Language Native Lightly Structured Databases for Large Language Model Driven Composite Materials Research

• URL: http://arxiv.org/abs/2509.06093v1
• Date: Sun, 07 Sep 2025 15:15:55 GMT
• Title: Language Native Lightly Structured Databases for Large Language Model Driven Composite Materials Research
• Authors: Yuze Liu, Zhaoyuan Zhang, Xiangsheng Zeng, Yihe Zhang, Leping Yu, Lejia Wang, Xi Yu,
• Abstract summary: We present a language-native database for boron nitride nanosheet (BNNS) polymer thermally conductive composites.<n>The system can synthesize literature into accurate, verifiable, and expert style guidance.
• Score: 6.31777560888658
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Chemical and materials research has traditionally relied heavily on knowledge narrative, with progress often driven by language-based descriptions of principles, mechanisms, and experimental experiences, rather than tables, limiting what conventional databases and ML can exploit. We present a language-native database for boron nitride nanosheet (BNNS) polymer thermally conductive composites that captures lightly structured information from papers across preparation, characterization, theory-computation, and mechanistic reasoning, with evidence-linked snippets. Records are organized in a heterogeneous database and queried via composite retrieval with semantics, key words and value filters. The system can synthesizes literature into accurate, verifiable, and expert style guidance. This substrate enables high fidelity efficient Retrieval Augmented Generation (RAG) and tool augmented agents to interleave retrieval with reasoning and deliver actionable SOP. The framework supplies the language rich foundation required for LLM-driven materials discovery.

Related papers

• LeMat-Synth: a multi-modal toolbox to curate broad synthesis procedure databases from scientific literature [60.879220305044726]
  We propose a multi-modal toolbox that employs large language models (LLMs) and vision language models (VLMs) to automatically extract and organize synthesis procedures and performance data.<n>We curated 81k open-access papers, yielding LeMat- Synth (v 1.0): a dataset containing synthesis procedures spanning 35 synthesis methods and 16 material classes.<n>We release a modular, open-source library designed to support community-driven extension to new corpora and synthesis domains.
  arXiv  Detail & Related papers  (2025-10-28T17:58:18Z)
• Struc-EMB: The Potential of Structure-Aware Encoding in Language Embeddings [16.728984584960738]
  This paper introduces and systematically evaluates a new paradigm for generating structure-aware text embeddings.<n>We investigate two primary in-process methods: sequential concatenation and parallel caching.<n>Our analysis reveals critical trade-offs: sequential concatenation excels with noisy, moderate-length contexts, while parallel caching scales more effectively to long, high-signal contexts but is more susceptible to distractors.
  arXiv  Detail & Related papers  (2025-10-09T19:45:54Z)
• Who Gets Cited Most? Benchmarking Long-Context Language Models on Scientific Articles [81.89404347890662]
  SciTrek is a novel question-answering benchmark designed to evaluate the long-context reasoning capabilities of large language models (LLMs) using scientific articles.<n>Our analysis reveals systematic shortcomings in models' abilities to perform basic numerical operations and accurately locate specific information in long contexts.
  arXiv  Detail & Related papers  (2025-09-25T11:36:09Z)
• Exploring Reasoning-Infused Text Embedding with Large Language Models for Zero-Shot Dense Retrieval [24.53573526375476]
  Reasoning-Infused Text Embedding builds upon existing language model embedding techniques by generating intermediate reasoning texts before computing embeddings.<n>Results on BRIGHT, a reasoning-intensive retrieval benchmark, demonstrate that RITE significantly enhances zero-shot retrieval performance across diverse domains.
  arXiv  Detail & Related papers  (2025-08-29T23:22:34Z)
• How Do LLM-Generated Texts Impact Term-Based Retrieval Models? [76.92519309816008]
  This paper investigates the influence of large language models (LLMs) on term-based retrieval models.<n>Our linguistic analysis reveals that LLM-generated texts exhibit smoother high-frequency and steeper low-frequency Zipf slopes.<n>Our study further explores whether term-based retrieval models demonstrate source bias, concluding that these models prioritize documents whose term distributions closely correspond to those of the queries.
  arXiv  Detail & Related papers  (2025-08-25T06:43:27Z)
• Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction [80.88654868264645]
  Arranged and Organized Extraction Benchmark designed to evaluate ability of large language models to comprehend fragmented documents.<n>AOE includes 11 carefully crafted tasks across three diverse domains, requiring models to generate context-specific schema tailored to varied input queries.<n>Results show that even the most advanced models struggled significantly.
  arXiv  Detail & Related papers  (2025-07-22T06:37:51Z)
• Large Language Models are Good Relational Learners [55.40941576497973]
  We introduce Rel-LLM, a novel architecture that utilizes a graph neural network (GNN)- based encoder to generate structured relational prompts for large language models (LLMs)<n>Unlike traditional text-based serialization approaches, our method preserves the inherent relational structure of databases while enabling LLMs to process and reason over complex entity relationships.
  arXiv  Detail & Related papers  (2025-06-06T04:07:55Z)
• Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries [8.779871128906787]
  Multi-modal datasets often miss the detailed descriptions that properly capture the rich information encoded in each item.<n>This makes answering complex natural language queries a major challenge in this domain.<n>We introduce a Generative-based Monte Carlo method that utilizes foundation models to generate synthetic samples.<n>Our system is open-source and ready for deployment, designed to be easily adopted by researchers and developers.
  arXiv  Detail & Related papers  (2024-12-01T01:36:41Z)
• From Text to Insight: Large Language Models for Materials Science Data Extraction [4.08853418443192]
  The vast majority of materials science knowledge exists in unstructured natural language.<n>Structured data is crucial for innovative and systematic materials design.<n>The advent of large language models (LLMs) represents a significant shift.
  arXiv  Detail & Related papers  (2024-07-23T22:23:47Z)
• STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases [93.96463520716759]
  We develop STARK, a large-scale Semi-structure retrieval benchmark on Textual and Knowledge Bases. Our benchmark covers three domains: product search, academic paper search, and queries in precision medicine. We design a novel pipeline to synthesize realistic user queries that integrate diverse relational information and complex textual properties.
  arXiv  Detail & Related papers  (2024-04-19T22:54:54Z)
• DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text [73.68051228972024]
  Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
  arXiv  Detail & Related papers  (2023-10-31T04:37:57Z)
• Synergistic Interplay between Search and Large Language Models for Information Retrieval [141.18083677333848]
  InteR allows RMs to expand knowledge in queries using LLM-generated knowledge collections. InteR achieves overall superior zero-shot retrieval performance compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-12T11:58:15Z)
• Leveraging Language Representation for Material Recommendation, Ranking, and Exploration [0.0]
  We introduce a material discovery framework that uses natural language embeddings derived from language models as representations of compositional and structural features. By applying the framework to thermoelectrics, we demonstrate diversified recommendations of prototype structures and identify under-studied high-performance material spaces.
  arXiv  Detail & Related papers  (2023-05-01T21:58:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.