PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
May 14, 2026The Journal of the Acoustical Society of America0 citations

Retrieval-augmented compact language model for porous acoustic metamaterials

View Full Paper
JCJennifer L. CelesteMichigan Technological UniversityELEvan LucasMichigan Technological UniversityBSBhisham SharmaMichigan Technological University

Key Points

  • The aim is to create a compact language model tailored to porous acoustic metamaterials to improve domain-specific research.
  • Developed a compact, domain-specific language model.
  • Utilized continual pre-training with acoustics textbooks and research papers.
  • Implemented retrieval-augmented generation for dynamic access to recent literature.
  • Reduced model size and training complexity for local deployment.
  • Enhanced privacy and customization for specific subfields.
  • Supported research and innovation in foam-based acoustic absorbers and resonant structures.

Abstract

Since ChatGPT’s release in 2022, general-purpose large language models (LLMs) have been increasingly adopted as AI assistants, though their effectiveness in specialized scientific domains remains limited. While domain-specific LLMs, such as BloombergGPT for finance or Med-PaLM 2 for healthcare, address these limitations, their training costs and data requirements remain substantial. This project proposes developing a compact, domain-specific language model tailored to porous acoustic metamaterials. Our method involves continual pre-training using targeted acoustics textbooks and research papers, followed by supervised fine-tuning with domain-specific question-answer pairs. To ensure accuracy and relevance, the model will utilize retrieval-augmented generation (RAG), dynamically accessing an external knowledge base of recent literature and technical resources. By reducing model size and training complexity, we aim to enable local deployment, enhancing privacy and allowing researchers to customize the model for specific subfields, such as foam-based acoustic absorbers or resonant structure optimization. This work demonstrates a practical approach to creating lightweight, domain-focused language assistants that support research and innovation in acoustic metamaterials.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Celeste et al. (2025) studied this question.

synapsesocial.com/papers/6a05684ea550a87e60a20c52https://doi.org/10.1121/10.0040183
Ask AI
Helpful
Bookmark
Share
View Full Paper