-quality parallel corpus from OPUS Books and the fine-tuning of Meta's NLLB-200 models for German--English translation. We detail a dataset extraction pipeline that filters 45k raw OPUS sentence pairs to 25k high-quality examples through encoding validation, length filtering, language identification, deduplication, and quality scoring. We present a reproducible fine-tuning methodology optimized for consumer GPUs using mixed precision, gradient accumulation, and gradient checkpointing. Our fine-tuned NLLB-600M model achieves statistically significant improvements (+3.4 BLEU, +2.6 chrF++, -3.2 TER) over the base model on literary and technical German-English translation. We demonstrate practical deployment by integrating the fine-tuned model into LinguaHaru, an existing open-source document translation system, achieving format-preserving translation across PDF and Office documents. All dataset preparation scripts, training code, and evaluation tools are provided for reproducibility. The fine-tuned model is available at HuggingFace.
Nov 4, 2026

Dialect Matters: A Dialect-Aware Baseline for Igala-English Machine Translation

The massive permeability of intelligent systems in every sphere of human activities have greatly enhanced clarity, ease of work, and increased general global understanding which has significantly awaken the use of intelligent systems by all users. Intelligent systems greatly rely on precise dataset/corpus for the correctness of their output. Despite efforts by researchers to address Low-resource language in the Natural Language Processing (NLP), Igala still has zero parallel corpora despite efforts by researchers. We present a dialect-aware baseline for Igala-English machine translation, among first open systems and first with dialectal variation analysis. Our dataset of 1137 sentences (899 training) is first with dialect tags: Idah 459 (40.4%), Ankpa 297 (26.1%), Ibaji 160 (14.1%), Other 187 (16.4%), Ogugu 32 (2.8%). Same English yields 20-60 Igala forms. Mixed-dialect training achieves balanced BLEU 11.66 versus Idah-only model which drops 4.7 BLEU on Ibaji (13.2 on Idah, 8.5 on Ibaji), proving dialect fairness requires mixing. Fine-tuned from Helsinki-NLP/opus-mt-en-mul (78M), epoch ablation shows convergence at 8 epochs and overfitting at 15. BLEU 11.66, chrF 46.69. Analysis shows 899 sentences on log-linear trend consistent with African low-resource literature. This work provides first dialectal impact analysis for Igala and establishes baseline for future work.
Nov 3, 2026

HERIT: Enabling Global Access to Hanja-to-English Historical Translation by Mitigating Temporal Bias

Historical archives are invaluable for multidisciplinary research but remain inaccessible globally due to severe language barriers. While manual translation is prohibitively expensive and time-consuming, simply applying existing machine translation models is inadequate due to unique linguistic nuances and the temporal bias inherent in scarce human-labeled corpora. To address these challenges, we propose HERIT, a systematic domain-adaptation pipeline that leverages retrieval-augmented generation (RAG) to generate high-quality pseudo-labeled data from abundant Hanja-Korean corpora. This approach substantially expands the training dataset, mitigating both data scarcity and temporal overfitting across different historical periods. Extensive automated and human evaluations demonstrate that HERIT consistently outperforms baselines. Finally, we translate previously untranslated portions of the archives using our model, thereby enabling global access to these resources for researchers.
Nov 1, 2026

Current state of LLMs for Arabic dialectal machine translation

This work presents an evaluation of large language models (LLMs) for English to dialectal Arabic machine translation on the MADAR dataset. We evaluate both translation directions (English to Arabic and vice-versa) on 16 Arabic dialects. Our experiments cover a diverse set of models, including specialized Arabic models (Jais, Nile), multilingual models (Gemma, Command-R, Mistral, Aya), and commercial APIs (GPT-4.1). We employ multiple evaluation metrics: BLEU, CHRF, COMET (both reference-based and reference-less variants) and GEMBA (LLM-as-a-judge), as well as a small-scale manual evaluation, to assess translation quality. We discuss the challenges of automatic MT evaluation, especially in the context of Arabic dialects. We also evaluate the ability of LLMs to classify the dialect used in a text. The study offers insights into the capabilities and limitations of current LLMs for dialectal Arabic machine translation, particularly highlighting the difficulty of handling dialectal diversity, although the results may be influenced by possible training data contamination, which is always a concern with LLMs.
Nov 1, 2026

