基于科学知识的解码约束：提升大语言模型的可靠性
Scientific Knowledge-driven Decoding Constraints Improving the Reliability of LLMs
- Nanjing University（南京大学）
- Tsinghua University（清华大学）
- Northeastern University（东北大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出SciDC方法，通过整合领域知识与强约束提升LLM在科学任务中的可靠性，实验显示在工业配方设计、肿瘤诊断和逆合成规划中平均准确率提升12%。
AI中文摘要：
大语言模型（LLMs）展现出强大的知识储备和任务解决能力，但仍然面临严重的幻觉问题，阻碍了其实际应用。尽管科学理论和规则能有效指导人类操作者的行为，但LLMs尚未充分通过训练或提示利用这些高度浓缩的知识。为解决这一问题，我们提出SciDC，一种整合领域知识与强约束的LLM生成方法。通过采用强大的LLM自动将灵活的知识转换为多层标准化规则，我们构建了一个可扩展的框架，有效约束模型在领域任务上的生成。在科学任务上，包括工业配方设计、临床肿瘤诊断和逆合成规划的实验，一致证明了该方法的有效性，平均准确率比基线生成提高了12%。我们进一步讨论了LLMs自动归纳总结高度浓缩知识的潜力，展望了加速整体科学研究进程的实用解决方案。本文代码可通过（https://github.com/Maotian-Ma/SciDC）获取。
英文摘要：
Large language models (LLMs) have shown strong knowledge reserves and task-solving capabilities, but still face the challenge of severe hallucination, hindering their practical application. Though scientific theories and rules can efficiently direct the behaviors of human manipulators, LLMs still do not utilize these highly-condensed knowledge sufficiently through training or prompting. To address this issue, we propose \textbf{SciDC}, an LLM generation method that integrate subject-specific knowledge with strong constraints. By adopting strong LLMs to automatically convert flexible knowledge into multi-layered, standardized rules, we build an extensible framework to effectively constrain the model generation on domain tasks. Experiments on scientific tasks including industrial formulation design, clinical tumor diagnosis and retrosynthesis planning, consistently demonstrate the effectiveness of our method, achieving a 12\% accuracy improvement on average compared with vanilla generation. We further discuss the potential of LLMs in automatically inductively summarizing highly-condensed knowledge, looking ahead to practical solutions for accelerating the overall scientific research process. All the code of this paper can be obtained (https://github.com/Maotian-Ma/SciDC).
