Related papers: Multi-Lingual Malaysian Embedding: Leveraging Larg…

Multimodal large language models (MLLMs) have shown success in vision-language tasks, but their ability to reason over complex educational materials remains largely untested. This work presents the first evaluation of state-of-the-art…

Retrieval-augmented generation (RAG) extends large language models (LLMs) with external knowledge, but it must balance limited effective context, redundant retrieved evidence, and the loss of fine-grained facts under aggressive compression.…

In enterprise settings, efficiently retrieving relevant information from large and complex knowledge bases is essential for operational productivity and informed decision-making. This research presents a systematic empirical framework for…

Large language models (LLMs) have advanced the state of the art in natural language processing. However, their predominant design for English or a limited set of languages creates a substantial gap in their effectiveness for low-resource…

Modern moderation systems increasingly support multiple languages, but often fail to address localisation and low-resource variants - creating safety gaps in real-world deployments. Small models offer a potential alternative to large LLMs,…

Recent large language models (LLMs) demonstrate impressive capabilities in handling long contexts, some exhibiting near-perfect recall on synthetic retrieval tasks. However, these evaluations have mainly focused on English text and involved…

Embedding models are crucial for various natural language processing tasks but can be limited by factors such as limited vocabulary, lack of context, and grammatical errors. This paper proposes a novel approach to improve embedding…

Large Language Models (LLMs) have consistently showcased remarkable generalization capabilities when applied to various language tasks. Nonetheless, harnessing the full potential of LLMs for Radiology Report Generation (R2Gen) still…

We introduce the multilingual Granite Embedding R2 models, a family of encoder-based embedding models for enterprise-scale dense retrieval across 200+ languages. Extending our English-focused R2 release, these models add enhanced support…

Researchers working on low-resource languages face persistent challenges due to limited data availability and restricted access to computational resources. Although most large language models (LLMs) are predominantly trained in…

Retrieval Augmented Generation (RAG) is emerging as a powerful technique to enhance the capabilities of Generative AI models by reducing hallucination. Thus, the increasing prominence of RAG alongside Large Language Models (LLMs) has…

Semantic textual similartiy (STS) and information retrieval tasks (IR) tasks have been the two major avenues to record the progress of embedding models in the past few years. Under the emerging Retrieval-augmented Generation (RAG) paradigm,…

Research on Multi-modal Large Language Models (MLLMs) towards the multi-image cross-modal instruction has received increasing attention and made significant progress, particularly in scenarios involving closely resembling images (e.g.,…

Large Language Models (LLMs) generate responses to questions; however, their effectiveness is often hindered by sub-optimal quality of answers and occasional failures to provide accurate responses to questions. To address these challenges,…

Retrieval-Augmented Generation (RAG) is essential for integrating external knowledge into Large Language Model (LLM) outputs. While the literature on RAG is growing, it primarily focuses on systematic reviews and comparisons of new…

Large language models (LLM) hold significant potential for applications in biomedicine, but they struggle with hallucinations and outdated knowledge. While retrieval-augmented generation (RAG) is generally employed to address these issues,…

With hundreds of multilingual embedding models available, practitioners lack clear guidance on which provide genuine cross-lingual semantic alignment versus task performance through language-specific patterns. Task-driven benchmarks (MTEB)…

We present F2LLM-v2, a new family of general-purpose, multilingual embedding models in 8 distinct sizes ranging from 80M to 14B. Trained on a newly curated composite of 60 million publicly available high-quality data samples, F2LLM-v2…

The choice of embedding model is a crucial step in the design of Retrieval Augmented Generation (RAG) systems. Given the sheer volume of available options, identifying clusters of similar models streamlines this model selection process.…

Large Reasoning Models (LRMs) still exhibit large performance gaps between English and other languages, yet much current work assumes these gaps can be closed simply by making reasoning in every language resemble English reasoning. This…