Related papers: Multilingual Blending: LLM Safety Alignment Evalua…

Large language models (LLMs) are increasingly being adopted in educational settings. These applications expand beyond English, though current LLMs remain primarily English-centric. In this work, we ascertain if their use in education…

The safety alignment of large language models (LLMs) is becoming increasingly important with their democratization. In this paper, we study the safety degradation that comes with adapting LLMs to new tasks. We attribute this safety…

We present the first comprehensive study of Memorization in Multilingual Large Language Models (MLLMs), analyzing 95 languages using models across diverse model scales, architectures, and memorization definitions. As MLLMs are increasingly…

Multilingual Large Language Models are capable of using powerful Large Language Models to handle and respond to queries in multiple languages, which achieves remarkable success in multilingual natural language processing tasks. Despite…

The performance differential of large language models (LLM) between languages hinders their effective deployment in many regions, inhibiting the potential economic and societal value of generative AI tools in many communities. However, the…

Multilingual Large Language Models (LLMs) have gained large popularity among Natural Language Processing (NLP) researchers and practitioners. These models, trained on huge datasets, show proficiency across various languages and demonstrate…

Most current large language models (LLMs) support a wide variety of languages in addition to English, including high-resource languages (e.g. German, Chinese, French), as well as low-resource ones (e.g. Swahili, Telugu). In addition they…

Roadway safety and mobility remain critical challenges for modern transportation systems, demanding innovative analytical frameworks capable of addressing complex, dynamic, and heterogeneous environments. While traditional engineering…

Large language models (LLMs) have become integral to a wide range of applications worldwide, driving an unprecedented global demand for effective multilingual capabilities. Central to achieving robust multilingual performance is the…

Clinical trial matching is a key process in health delivery and discovery. In practice, it is plagued by overwhelming unstructured data and unscalable manual processing. In this paper, we conduct a systematic study on scaling clinical trial…

The rapid advancement of Large Language Models (LLMs) has brought about remarkable generative capabilities but also raised concerns about their potential misuse. While strategies like supervised fine-tuning and reinforcement learning from…

The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve model safety and trustworthiness, adversaries can exploit these techniques to undermine…

As vision-language models (VLMs) become increasingly capable, maintaining a balance between safety and usefulness remains a central challenge. Safety mechanisms, while essential, can backfire, causing over-refusal, where models decline…

Aligned representations across languages is a desired property in multilingual large language models (mLLMs), as alignment can improve performance in cross-lingual tasks. Typically alignment requires fine-tuning a model, which is…

Multilingual LLMs are increasingly used when instruction, source content, and required response languages do not coincide. Existing benchmarks have expanded multilingual instruction-following evaluation, but they rarely isolate these three…

Language Confusion is a phenomenon where Large Language Models (LLMs) generate text that is neither in the desired language, nor in a contextually appropriate language. This phenomenon presents a critical challenge in text generation by…

Despite their strong ability to retrieve knowledge in English, current large language models show imbalance abilities in different languages. Two approaches are proposed to address this, i.e., multilingual pretraining and multilingual…

Existing large language models (LLMs) for machine translation are typically fine-tuned on sentence-level translation instructions and achieve satisfactory performance at the sentence level. However, when applied to document-level…

This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs). These challenges are organized into three different categories: scientific understanding of LLMs, development and…

Large Language Models (LLMs) are known to lack cultural representation and overall diversity in their generations, from expressing opinions to answering factual questions. To mitigate this problem, we propose multilingual prompting: a…