CULTURE-CMT: Benchmarking Contextualized Social Media Translation

Social-media comments are interactions, yet they are often translated and evaluated as isolated text. This mismatch is especially problematic when meaning depends on surrounding discussion, community-specific slang, or culturally situated expressions. We introduce CULTURE-CMT, a Chinese-English benchmark for contextualized social-media comment translation that restores the post and conversational context naturally available to users. Its 572 manually verified examples are organized into Slang, Context, and Both, enabling diagnostic analysis of distinct and interacting sources of translation difficulty. To support scalable evaluation, we further develop a retrieval-augmented cultural-effectiveness Judger that combines a calibrated scoring model with dynamically retrieved cultural knowledge. CULTURE-CMT reveals several non-trivial patterns. Providing interaction context improves most model configurations, but does not eliminate culturally ineffective translations. Examples requiring both contextual grounding and culturally situated language remain substantially more difficult than either source of difficulty alone. Moreover, larger models are not consistently better, and thinking produces highly model-dependent gains, including occasional degradation. In contrast, a 27B model adapted on benchmark-disjoint social-media data achieves the lowest observed invalidity rate among the evaluated configurations under thinking inference with context. Together, these results suggest that realistic social-media translation is not simply a matter of scaling models or reasoning longer, but of learning to translate meaning as it is constructed within evolving online interactions.
Nov 1, 2026

Retrieval-Enhanced Cultural Evaluation for Social Media Translation Training

Social media translation requires preserving meaning while capturing the cultural nuances of user-generated content (UGC). However, gaps in the cultural knowledge of LLM-based evaluators can lead to inaccurate assessments and unreliable training rewards. To improve these signals, we use retrieval-enhanced cultural evaluation to train CUE-MT, a family of social media translation models. A calibrated, domain-specific Judger guides supervised data refinement and is augmented by an Agent for hard-example mining and reinforcement learning. The Agent retrieves relevant external evidence as needed and distills it into concise hints that the Judger uses to score translations and assign rewards. Across 9B, 27B, and 35B-A3B backbones, CUE-MT outperforms the evaluated open-source baselines of comparable size on CUE-MT-Bench and three public benchmarks. Human evaluation on CUE-MT-Bench shows cultural effectiveness gains of 7.44-15.12 percentage points over the strongest external baseline in each size group. Retrieval improves the Judger's four-way classification accuracy by 8.07 percentage points over a matched no-retrieval baseline that uses LLM-generated hints alone. Training ablations further support the combination of hard-example mining and Agent-enhanced rewards.
Oct 29, 2026

Mobilizing the Archive: Bitext Extraction at Scale from Archival Documents for Extremely Low-resource Languages

While mining parallel sentences from web pages has proven effective for low-resource machine translation, the majority of the world's languages have little to no web presence. What they do have, though, are resources that are the result of centuries of efforts by linguists, such as grammars, dictionaries, and other documentation materials. We propose extracting translation examples from such linguistic resources, which offer parallel data for languages under-represented online and could potentially scale to thousands more languages. We develop a pipeline to achieve this, leveraging an Optical Character Recognition (OCR) model as well as a vision language model (VLM), to ensure identified content to be aligned with visual layout information. We demonstrate the utility of the extracted bitexts for bootstrapping translation systems across 20 languages, both by training machine translation models and by applying in-context learning for large language models. For in-context learning, we observe improvements of +15.78 and +6.94 chrF2++ over zero-shot translation for into low- and high-resource languages, respectively.
Oct 26, 2026

Beyond Words Alone: Disentangling Distributed Evidence for Visually Grounded Cultural Translation

Social media enables cross-lingual communication, yet the meaning of user-generated content (UGC) is often distributed across text, images, and cultural knowledge, making translation challenging. Existing evaluations typically treat images as optional and assume textual information is sufficient, obscuring whether errors stem from missing visual evidence or inadequate cultural adaptation. We introduce Culture-MMT, a diagnostic benchmark for distributed-evidence pragmatic reconstruction in social-media translation. It contains 498 curated, de-identified UGC instances across 20 domains, categorized into Symbol, Visual, and Hybrid by their required evidence. We also develop a human-aligned domain-specific judge, Judger, and a controlled evaluation framework that systematically varies the evidence available to translators. Across 17 model configurations, real images improve performance by +0.280 on Visual and +0.197 on Hybrid, but only +0.050 on Symbol, while random images provide no comparable gains. Human-authored descriptions further show that jointly dependent cases remain more challenging even when visual facts are explicit. These results characterize culturally effective social-media translation as {meaning reconstruction from distributed evidence}, highlighting visual grounding and cultural-pragmatic adaptation as distinct model bottlenecks.
Oct 23, 2026

