Related papers: TransliCo: A Contrastive Learning Framework to Add…
Multilingual Large Language Models (LLMs) develop cross-lingual abilities despite being trained on limited parallel data. However, they often struggle to generate responses in the intended language, favoring high-resource languages such as…
Large language models are powerful but often limited by high computational cost, privacy concerns, and English-centric training. Recent progress demonstrates that small, efficient models with around one billion parameters can deliver strong…
Research on language technology for the development of medical applications is currently a hot topic in Natural Language Understanding and Generation. Thus, a number of large language models (LLMs) have recently been adapted to the medical…
Transfer learning based on pretraining language models on a large amount of raw data has become a new norm to reach state-of-the-art performance in NLP. Still, it remains unclear how this approach should be applied for unseen languages that…
As instruction-tuned large language models (LLMs) gain global adoption, their ability to follow instructions in multiple languages becomes increasingly crucial. In this work, we investigate how multilinguality during instruction tuning of a…
As large language models (LLMs) are deployed in multilingual settings, their safety behavior in culturally diverse, low-resource languages remains poorly understood. We present the first systematic evaluation of LLM safety across 12 Indic…
Developing a unified multilingual model has long been a pursuit for machine translation. However, existing approaches suffer from performance degradation -- a single multilingual model is inferior to separately trained bilingual ones on…
Cross-lingual transfer in language models is difficult to study in natural corpora because lexical overlap, morphology, data imbalance, and tokenization are entangled. We introduce an in-vitro framework with two procedurally generated…
The curse of multilinguality phenomenon is a fundamental problem of multilingual Large Language Models (LLMs), where the competition between massive languages results in inferior performance. It mainly comes from limited capacity and…
Pre-trained Language Models (PLMs) have achieved remarkable performance gains across numerous downstream tasks in natural language understanding. Various Chinese PLMs have been successively proposed for learning better Chinese language…
Multilingual programming, which involves using multiple programming languages (PLs) in a single project, is increasingly common due to its benefits. However, it introduces cross-language bugs (CLBs), which arise from interactions between…
The training of large language models (LLMs) necessitates substantial data and computational resources, and updating outdated LLMs entails significant efforts and resources. While numerous model editing techniques (METs) have emerged to…
The language ability of Large Language Models (LLMs) is often unbalanced towards English because of the imbalance in the distribution of the pre-training data. This disparity is demanded in further fine-tuning and affecting the…
Existing work in multilingual pretraining has demonstrated the potential of cross-lingual transferability by training a unified Transformer encoder for multiple languages. However, much of this work only relies on the shared vocabulary and…
Due to high data demands of current methods, attention to zero-shot cross-lingual spoken language understanding (SLU) has grown, as such approaches greatly reduce human annotation effort. However, existing models solely rely on shared…
Recently, large language models (LLMs) have emerged as a groundbreaking technology and their unparalleled text generation capabilities have sparked interest in their application to the fundamental sentence representation learning task.…
The impressive performance of GPT-3 using natural language prompts and in-context learning has inspired work on better fine-tuning of moderately-sized models under this paradigm. Following this line of work, we present a contrastive…
Contrastive learning is a well-established paradigm in representation learning. The standard framework of contrastive learning minimizes the distance between "similar" instances and maximizes the distance between dissimilar ones in the…
Natural Language Processing systems are heavily dependent on the availability of annotated data to train practical models. Primarily, models are trained on English datasets. In recent times, significant advances have been made in…
We study the problem of multilingual masked language modeling, i.e. the training of a single model on concatenated text from multiple languages, and present a detailed study of several factors that influence why these models are so…