Today’s MT digest highlights a mix of system-building, evaluation, and post-training methods that sharpen multilingual performance across under-resourced and dialect-rich settings. Common threads include better support for non-English languages, more robust multilingual tool use, and methods to recover quality lost through quantization or biased evaluation pipelines.

Poly-Dialectal Neural Machine Translation System for Bangla Regional Dialects

Regional dialectal variation poses a fundamental challenge to natural language processing (NLP) in Bangla, where over 240 million speakers communicate across diverse regional variants that diverge significantly from Standard Colloquial Bangla (SCB) in phonology, morphology, and lexicon. Contemporary neural machine trans- lation (NMT) architectures and large language models (LLMs) predominantly as- sume a homogeneous language distribution, resulting in severe performance degra- dation when translating low-resource regional dialects. In this work, we present a unified Poly-Dialectal Neural Machine Translation System capable of multi-directional translation across 12 Bangla regional dialects without routing through an inter- mediary standard pivot. We compile the largest multi-dialect parallel corpus for Bangla to date, comprising 51,531 non-null parallel sentence pairs across 12 di- alects, incorporating 2,500 expert-verified, bidirectional parallel sentence pairs for five previously unaddressed dialects. Evaluating sequence-to-sequence architec- tures under Weight-Decomposed Low-Rank Adaptation (DoRA), our fine-tuned BanglaT5 model achieves state-of-the-art translation performance (29.26 BLEU, 57.26 chrF++), outperforming NLLB-200 (615M) and mBART-50 (611M) while preserving morphological coherence. Furthermore, we conduct a systematic cross- dialectal transfer analysis and dataset scaling study, establishing empirical thresh- olds for low-resource dialect adaptation. Finally, we deploy the optimized INT8- quantized model as an open-access web application to promote digital inclusion for marginalized dialect communities. The complete dataset is publicly available at Mendeley Data (https://data.mendeley.com/datasets/v9cf66fk2t/2).

When the API Speaks the Wrong Language: Revisiting Post-Training for Multilingual Tool Use

The reliability of Large Language Models (LLMs) for API calling degrades in multilingual settings. A common failure occurs when a model selects the correct tool but generates argument values in an inconsistent language, which we term Argument Language Mismatch (ALM). Although semantically correct, such outputs are operationally invalid and not captured by standard API-calling metrics. We revisit post-training strategies for mitigating ALM and find that, in our benchmark, supervised fine-tuning (SFT) provides a strong baseline, substantially improving argument language consistency and end-to-end function call accuracy. Under consistent model selection, SFT achieves performance comparable to, and sometimes exceeding more complex reinforcement learning (RL) approaches. We further examine whether RL with structured, argument-aware rewards offers additional benefits. While methods such as Group Relative Policy Optimization (GRPO) can improve language consistency and better preserve general reasoning ability, these gains are incremental and most pronounced in generalization and multi-objective trade-offs. Overall, our results suggest that much of the performance in multilingual API grounding can be achieved through careful supervised training, with RL providing targeted rather than fundamental improvements.

TELLME: Test-Enhanced Learning for Language Model Enrichment

Continual pre-training (CPT) has been widely adopted as a method for domain adaptation in large language models. However, CPT has consistently been accompanied by challenges, such as the difficulty of acquiring large-scale domain-specific datasets and high computational costs. In this study, we propose a novel method called Test-Enhanced Learning for Language Model Enrichment (TELLME) to alleviate these issues. TELLME leverages the TestEnhanced Learning (TEL) principle, whereby the model's training efficiency is improved using quizzes during training. It integrates this principle with CPT, thereby promoting efficient domain-specific knowledge acquisition and long-term memory retention. Experimental results demonstrate that TELLME outperforms existing methods by up to 23.6% in the financial domain and achieves a 9.8% improvement in long-term memory retention.

When the Knowledge Base Becomes the Gold Standard: Measuring Resource-Shared Evaluation Loops in Entity-Level Machine Translation

The Seungjeongwon Ilgi, a UNESCO Memory of the World record, is only 37.4% translated, and the most conspicuous failure mode in automatic translation is the person name -- a misread name corrupts the historical fact rather than merely the surface. Low-resource historical domains have no expert gold standard for entity translation, so practitioners substitute a knowledge base (KB) for the gold. That KB is the same resource injected into the system: scoring becomes self-referential and the metric measures instruction compliance rather than translation quality. We measure this loop. Using expert person-name annotations from the National Institute of Korean History as a gold independent of the injection pipeline, we hold the entity set fixed and vary only the provenance of the correct reading. Of 527 expert-annotated mentions, only 31.1% lie outside the injection pipeline, and the residual loop is not uniform -- in the overlapping segment the injected reading agrees with the human translation 97.8% of the time against 70.1% in the independent one, so the segment that looks healthiest is the one the loop is holding up. Across four models, a difference-in-differences analysis shows the gain from KB injection is confined to the segment whose gold shares the injected resource; in the independent segment it is at or below zero. Post-injection preservation clusters in a narrow 0.910-0.996 band even though baseline capability differs fivefold, so the reported gain is the complement of prior performance and weaker models appear to improve more dramatically. On an independent sample built by removing the construction filter, the measure replicates within model (overlapping intervals) while discriminating between models (non-overlapping intervals) -- it reflects a property of the model, not of the sample.

Language-Conditional Dequantization: Recovering What Quantization Steals from Non-English Languages

Aggressive quantization disproportionately harms multilingual capability: in the sub-4B INT3 GPTQ regime, we measure 2-4x larger perplexity degradation on non-English languages than on English. We propose Language-Conditional Dequantization (LCD), a post-hoc method that attaches per-language rank-2 LoRA corrections to the linear layers of an already-quantized model, adding 0.12% parameters per language and training in under 20 minutes on a single GPU. Across Qwen2.5-3B and Llama-3.2-3B, LCD recovers 70-83% of the perplexity gap for non-Latin script languages and 17-28% of the GlobalMMLU accuracy gap, outperforming a language-agnostic correction of equal capacity by 3-9 points on typologically distant languages and a data-free low-rank baseline (LQER) by an order of magnitude. We further identify a perplexity-accuracy disconnect and trace it to where quantization concentrates damage: early-depth errors (Llama) propagate downstream and resist local correction, while late-depth errors (Qwen) do not. A layer-restricted variant of LCD validates this mechanism directly.