Communicating with the Entire Population: Machine Translation of Emergency Alerts and Warnings

It is essential that we communicate with the entirety of an affected population during a crisis, including those who do not speak a region's dominant language(s). Commercial Translation tools offer a tempting solution to broaden access and can provide a lifeline when no other resources are available. However, Emergency response managers often operate in the dark regarding the quality and adequacy of these automated outputs. In this paper, we conduct a nationwide survey of emergency managers to understand their current workflows, perspectives, and operational challenges. We then evaluate commercial translation tools against these needs, shedding light on their utility and offering practical guidance on how and when these tools can be safely used in emergency response.
Oct 23, 2026

When is more search useful? An Empirical Study of Search Utility in Quality-Aware Decoding for Machine Translation

Quality-Aware Decoding (QAD) improves machine translation through test-time scaling, generating multiple candidate translations and selecting the final output with a quality-aware decoder. Usually the same candidate budget N is spent on every source sentence, assuming that all inputs require the same amount of search. We show that this assumption does not hold and that the quality gain obtained from additional candidates varies across sentences. We study search utility through three quantities: total scaling gain, how much quality a sentence can gain from a much larger candidate pool; marginal scaling gain, the expected gain from generating one additional batch of candidates; and the sampling saturation point, the candidate budget required to realize most of the total scaling gain. We investigate two sources of information for predicting these quantities: signals available before candidate-set expansion, and statistics computed from the candidate pool accumulated during search. We find that sentence-level signals correlate with total scaling gain but are less informative about the sampling saturation point. In contrast, properties of the current candidate pool provide useful signals of marginal scaling gain. Finally, we show that these signals can identify sentences that obtain larger gains when additional search is selectively applied.
Oct 23, 2026

EDWARD-NMT: Elastic Dimensions With Adaptive Routing and Dual-consistency for Neural Machine Translation

Sparse Mixture-of-Experts (MoE) is a powerful paradigm for scaling Neural Machine Translation (NMT) and managing language heterogeneity. However, practical limitations hinder its deployment on resource-constrained devices: the entire expert pool must remain in memory, and the per-token compute budget is statically fixed during training by rigid top-k routing. We introduce EDWARD-NMT (Elastic Dimensions With Adaptive Routing and Dual-consistency for NMT), a novel MoE encoder-decoder architecture designed for a train once, deploy anywhere paradigm that exposes a family of deployable sub-networks at inference time. EDWARD-NMT integrates three key innovations: (i) Matryoshka-style elastic dimensions to flexibly reduce the memory footprint; (ii) an adaptive sigmoid router with a learned, task-conditioned threshold, allowing each token to dynamically determine its active expert count; and (iii) a dual-consistency objective to maximize the performance of the extracted sub-networks. Extensive experiments on PhoMT (En-Vi), WMT-14 (En-De), multilingual OPUS-16, and a multi-domain De-En benchmark validate our approach. The full-capacity architecture matches or exceeds strong MoE baselines with improved parameter efficiency. Furthermore, the sub-networks seamlessly extracted from a single checkpoint consistently outperform comparably sized dense Transformers without any retraining.
Oct 21, 2026

Climbing the Ladder: Automating Data Pipelines and Reproducing Baselines in Low-Resource Settings

