专为半导体显示行业打造的高效推理大模型，性能超越超大规模模型。
X-Intelligence 3.0: Training and Evaluating Reasoning LLM for Semiconductor Display
- 基于行业知识库进行微调与强化学习，提升专业推理能力。
- 320亿参数模型在多个评测中优于6710亿参数的DeepSeek-R1。
- 支持自动化评估与领域检索增强生成，适合产业工程师使用。
大型语言模型在推理任务上取得显著进展，但在半导体显示行业的应用仍受限于缺乏领域专业知识。为此，我们提出X-Intelligence 3.0，首个专为半导体显示行业设计的高性能推理模型。该模型基于精心构建的行业知识库，通过监督微调和强化学习提升理解与推理能力。为加速开发，我们构建了模拟专家评估的自动化评估框架，并集成领域专用的检索增强生成（RAG）机制，在基准数据集上实现显著性能提升。尽管模型规模仅为320亿参数，其在多项评测中仍优于6710亿参数的SOTA模型DeepSeek-R1。这证明了其卓越的效率，为半导体显示领域的长期推理难题提供了强大解决方案。
原文摘要 · Abstract (English)
Large language models (LLMs) have recently achieved significant advances in reasoning and demonstrated their advantages in solving challenging problems. Yet, their effectiveness in the semiconductor display industry remains limited due to a lack of domain-specific training and expertise. To bridge this gap, we present X-Intelligence 3.0, the first high-performance reasoning model specifically developed for the semiconductor display industry. This model is designed to deliver expert-level understanding and reasoning for the industry's complex challenges. Leveraging a carefully curated industry knowledge base, the model undergoes supervised fine-tuning and reinforcement learning to enhance its reasoning and comprehension capabilities. To further accelerate development, we implemented an automated evaluation framework that simulates expert-level assessments. We also integrated a domain-specific retrieval-augmented generation (RAG) mechanism, resulting in notable performance gains on benchmark datasets. Despite its relatively compact size of 32 billion parameters, X-Intelligence 3.0 outperforms SOTA DeepSeek-R1-671B across multiple evaluations. This demonstrates its exceptional efficiency and establishes it as a powerful solution to the longstanding reasoning challenges faced by the semiconductor display industry.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。