Model Detail
multilingual-e5-large
—AfriVoices-KE: A Multilingual Speech Dataset for Kenyan Languages
arXiv:2604.08448v1 Announce Type: new Abstract: AfriVoices-KE is a large-scale multilingual speech dataset comprising approximately 3,000 hours of audio across five Kenyan languages: Dholuo, Kikuyu, Kalenjin, Maasai, and Somali. The dataset includes 750 hours of scripted speech and 2,250 hours of sp
Mina: A Multilingual LLM-Powered Legal Assistant Agent for Bangladesh for Empowering Access to Justice
arXiv:2511.08605v3 Announce Type: replace Abstract: Bangladesh's low-income population faces major barriers to affordable legal advice due to complex legal language, procedural opacity, and high costs. Existing AI legal assistants lack Bengali-language support and jurisdiction-specific adaptation, l
FLeX: Fourier-based Low-rank EXpansion for multilingual transfer
arXiv:2604.06253v1 Announce Type: cross Abstract: Cross-lingual code generation is critical in enterprise environments where multiple programming languages coexist. However, fine-tuning large language models (LLMs) individually for each language is computationally prohibitive. This paper investigate
Multilingual Cognitive Impairment Detection in the Era of Foundation Models
arXiv:2604.06758v1 Announce Type: new Abstract: We evaluate cognitive impairment (CI) classification from transcripts of speech in English, Slovene, and Korean. We compare zero-shot large language models (LLMs) used as direct classifiers under three input settings -- transcript-only, linguistic-feat
Multilingual Embedding Probes Fail to Generalize Across Learner Corpora
arXiv:2604.07095v1 Announce Type: new Abstract: Do multilingual embedding models encode a language-general representation of proficiency? We investigate this by training linear and non-linear probes on hidden-state activations from Qwen3-Embedding (0.6B, 4B, 8B) to predict CEFR proficiency levels fr
Enhancing Multilingual RAG Systems with Debiased Language Preference-Guided Query Fusion
arXiv:2601.02956v2 Announce Type: replace Abstract: Multilingual Retrieval-Augmented Generation (mRAG) systems often exhibit a perceived preference for high-resource languages, particularly English, resulting in the widespread adoption of English pivoting. While prior studies attribute this advantag