EXAONE Deep：提升推理能力的语言模型
计算与语言
2026-01-05 v3 人工智能
摘要
我们提出了 EXAONE Deep 系列模型，展示了在各种推理任务（包括数学和编码基准测试）中的卓越能力。我们的模型主要基于包含长时间推理过程的推理专用数据集进行训练。评估结果表明，我们的较小模型 EXAONE Deep 2.4B 和 7.8B 在同等规模的其他模型中表现出优异性能，而最大的模型 EXAONE Deep 32B 在性能上与领先的开源权重模型持相当竞争力。所有 EXAONE Deep 模型均对科研开放，可从 https://huggingface.co/LGAI-EXAONE 下载。
引用
@article{arxiv.2503.12524,
title = {EXAONE Deep: Reasoning Enhanced Language Models},
author = {Kyunghoon Bae and Eunbi Choi and Kibong Choi and Stanley Jungkyu Choi and Yemuk Choi and Seokhee Hong and Junwon Hwang and Hyojin Jeon and Kijeong Jeon and Gerrard Jeongwon Jo and Hyunjik Jo and Jiyeon Jung and Hyosang Kim and Joonkee Kim and Seonghwan Kim and Soyeon Kim and Sunkyoung Kim and Yireun Kim and Yongil Kim and Youchul Kim and Edward Hwayoung Lee and Haeju Lee and Honglak Lee and Jinsik Lee and Kyungmin Lee and Sangha Park and Yongmin Park and Sihoon Yang and Heuiyeen Yeen and Sihyuk Yi and Hyeongu Yun},
journal= {arXiv preprint arXiv:2503.12524},
year = {2026}
}