Related papers: Vuyko Mistral: Adapting LLMs for Low-Resource Dial…

Large Language Models (LLMs) demonstrate remarkable fluency across high-resource languages yet consistently fail to generate coherent text in Kashmiri, a language spoken by approximately seven million people. This performance disparity…

We present an ongoing initiative to provide open, very large, high-quality, and richly annotated textual datasets for almost 200 languages. At 30 trillion tokens, this is likely the largest generally available multilingual collection of LLM…

Large language models (LLMs) demonstrate exceptional performance on complex reasoning tasks. However, despite their strong reasoning capabilities in high-resource languages (e.g., English and Chinese), a significant performance gap persists…

LLMs are typically trained in high-resource languages, and tasks in lower-resourced languages tend to underperform the higher-resource language counterparts for in-context learning. Despite the large body of work on prompting settings, it…

Large Language Models (LLMs) generalize across tasks via reusable representations and flexible reasoning, yet remain brittle in real deployment under evolving tasks and continual distribution shift. A common approach is Test-Time Adaptation…

Large Language Models (LLMs) have advanced rapidly as tools for automating code generation in scientific research, yet their ability to interpret and use unfamiliar Python APIs for complex computational experiments remains poorly…

The evaluation of Large Language Models (LLMs) for translation tasks has primarily focused on high-resource languages, leaving a significant gap in understanding their performance on low-resource and endangered languages. This study…

Can large language models converse in languages virtually absent from their training data? We investigate this question through a case study on Tulu, a Dravidian language with over 2 million speakers but minimal digital presence. Rather…

This paper explores the integration of graph knowledge from linguistic ontologies into multilingual Large Language Models (LLMs) using adapters to improve performance for low-resource languages (LRLs) in sentiment analysis (SA) and named…

Commercial large language models (LLMs), like OpenAI's GPT-4 powering ChatGPT and Anthropic's Claude 3 Opus, have dominated natural language processing (NLP) benchmarks across different domains. New competing Open-Source alternatives like…

Learned metrics such as BLEURT have in recent years become widely employed to evaluate the quality of machine translation systems. Training such metrics requires data which can be expensive and difficult to acquire, particularly for…

General translation models often still struggle to generate accurate translations in specialized domains. To guide machine translation practitioners and characterize the effectiveness of domain adaptation methods under different data…

Recent advances in large language models (LLMs) have stepped forward the development of multilingual speech and machine translation by its reduced representation errors and incorporated external knowledge. However, both translation tasks…

In an evolving landscape of crisis communication, the need for robust and adaptable Machine Translation (MT) systems is more pressing than ever, particularly for low-resource languages. This study presents a comprehensive exploration of…

This paper presents a study on the feasibility of using large language models (LLM) for coding with low-resource and domain-specific programming languages that typically lack the amount of data required for effective LLM processing…

Recent regulatory initiatives like the European AI Act and relevant voices in the Machine Learning (ML) community stress the need to describe datasets along several key dimensions for trustworthy AI, such as the provenance processes and…

Existing large language models struggle to support numerous low-resource languages, particularly the extremely low-resource ones, for which there is minimal training data available for effective parameter updating. We thus investigate…

Language modeling has witnessed remarkable advancements in recent years, with Large Language Models (LLMs) like ChatGPT setting unparalleled benchmarks in human-like text generation. However, a prevailing limitation is the…

Retrieval-augmented generation (RAG) introduces additional information to enhance large language models (LLMs). In machine translation (MT), previous work typically retrieves in-context examples from paired MT corpora, or domain-specific…

\textbf{RE}trieval-\textbf{A}ugmented \textbf{L}LM-based \textbf{M}achine \textbf{T}ranslation (REAL-MT) shows promise for knowledge-intensive tasks like idiomatic translation, but its reliability under noisy retrieval contexts remains…