We investigate a surprising limitation of LLMs: their inability to consistently generate text in a
user's desired language. We create the Language Confusion Benchmark (LCB) to evaluate …

Multilingual Large Language Models are capable of using powerful Large Language
Models to handle and respond to queries in multiple languages, which achieves remarkable …

Supervised fine-tuning (SFT), supervised instruction tuning (SIT) and in-context learning
(ICL) are three alternative, de facto standard approaches to few-shot learning. ICL has …

Task semantics can be expressed by a set of input-output examples or a piece of textual
instruction. Conventional machine learning approaches for natural language processing …

Improving the alignment of Large Language Models (LLMs) with respect to the cultural
values that they encode has become an increasingly important topic. In this work, we study …

Work on instruction-tuned Large Language Models (LLMs) has used automatic methods
based on text overlap and LLM judgments as cost-effective alternatives to human …

Despite the recent popularity of Large Language Models (LLMs) in Machine Translation
(MT), their performance in low-resource languages (LRLs) still lags significantly behind …

Abstract Recently, Large Language Models (LLMs) have shown impressive language
capabilities, while most of them have very unbalanced performance across different …

The successful adaptation of multilingual language models (LMs) to a specific language-
task pair critically depends on the availability of data tailored for that condition. While cross …

Multilingual large language models (MLLMs) leverage advanced large language models to
process and respond to queries across multiple languages, achieving significant success in …