paper-with-me

홈 › Papers

SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages

2024-07-29 · Wenxuan Zhang, Hou Pong Chan, Yiran Zhao, Mahani Aljunied, Jianyu Wang, Chaoqun Liu, Yue Deng, Zhiqiang Hu, Weiwen Xu, Yew Ken Chia, Xin Li, Lidong Bing

Large Language Models (LLMs) have shown remarkable abilities across various tasks, yet their development has predominantly centered on high-resource languages like English and Chinese, leaving low-resource languages underserved. To address this disparity, we present SeaLLMs 3, the latest iteration of the SeaLLMs model family, tailored for Southeast Asian languages. This region, characterized by its rich linguistic diversity, has lacked adequate language technology support. SeaLLMs 3 aims to bridge this gap by covering a comprehensive range of languages spoken in this region, including English, Chinese, Indonesian, Vietnamese, Thai, Tagalog, Malay, Burmese, Khmer, Lao, Tamil, and Javanese. Leveraging efficient language enhancement techniques and a specially constructed instruction tuning dataset, SeaLLMs 3 significantly reduces training costs while maintaining high performance and versatility. Our model excels in tasks such as world knowledge, mathematical reasoning, translation, and instruction following, achieving state-of-the-art performance among similarly sized models. Additionally, we prioritized safety and reliability by addressing both general and culture-specific considerations and incorporated mechanisms to reduce hallucinations. This work underscores the importance of inclusive AI, showing that advanced LLM capabilities can benefit underserved linguistic and cultural communities.

📄 PDF Abstract BibTeX arXiv:2407.19672

Code (2)

DAMO-NLP-SG/SeaExam 공식 구현
damo-nlp-sg/seallms

Tasks

DiversityInstruction FollowingMathematical ReasoningWorld Knowledge

Similar Papers 제목 키워드 기반

SeaLLMs -- Large Language Models for Southeast Asia

2023-12-01 · Xuan-Phi Nguyen, Wenxuan Zhang, Xin Li, Mahani Aljunied 외

Despite the remarkable achievements of large language models (LLMs) in various tasks, there remains a linguistic bias that favors high-resource languages, such as English, often at the expense of low-resource and regiona…

Instruction Following

SeaLLMs-Audio: Large Audio-Language Models for Southeast Asia

2025-11-03 · Chaoqun Liu, Mahani Aljunied, Guizhen Chen, Hou Pong Chan 외 arxiv

We introduce SeaLLMs-Audio, the first large audio-language model (LALM) tailored for multiple Southeast Asian (SEA) languages-Indonesian (id), Thai (th), and Vietnamese (vi)-alongside English (en) and Chinese (zh). Train…

Speech-to-Text TranslationSpeech Emotion RecognitionQuestion AnsweringSpeech Recognition

Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models

2023-08-30 · Neha Sengupta, Sunil Kumar Sahu, Bokang Jia, Satheesh Katipomu 외

We introduce Jais and Jais-chat, new state-of-the-art Arabic-centric foundation and instruction-tuned open generative large language models (LLMs). The models are based on the GPT-3 decoder-only architecture and are pret…

DecoderSafety Alignment

A Comparative Study of Language Models for Khmer Retrieval-Augmented Question Answering

2026-05-21 · Sereiwathna Ros, Phannet Pov, Ratanaktepi Chhor, Kimleang Ly 외 arxiv

Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for grounding large language model (LLM) outputs in retrieved evidence, thereby reducing hallucination and improving factual accuracy. Its efficacy…

Semantic SimilarityQuestion Answering

OpenLLM-Ro -- Technical Report on Open-source Romanian LLMs

2024-05-13 · Mihai Masala, Denis C. Ilie-Ablachim, Dragos Corlatescu, Miruna Zavelca 외

In recent years, Large Language Models (LLMs) have achieved almost human-like performance on various tasks. While some LLMs have been trained on multilingual data, most of the training data is in English. Hence, their pe…