arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.17244cs.CLcond-mat.mtrl-scics.AI
收藏

LLaMP:为高保真材料知识检索与蒸馏而增强的大型语言模型

LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillation

University of California, Berkeley(加州大学伯克利分校);Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室);Foothill College(福希尔学院);Cavendish Laboratory, University of Cambridge(剑桥大学卡文迪许实验室)

Yuan Chiang, Elvis Hsieh, Chia-Hong Chou, Janosh Riebesell

AI总结:

本文提出LLaMP,一个多模态RAG框架,通过分层ReAct智能体动态交互材料数据并运行原子模拟,无需微调即可降低LLM幻觉,有效缓解体模量等材料属性的内在偏见,为材料信息学探索与知识蒸馏提供无幻觉途径。

摘要:

降低大型语言模型(LLMs)的幻觉对于在科学领域的应用至关重要,因为可靠性和可重复性是关键。然而,LLMs本质上缺乏长期记忆,这使得在特定领域文献和数据上对它们进行微调成为一项非平凡、临时且不可避免带有偏见的任务。在此我们介绍了LLaMP,这是一个多模态检索增强生成(RAG)框架,包含分层推理与行动(ReAct)智能体,能够动态且递归地与Materials Project(MP)上的计算和实验数据进行交互,并通过高通量工作流接口运行原子模拟。无需微调,LLaMP展现出强大的工具使用能力,能够理解和整合各种模态的材料科学概念,实时获取相关数据存储,处理高阶数据(如晶体结构和弹性张量),并简化计算材料和化学中的复杂任务。我们提出了一种结合不确定性和置信度估计的简单指标,以评估LLaMP和原始LLMs响应的自洽性。我们的基准测试表明,LLaMP有效缓解了LLMs中的内在偏见,抵消了体模量、电子带隙和形成能方面的误差,这些误差似乎源于混合数据源。我们还展示了LLaMP使用预训练的机器学习力场编辑晶体结构和运行退火分子动力学模拟的能力。该框架提供了一种直观且几乎无幻觉的方法来探索和扩展材料信息学,并为知识蒸馏和微调其他语言模型建立了一条途径。代码和实时演示可在https://github.com/chiang-yuan/llamp获取。

英文摘要:

Reducing hallucination of Large Language Models (LLMs) is imperative for use in the sciences, where reliability and reproducibility are crucial. However, LLMs inherently lack long-term memory, making it a nontrivial, ad hoc, and inevitably biased task to fine-tune them on domain-specific literature and data. Here we introduce LLaMP, a multimodal retrieval-augmented generation (RAG) framework of hierarchical reasoning-and-acting (ReAct) agents that can dynamically and recursively interact with computational and experimental data on Materials Project (MP) and run atomistic simulations via high-throughput workflow interface. Without fine-tuning, LLaMP demonstrates strong tool usage ability to comprehend and integrate various modalities of materials science concepts, fetch relevant data stores on the fly, process higher-order data (such as crystal structure and elastic tensor), and streamline complex tasks in computational materials and chemistry. We propose a simple metric combining uncertainty and confidence estimates to evaluate the self-consistency of responses by LLaMP and vanilla LLMs. Our benchmark shows that LLaMP effectively mitigates the intrinsic bias in LLMs, counteracting the errors on bulk moduli, electronic bandgaps, and formation energies that seem to derive from mixed data sources. We also demonstrate LLaMP's capability to edit crystal structures and run annealing molecular dynamics simulations using pre-trained machine-learning force fields. The framework offers an intuitive and nearly hallucination-free approach to exploring and scaling materials informatics, and establishes a pathway for knowledge distillation and fine-tuning other language models. Code and live demo are available at https://github.com/chiang-yuan/llamp

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