Here is today's selection of cs.CL papers exploring advancements in multilingual and multimodal machine translation. The common theme focuses on developing innovative pipelines, benchmarks, and datasets to enhance translation quality and adaptability across diverse languages and cultural contexts.

A U-Net and Transformer Pipeline for Multilingual Image Translation

This paper presents an end-to-end multilingual translation pipeline that integrates a custom U-Net for text detection, the Tesseract engine for text recognition, and a from-scratch sequence-to-sequence (Seq2Seq) Transformer for Neural Machine Translation (NMT). Our approach first utilizes a U-Net model, trained on a synthetic dataset , to accurately segment and detect text regions from an image. These detected regions are then processed by Tesseract to extract the source text. This extracted text is fed into a custom Transformer model trained from scratch on a multilingual parallel corpus spanning 5 languages. Unlike systems reliant on monolithic pre-trained models, our architecture emphasizes full customization and adaptability. The system is evaluated on its text detection accuracy, text recognition quality, and translation performance via BLEU scores. The complete pipeline demonstrates promising results, validating the viability of a custom-built system for translating text directly from images.

Quality-Aware Translation Tagging in Multilingual RAG system

Multilingual Retrieval-Augmented Generation (mRAG) often retrieves English documents and translates them into the query language for low-resource settings. However, poor translation quality degrades response generation performance. Existing approaches either assume sufficient translation quality or utilize the rewriting method, which introduces factual distortion and hallucinations. To mitigate these problems, we propose Quality-Aware Translation Tagging in mRAG (QTT-RAG), which explicitly evaluates translation quality along three dimensions-semantic equivalence, grammatical accuracy, and naturalness&fluency-and attach these scores as metadata without altering the original content. We evaluate QTT-RAG against CrossRAG and DKM-RAG as baselines in two open-domain QA benchmarks (XORQA, MKQA) using six instruction-tuned LLMs ranging from 2.4B to 14B parameters, covering two low-resource languages (Korean and Finnish) and one high-resource language (Chinese). QTT-RAG outperforms the baselines by preserving factual integrity while enabling generator models to make informed decisions based on translation reliability. This approach allows for effective usage of cross-lingual documents in low-resource settings with limited native language documents, offering a practical and robust solution across multilingual domains.

M$^{3}$T2IBench: A Large-Scale Multi-Category, Multi-Instance, Multi-Relation Text-to-Image Benchmark

Text-to-image models are known to struggle with generating images that perfectly align with textual prompts. Several previous studies have focused on evaluating image-text alignment in text-to-image generation. However, these evaluations either address overly simple scenarios, especially overlooking the difficulty of prompts with multiple different instances belonging to the same category, or they introduce metrics that do not correlate well with human evaluation. In this study, we introduce M$^3$T2IBench, a large-scale, multi-category, multi-instance, multi-relation along with an object-detection-based evaluation metric, $AlignScore$, which aligns closely with human evaluation. Our findings reveal that current open-source text-to-image models perform poorly on this challenging benchmark. Additionally, we propose the Revise-Then-Enforce approach to enhance image-text alignment. This training-free post-editing method demonstrates improvements in image-text alignment across a broad range of diffusion models. \footnote{Our code and data has been released in supplementary material and will be made publicly available after the paper is accepted.}

M4FC: a Multimodal, Multilingual, Multicultural, Multitask Real-World Fact-Checking Dataset

Existing real-world datasets for multimodal automated fact-checking have multiple limitations: they contain few instances, focus on only one or two languages and tasks, suffer from evidence leakage, or depend on external sets of news articles for sourcing true claims. To address these shortcomings, we introduce M4FC, a new real-world dataset comprising 4,982 images paired with 6,980 claims. The images, verified by professional fact-checkers from 22 organizations, represent diverse cultural and geographic contexts. Each claim is available in one or two out of ten languages. M4FC spans six multimodal fact-checking tasks: visual claim extraction, claimant intent prediction, fake detection, image contextualization, location verification, and verdict prediction. We provide baseline results for all tasks and analyze how combining intermediate tasks influence downstream verdict prediction performance. We make our dataset and code available.

AfriMTEB and AfriE5: Benchmarking and Adapting Text Embedding Models for African Languages

Text embeddings are an essential building component of several NLP tasks such as retrieval-augmented generation which is crucial for preventing hallucinations in LLMs. Despite the recent release of massively multilingual MTEB (MMTEB), African languages remain underrepresented, with existing tasks often repurposed from translation benchmarks such as FLORES clustering or SIB-200. In this paper, we introduce AfriMTEB -- a regional expansion of MMTEB covering 59 languages, 14 tasks, and 38 datasets, including six newly added datasets. Unlike many MMTEB datasets that include fewer than five languages, the new additions span 14 to 56 African languages and introduce entirely new tasks, such as hate speech detection, intent detection, and emotion classification, which were not previously covered. Complementing this, we present AfriE5, an adaptation of the instruction-tuned mE5 model to African languages through cross-lingual contrastive distillation. Our evaluation shows that AfriE5 achieves state-of-the-art performance, outperforming strong baselines such as Gemini-Embeddings and mE5.