The massively multilingual translation systems that now include Sicilian learned it from noisy, non-standardised web text. To obtain better translation quality, we redevelop the small neural machine translation (NMT) system that Wdowiak customized for Sicilian. We rebuild on maintained software the extraction of the parallel text from the PDFs of the bilingual journal Arba Sicula, whose sentences are aligned by a language-agnostic sentence encoder with thresholds tuned against an existing hand alignment and then filtered for the typical errors of automatic alignment. Furthermore, the tokenization and the desinence-biased subword segmentation of the original system are ported to a Perl-free implementation, and all the results are measured on a frozen test set drawn from the journal. We compare small Transformers trained from scratch with the pretrained NLLB model adapted by low-rank fine-tuning, in both directions and with Italian as a closely related bridge language, and we adapt to the pretrained model the reverse-training recipe of the original system, i.e., a stage on forward-scored back-translations of the web Sicilian followed by a stage on the curated literary text. The pretrained model is by far the better of the two, and the staged training improves the translation into Sicilian more than the translation from it. On the test set of the original system, and in the tokenized space in which it was scored, the staged model with a larger adapter and more back-translations is above the reverse-training recipe in the directions that involve English and below it between Sicilian and Italian. Yet, a multilingual adapter degrades the directions on which it was not trained, which limits its use as a general multilingual model.
Oct 21, 2026

Towards English - Mizo Legal Machine Translation: Corpus Creation, Analysis, and Benchmarks

Indian court proceedings are held in English, so speakers of languages with limited translation technology have limited access to them. We present the first English Mizo parallel dataset of Indian court judgments. It contains 13,168 sentence pairs from the Gauhati High Court and the Supreme Court of India. Professional native Mizo translators translated complete documents; sentence pairs were manually aligned, and two independent reviewers checked the results. Our study finds that English words are borrowed in a very selective way: official and legal terms are almost always kept in English, but words for everyday things like actions, situations, and results are usually expressed in native Mizo. Mizo diacritics are also used inconsistently across the corpus. When we fine tune the NLLB 200 1.3B model on our training data, it scores 27.47 BLEU on a balanced legal test set of 1,000 sentence pairs, an improvement of 7.16 BLEU over the base model. However, it still uses English words about three times more often than a human translator does.
Oct 20, 2026

UvA-MT's Participation in the WMT26 General Translation Shared Task

This paper presents UvA-MT's submission to the WMT 2026 General Machine Translation shared task, competing in the unconstrained track across all 23 translation directions. This year, we fully leverage the test-time methods of Large Language Models (LLMs) for machine translation. Specifically, (1) we use sequential sampling with a refinement prompt to generate a pool of translation candidates for each source segment, a strategy shown to outperform traditional parallel sampling; and (2) we employ LLMs as pairwise judges to select the best candidate via a round-robin voting mechanism, with offline evaluation on the WMT25 benchmark showing a very clear improvement over point-wise best-of-N selection. Combined, these two strategies form our WMT26 submission.
Oct 18, 2026

Towards Figurative Language Understanding in Moroccan Darija: An Evaluation of Large Language Models

Figurative language remains a major challenge for Machine Translation (MT) systems, as the intended meaning of such expressions often goes beyond literal translation. Although recent advances in Large Language Models (LLMs) improved the translation of Arabic dialects, benchmark resources for evaluating figurative language translation in Moroccan Darija remain scarce. To this end, we introduce the Moroccan Darija Figurative Language Corpus (MDFC), a benchmark dataset for MT and multiple-choice question (MCQ) selection covering idioms, metaphors, and proverbs. Using MDFC, we evaluate 19 open- and closed-weight language models and MT systems at both the expression and contextual levels under zero-shot and six-shot settings. We also conduct layer-wise similarity-based probing to determine how model representations distinguish figurative from literal meanings. Our findings reveal that closed-weight models achieve the strongest translation performance, while the benefits of contextual information vary across models and tasks. Differences between translation performance and MCQ accuracy highlight the distinction between generating an appropriate figurative translation and recognizing the intended meaning among candidate translations.
Oct 18, 2026

Generation-Heavy Hybrid Machine Translation

The state of the art techniques in Machine Translation (MT) require large amounts of symmetric resources from source and target languages. This is true regardless of whether the approach is Transfer or Interlingua, Symbolic or Statistical. Symmetry within these approaches is necessary to ensure quality, robustness and retargetability. In reality, such symmetry, whether it is in terms of structural transfer lexicons, interlingual dictionaries or parallel corpora, is a major bottleneck in developing any MT system. This dissertation presents an approach to MT that addresses the lack of symmetry by exploiting symbolic and statistical target language resources in source-poor/target-rich language pairs. This approach is called Generation-Heavy Hybrid Machine Translation (GHMT). Expected source language resources include a syntactic parser and a simple one-to-many translation dictionary. No transfer rules or complex interlingual representations are used. Rich target language symbolic resources are used to overgenerate multiple structural variations from a target-glossed syntactic dependency representation of source language sentences. Statistical target-language resource are then used to select amongst the overgenerated translations. The source-target asymmetry of systems developed in this approach makes them more easily retargetable to new source languages.
Oct 17, 2026

