The paper proposes MACAT, a Multi-Agent Culture-Aware Translation framework, to selectively translate culture-loaded words in ancient Chinese texts, achieving superior performance over existing method…

The paper benchmarks local, offline LLMs for confidential translation workflows, demonstrating that while they are viable for privacy-sensitive use, they generally lag behind top commercial NMT system…

The paper introduces OpenSTBench, a unified, multidimensional evaluation framework designed to comprehensively compare heterogeneous speech translation systems by jointly assessing translation, speech…

The paper proposes an aggressive, parameter-efficient method to prune non-essential experts from Mixture-of-Experts (MoE) LLMs, significantly compressing the model while maintaining high machine trans…

The paper proposes an advanced auditing framework for classical-to-modern LLM translations, demonstrating that embedding drift signals potential error severity rather than error itself, and identifyin…

The paper proposes Luar, a framework that trains reasoning language models to selectively use English translation only when their direct understanding of a non-English input is unreliable, significant…

The paper introduces Loong, a novel human-like agent that significantly improves long document translation by adaptively selecting and utilizing optimal historical context using a specialized memory m…

This paper investigates improving speculative decoding for multilingual LLM inference, finding that n-gram draft models offer consistent speed-ups across languages despite lower token acceptance rates…

This paper proposes a domain-specialized large language model, PoetryQwen, for precise translation and emotional understanding of classical poetry.

Elevator is a novel, deterministic binary translator that statically translates entire x86-64 executables to AArch64 by considering all possible interpretations of every byte, eliminating the need for…

The paper proposes DOA, a training-free attention policy that leverages self-attention in decoder-only SpeechLLMs to achieve high-quality, low-latency simultaneous long-form translation without requir…

The paper introduces and evaluates five parameter alignment strategies that significantly mitigate catastrophic forgetting when continually pretraining multilingual expert language models across multi…

The paper demonstrates that the internal signals governing figurative language generation are reusable across multiple languages, showing that a steering direction learned in one language can effectiv…

The paper shows that safety failures in low-resource languages are due to a failure in the model's safety decision calibration, not a lack of underlying knowledge, and proposes a recalibration method…

The paper introduces MIDI, a novel multilingual dataset that embeds idioms in realistic sentence and conversational contexts across diverse resource levels, revealing that idiom comprehension is signi…

This paper introduces a Hybrid Mixture-of-Experts (HybridMoE) framework and a specialized corpus (Varnika) to significantly improve language models' ability to understand and retain figurative, cultur…

This paper demonstrates that multilingual code-switching instruction tuning, involving four languages (English, Japanese, Korean, and Chinese), significantly improves average multilingual performance,…

The paper introduces XLGoBench, a synthetic benchmark of algorithmic tasks designed to detect persistent cross-lingual skill gaps in large language models.

The paper proposes using GPT-4o to generate controlled paraphrases of target text for sign language translation (SLT) augmentation, achieving significant BLEU-4 improvements on PHOENIX14T.

The paper develops a theoretically grounded framework for evaluating multilingual LLMs in Social Sciences and Humanities, moving beyond traditional NLP benchmarks to assess interpretive validity and c…