We present **JPharmatron**, a Japanese domain-specific large language model (LLM) for the pharmaceutical field, developed through continual pre-training on two billion Japanese pharmaceutical tokens and eight billion English biomedical tokens. For rigorous evaluation, we introduce **JPharmaBench**, a benchmark suite consisting of three new benchmarks: YakugakuQA, based on national pharmacist licensing exams; NayoseQA, which tests cross-lingual synonym and terminology normalization; and SogoCheck, a novel task involving cross-document consistency checking.We evaluate our model against open-source medical LLMs and commercial models, including GPT-4o. Experimental results show that **JPharmatron** outperforms existing open models and achieves competitive performance with commercial ones.Interestingly, even GPT-4o performs poorly on SogoCheck, suggesting that cross-sentence consistency reasoning remains an open challenge.**JPharmatron** enables secure and local model deployment for pharmaceutical tasks, where privacy and legal constraints limit the use of closed models. Besides, **JPharmaBench** offers a reproducible framework for evaluating Japanese pharmaceutical natural language processing. Together, they demonstrate the feasibility of practical and cost-efficient language models for Japanese healthcare and pharmaceutical sectors.Our model, codes, and datasets are available on HuggingFace: https://huggingface.co/collections/EQUES/jpharmatron and https://huggingface.co/collections/EQUES/jpharmabench.

We study automatic post-editing for patent translation, where accuracy and traceability are critical, and propose a two-step pipeline that combines a multilingual encoder for token-level error detection with an LLM for targeted correction. As no word-level annotations exist for Japanese–English patents, we create supervised data by injecting synthetic errors into parallel patent sentences and fine-tune mBERT, XLM-RoBERTa, and mDeBERTa as detectors. In the second stage, GPT-4o is prompted to revise translations either freely or under a restricted policy that allows edits only on detector-marked spans. For error detection, evaluation on synthetic errors shows that encoder-based detectors outperform LLMs in both F1 and MCC. For error correction, tests on synthetic, repetition, and omission datasets demonstrate statistically significant BLEU gains over LLM methods for synthetic and repetition errors, while omission errors remain challenging. Overall, pairing compact encoders with an LLM enables more accurate and controllable post-editing for key patent error types, reducing unnecessary rewrites via restricted edits. Future work will focus on strengthening omission modeling to better detect and correct missing content.

In patent documents, patent claims represent a particularly important section as they define the scope of the claims. However, due to the length and unique formatting of these sentences, neural machine translation (NMT) systems are prone to translation errors, such as omissions and repetitions. To address these challenges, this study proposes a translation method that first segments the source sentences into multiple shorter clauses using a clause segmentation model tailored to facilitate translation. These segmented clauses are then translated using a clause translation model specialized for clause-level translation. Finally, the translated clauses are rearranged and edited into the final translation using a reordering and editing model. In addition, this study proposes a method for constructing clause-level parallel corpora required for training the clause segmentation and clause translation models. This method leverages word alignment tools to create clause-level data from sentence-level parallel corpora. Experimental results demonstrate that the proposed method achieves statistically significant improvements in BLEU scores compared to conventional NMT models. Furthermore, for sentences where conventional NMT models exhibit omissions and repetitions, the proposed method effectively suppresses these errors, enabling more accurate translations.

This paper presents the submission of NTTSU for the constrained track of the English–Japanese and Japanese–Chinese at the WMT2025 general translation task.For each translation direction, we build translation models from a large language model by combining continual pretraining, supervised fine-tuning, and preference optimization based on the translation quality and adequacy.We finally generate translations via context-aware MBR decoding to maximize translation quality and document-level consistency.

This paper aims to augment fans’ ability to critique and exploreinformation related to celebrities of interest. First, we collect postsfrom X (formerly Twitter) that discuss matters related to specificcelebrities. For the collection of major impressions from these posts,we employ ChatGPT as a large language model (LLM) to analyze andsummarize key sentiments. Next, based on collected impressions, wesearch for Web pages and collect the content of the top 30 ranked pagesas the source for exploring the reasons behind those impressions. Oncethe Web page content collection is complete, we collect and aggregatedetailed reasons for the impressions on the celebrities from the contentof each page. For this part, we continue to use ChatGPT, enhanced bythe retrieval augmented generation (RAG) framework, to ensure thereliability of the collected results compared to relying solely on theprior knowledge of the LLM. Evaluation results by comparing a referencethat is manually collected and aggregated reasons with those predictedby ChatGPT revealed that ChatGPT achieves high accuracy in reasoncollection and aggregation. Furthermore, we compared the performance ofChatGPT with an existing model of mT5 in reason collection and confirmedthat ChatGPT exhibits superior performance.

The NTTSU team’s submission leverages several large language models developed through a training procedure that includes continual pre-training and supervised fine-tuning. For paragraph-level translation, we generated synthetic paragraph-aligned data and utilized this data for training.In the task of translating Japanese to Chinese, we particularly focused on the speech domain translation. Specifically, we built Whisper models for Japanese automatic speech recognition (ASR). We used YODAS dataset for Whisper training. Since this data contained many noisy data pairs, we combined the Whisper outputs using ROVER for polishing the transcriptions. Furthermore, to enhance the robustness of the translation model against errors in the transcriptions, we performed data augmentation by forward translation from audio, using both ASR and base translation models.To select the best translation from multiple hypotheses of the models, we applied Minimum Bayes Risk decoding + reranking, incorporating scores such as COMET-QE, COMET, and cosine similarity by LaBSE.