GLOSS-MT: Controllable Low-Resource Machine Translation with an Editable Dictionary

Adapting a pretrained machine translation (MT) model to new terminology usually requires new parallel data and another round of fine-tuning, which is costly for low-resource languages. We ask whether controllability can be added to MT, and the fine-tuning burden reduced, without degrading the pretrained model. GLOSS-MT looks up the source's noun phrases in an offline English-Twi dictionary, replaces every phrase found by its Twi translation in place, and fine-tunes a translation model once to translate these mixed inputs. We apply the same data and pipeline to NLLB-200 (600M, 1.3B, 3.3B), OPUS-MT en-tw and TranslateGemma 4B. On a document-level English-to-Asante Twi benchmark (84 documents, four domains), every fine-tune scores above its pretrained base in chrF2 (+2.85 to +5.48), and the three NLLB fine-tunes are the best open systems (50.12-50.80). A direct controllability test on human-translated Bible passages shows that the three fine-tunes tested write 79-97% of the dictionary terms, and that replacing every dictionary entry by a different term changes the output accordingly (70-97% of the new terms appear) with no retraining. We release the models, data and code.
Oct 17, 2026

Training with Ciphers to Enhance In-Context Terminology Learning For Translation from Rare Languages

Fine-tuning LLMs with in-context examples (IC-Train) lets translation models adapt to new parallel data at deployment, but it is unclear whether they actually learn the translations of rare terms from those examples. We formalize this capability as in-context term learning (ICTL). We show that standard IC-Train develops this capability only weakly, and propose RareCipherFT, which strengthens it without any lexical resources. RareCipherFT pairs each training target with in-context examples that share a rare term with it. It then replaces that term with a character-shuffled cipher in both the context and the reference, so the term can only be recovered by copying from context. The ciphered fraction of training data is annealed to preserve translation quality. Across seven translation directions between English and Tamil, Assamese, Mizo, Nepali and Hausa, and four models from 1B to 7B parameters, RareCipherFT raises term recall over standard IC-Train by 5-15 absolute points without lowering COMET. Probes using synonyms, nonce words and controls for shared surface context show that these gains come from linking source terms to their in-context translations rather than from shortcuts.
Oct 17, 2026

When Opposite Premises Translate Identically: A Source-Conditioned Diagnostic for Multilingual Commonsense Items

Multilingual reasoning comparisons depend on translated premises preserving the relations in their English sources. Automatic translation scores can rank source-target pairs, but an acceptance decision alone cannot certify a counterfactual benchmark field. We test a source-contrast diagnostic for ACCORD premises: reverse the English polarity, translate both arms independently, count identical target outputs, and score each arm against its own source. Across 71 matched question identities at two containing-item depths, five target languages, and three translation checkpoints, Swahili has 63, 113, and 67 exact collisions among 710 pairs per checkpoint. At a human-reference-calibrated threshold, round-trip NLI passes both arms of 3 of the 113 NLLB-3.3B collisions, while LaBSE passes 78. Each collision proves at least one unfaithful translation, but does not identify its arm. These controlled measurements do not establish screening accuracy on spontaneous translation errors or a language-by-hop reasoning effect; the study has no native equivalence labels or answer-model evaluation.
Oct 16, 2026

MAS-Bai: Linguistically Informed Adaptive Multi-Agent Translation for Bowen-Script Bai

