Related papers: Contextual Code Switching for Machine Translation …

Instruction tuning (IT) is widely used to teach pretrained large language models (LLMs) to follow arbitrary instructions, but is under-studied in multilingual settings. In this work, we conduct a systematic study of zero-shot cross-lingual…

Large Language Models (LLMs) are rapidly reshaping machine translation (MT), particularly by introducing instruction-following, in-context learning, and preference-based alignment into what has traditionally been a supervised…

The capacity and effectiveness of pre-trained multilingual models (MLMs) for zero-shot cross-lingual transfer is well established. However, phenomena of positive or negative transfer, and the effect of language choice still need to be fully…

In recent years, pre-trained large language models (LLMs) have demonstrated remarkable efficiency in achieving an inference-time few-shot learning capability known as in-context learning. However, existing literature has highlighted the…

Zero-shot cross-lingual transfer by fine-tuning multilingual pretrained models shows promise for low-resource languages, but often suffers from misalignment of internal representations between languages. We hypothesize that even when the…

The rapid advancement of large language models (LLMs) has led to a significant increase in automated tools in the software engineering, capable of performing various code-related tasks such as code generation, completion, and translation.…

Large language models (LLMs) such as ChatGPT can produce coherent, cohesive, relevant, and fluent answers for various natural language processing (NLP) tasks. Taking document-level machine translation (MT) as a testbed, this paper provides…

In this work, we compare the domain-specific translation performance of open-source autoregressive decoder-only large language models (LLMs) with task-oriented machine translation (MT) models. Our experiments focus on the medical domain and…

Large Language Models (LLMs) are increasingly being applied across various domains, including code-related tasks such as code translation. Previous studies have explored using LLMs for translating code between different programming…

Users interacting with Large Language Models (LLMs) in a multi-turn conversation routinely refine their requests or pivot to new topics. LLMs, however, often miss these topic shifts and carry over irrelevant context from previous turns,…

Large language models have demonstrated exceptional performance across multiple crosslingual NLP tasks, including machine translation (MT). However, persistent challenges remain in addressing context-sensitive units (CSUs), such as…

Large language models (LLMs) have demonstrated strong performance in general-purpose machine translation, but their effectiveness in complex, domain-sensitive translation tasks remains underexplored. Recent advancements in Large Reasoning…

In the domain of software development, LLMs have been utilized to automate tasks such as code translation, where source code from one programming language is translated to another while preserving its functionality. However, LLMs often…

While large language models (LLMs) exhibit strong multilingual abilities, their reliance on English as latent representations creates a translation barrier, where reasoning implicitly depends on internal translation into English. When this…

Large Language Models (LLM's) have demonstrated considerable success in various Natural Language Processing tasks, but they have yet to attain state-of-the-art performance in Neural Machine Translation (NMT). Nevertheless, their significant…

LLMs are increasingly being deployed for multilingual applications and have demonstrated impressive translation capabilities between several low and high-resource languages. An aspect of translation that often gets overlooked is that of…

While large language models (LLMs) demonstrate remarkable success in multilingual translation, their internal core translation mechanisms, even at the fundamental word level, remain insufficiently understood. To address this critical gap,…

Large language models (LLMs) have showcased impressive multilingual machine translation ability. However, unlike encoder-decoder style models, decoder-only LLMs lack an explicit alignment between source and target contexts. Analyzing…

Language Models (LMs) can perform new tasks by adapting to a few in-context examples. For humans, explanations that connect examples to task principles can improve learning. We therefore investigate whether explanations of few-shot examples…

Language style is often used by writers to convey their intentions, identities, and mastery of language. In this paper, we show that current large language models struggle to capture some language styles without fine-tuning. To address this…