Today’s MT digest highlights how translation-adjacent research is expanding beyond sentence conversion into design, speech, multimodal documents, and social media analysis. A common thread is stronger control over language behavior: several works focus on reducing language confusion, preserving style or pronunciation, and improving performance through targeted optimization or selective data augmentation. Another shared theme is evaluation in real-world settings, with emphasis on practical pipelines and applied media understanding rather than isolated benchmark gains.

Text Style Transfer with Machine Translation for Graphic Designs

Globalization of graphic designs such as those used in marketing materials and magazines is increasingly important for communication to broad audiences. To accomplish this, the textual content in the graphic designs needs to be accurately translated and have the text styling preserved in order to fit visually into the design. Preserving text styling requires high accuracy word alignment between the original and the translated text. The problem of word alignment between source and translated text is long known. The industry standards for extracting word alignments are defined by Giza++ and attention probabilities from neural machine translation (NMT) models. In this paper, we explore three new methods to tackle the word alignment problem for transferring text styles from the source to the translated text. The proposed methods are developed on top of commercially available NMT and LLM translation technologies. They include: NMT with custom input and output tags for text styling; LLM with custom input and output tags; a hybrid with NMT for translation followed by an LLM with use of unigram mappings. To analyze the performance of these solutions, their alignment results are compared with the results of an attention head approach to gauge their usability in graphic design applications. Interestingly, the attention head strong baseline proves more accurate than the LLM or NMT approach and on par with the hybrid NMT+LLM approach.

TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models

Large language models (LLMs) demonstrate strong multilingual capabilities, yet often fail to consistently generate responses in the intended language, exhibiting a phenomenon known as language confusion. Prior mitigation approaches based on sequence-level fine-tuning, such as DPO, ORPO, and GRPO, operate at the level of entire responses and can lead to unintended degradation of general model capabilities, motivating the need for more fine-grained alternatives. To address this, we introduce Token-Level Policy Optimization (TLPO), a fine-tuning framework designed to mitigate language confusion through localized, token-level updates. TLPO identifies error-prone positions, explores alternative candidate tokens, and updates the policy using a tailored objective to suppress error-inducing outputs at a granular level. This selective intervention enables effective mitigation of language confusion without compromising the model's general abilities. Experiments on multiple multilingual LLMs across diverse languages demonstrate that TLPO significantly outperforms baselines in improving language consistency while preserving downstream task accuracy.

Benchmarking Complex Multimodal Document Processing Pipelines: A Unified Evaluation Framework for Enterprise AI

Most enterprise document AI today is a pipeline. Parse, index, retrieve, generate. Each of those stages has been studied to death on its own -- what's still hard is evaluating the system as a whole. We built EnterpriseDocBench to take a swing at it: parsing fidelity, indexing efficiency, retrieval relevance, and generation groundedness, all on the same corpus. The corpus is built from public, permissively licensed documents across six enterprise domains (five represented in the current pilot). We ran three pipelines through it -- BM25, dense embedding, and a hybrid -- all with the same GPT-5 generator. The headline numbers: hybrid retrieval narrowly beats BM25 (nDCG@5 of 0.92 vs. 0.91), and both beat dense embedding (0.83). Hallucination doesn't grow monotonically with document length -- short documents and very long ones both hallucinate more than medium ones (28.1% and 23.8% vs. 9.2%). Cross-stage correlations are very weak: parsing->retrieval r=0.14, parsing->generation r=0.17, retrieval->generation 0.02. If quality were cascading the way most of us assume, those numbers would be much higher; they aren't. Design caveats are real (parsing fixed, generator shared, automated proxy metrics) and we don't oversell the result. One result that genuinely surprised us: factual accuracy on stated claims is 85.5%, but answer completeness averages 0.40. The system is right when it answers -- it just leaves things out. That gap matters more for real deployments than the headline accuracy number does. We also describe three reference architectures (ColPali, ColQwen2, agentic complexity-based routing) which are not yet integrated end-to-end. Framework, metrics, baselines, and collection scripts will be released open-source on acceptance.

Classification of Public Opinion on the Free Nutritional Meal Program on YouTube Media Using the LSTM Method

Public opinion towards the Free Nutritious Meal Program (MBG) on YouTube social media reflects diverse community responses. This study applies the Long Short-Term Memory (LSTM) method to classify sentiments from 7,733 YouTube comments. The results show that the LSTM model achieves 89% accuracy, with strong performance on negative sentiment (F1-score 0.94) but weaker performance on positive sentiment (F1-score 0.55) due to class imbalance, as negative data account for 87.7% of the dataset. These findings confirm the effectiveness of LSTM for sentiment analysis of Indonesian text while highlighting the challenge of imbalanced data. This research contributes to social media-based public policy evaluation

Selective Augmentation: Improving Universal Automatic Phonetic Transcription via G2P Bootstrapping

In the field of universal automatic phonetic transcription (APT), clean and diverse training transcriptions are required. However, such high-quality data is limited. We propose the bootstrapping approach Selective Augmentation to improve the available training transcriptions by selectively transferring distinctions between languages. Based on the model MultIPA, we exemplarily show that we could increase the accuracy of an existing feature (plosive voicing) and add a new feature (plosive aspiration) by augmenting the existing training data using information from a separate helper language (Hindi). We describe intrinsic challenges of the evaluation and develop objective metrics to determine the success: Voicing accuracy was increased by 17.6% by reducing the number of false positives. Additionally, aspiration recognition was introduced: While the baseline transcribed 0% of German /p, t, k/ as aspirated, our approach transcribed them as aspirated in 61.2% of the cases. Introducing aspiration recognition to APT models allowed for the tenuis class to be successfully reduced by 32.2%, which also reduces the conflations between the test language's plosives.