Large Language Models (LLMs) remain unreliable for extremely low-resource languages whose writing systems conflict with high-resource pretraining priors. We study Bai-Chinese translation in the Bowen script, where Chinese characters are frequently borrowed phonetically rather than semantically, causing severe literal-translation hallucinations. We propose MAS-Bai, a linguistically informed adaptive multi-agent framework for Bowen-script Bai-Chinese translation. MAS-Bai routes each input through either a lightweight retrieval-translation path or a deeper philological path with etymological and syntactic agents, and uses cycle-consistency with a lightweight reverse translator as an inference-time reliability signal. We construct a 6,536-sentence Bai-Chinese corpus and evaluate on a 1,536-sentence test set. MAS-Bai achieves 16.23 BLEU and 62.15 COMET, improving over Standard RAG by 8.11 BLEU and 6.85 COMET. Forward LoRA, expert ablations and controlled routing experiments distinguish the roles of supervised adaptation, Bai-specific expertise and conditional routing. The largest gains occur on Bowen phonetic loans and divergent Bai word order, while human evaluation and reverse-verifier analyses support the automatic results.
Oct 15, 2026

alkhder at AlexandriaX-2026: Context-Aware English-to-Dialectal Arabic Dialogue Translation with QLoRA-Fine-Tuned NileChat-3B

This paper describes team Alkhder's submission to Subtask 1 of the AlexandriaX-2026 shared task, which asks systems to translate English dialogue turns into thirteen Arabic dialects. We fine-tune NileChat-3B-Base with QLoRA on the Alexandria parallel dialogue corpus, training one set of adapter weights for all dialects. Each turn is translated conditioned on the target country and dialect, the domain, the participant roles, the speaker-addressee gender direction, and the preceding dialogue context. At inference, conversations are translated autoregressively and the model is fed its own previous outputs back as context without using any gold target-side test information. Under the constrained track, using only Alexandria data, it trains in about one hour and translates the private test set in under two hours. The system reaches a country-macro-averaged spBLEU of 20.36 and chrF++ of 36.64 on both tracks.
Oct 15, 2026

Unfragmenting Nawatl NMT: Single-Variant Specialization for Masewalkopa

In minoritized (low-resource) language technologies, a common response to data sparsity is to aggregate text across multiple varieties and treat the combined data as a single corpus. However, mixed corpora of closely related indigenous variants can produce an artificial register that is accountable to no single speaker community, a structural failure we call variant fragmentation. This issue is acute for minoritized languages native to Mexico, such as Nawatl. Building on a 70,000-pair multi-variant foundation, we specialize an mT5-large checkpoint to Masewalkopa (nhn), the Nawatl variety spoken in Santa Ana Tlacotenco. We curate 2,665 parallel pairs, reserve all sentence-level data for evaluation, and incorporate 192 elder-transcribed target sentences via asymmetric backtranslation. A custom finite-state analyzer reduces unanalyzed surface forms from 82.0% to 19.9% and supplies functional syntax tags as plain-text prefixes, allowing the model to reuse existing subword embeddings rather than relying on frozen special tokens. The resulting LoRA-v9c-b model achieves 58.46 dev chrF++ and 58.20/57.90 directional test chrF++. Finally, CTranslate2 int8 quantization reduces CPU latency from 137.5 to 1.8-2.6 seconds per request, enabling cost-bounded Cloud Run deployment.
Oct 14, 2026

Does Morphological Correctness Matter for Tokenization? A Scrambled Control Study in Tagalog

Typology-aware tokenizers are motivated by the claim that segmentation which respects morpheme boundaries preserves information that frequency-driven segmentation destroys. Studies routinely establish that it helps while assuming the boundaries must be linguistically correct. We separate them. Tagalog marks voice with infixes (s-um-ulat 'wrote', s-in-ulat 'was written'), so the root is not contiguous and no sequence of BPE merges can recover it. We build MorphAustro-Tok, a tokenizer that emits the root as a contiguous unit followed by a positional infix token, and compare it against a corpus-matched BPE baseline and, at two of three fertility levels, against a scrambled-morpheme control that preserves morph count, invertibility and per-type consistency while randomising the pseudo-infix. Across 33 runs, MorphAustro-Tok improves Tagalog machine translation over matched BPE by 0.84, 1.49 and 3.40 mean sentence-level chrF++ points. Token count does not explain the gain, since it grows as segmentation coarsens, and neither does capacity: at the coarsest level the scrambled arm carries more parameters and scores lower. Scrambling the analysis moves the gain by less than between-seed dispersion at both controlled levels, so we detect no contribution from morphological correctness at this scale.