A Lightweight Multi-Expert Generative Language Model System for Engineering Information and Knowledge Extraction

• URL: http://arxiv.org/abs/2505.21109v1
• Date: Tue, 27 May 2025 12:31:24 GMT
• Title: A Lightweight Multi-Expert Generative Language Model System for Engineering Information and Knowledge Extraction
• Authors: Bogdan Bogachov, Yaoyao Fiona Zhao,
• Abstract summary: Small Language Graph (SLG) is a lightweight adaptation solution designed to address the two key challenges outlined above.<n>SLG was able to surpass conventional fine-tuning methods on the Exact Match metric by 3 times.<n>Also, the graph architecture and the small size of expert nodes offer a possible opportunity for distributed AI systems.
• Score: 2.8007688938043622
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite recent advancements in domain adaptation techniques for large language models, these methods remain computationally intensive, and the resulting models can still exhibit hallucination issues. Most existing adaptation methods do not prioritize reducing the computational resources required for fine-tuning and inference of language models. Hallucination issues have gradually decreased with each new model release. However, they remain prevalent in engineering contexts, where generating well-structured text with minimal errors and inconsistencies is critical. This work introduces a novel approach called the Small Language Graph (SLG), which is a lightweight adaptation solution designed to address the two key challenges outlined above. The system is structured in the form of a graph, where each node represents a lightweight expert - a small language model fine-tuned on specific and concise texts. The results of this study have shown that SLG was able to surpass conventional fine-tuning methods on the Exact Match metric by 3 times. Additionally, the fine-tuning process was 1.7 times faster compared to that of a larger stand-alone language model. These findings introduce a potential for small to medium-sized engineering companies to confidently use generative AI technologies, such as LLMs, without the necessity to invest in expensive computational resources. Also, the graph architecture and the small size of expert nodes offer a possible opportunity for distributed AI systems, thus potentially diverting the global need for expensive centralized compute clusters.

Related papers

• Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo [90.78001821963008]
  A wide range of LM applications require generating text that conforms to syntactic or semantic constraints.<n>We develop an architecture for controlled LM generation based on sequential Monte Carlo (SMC)<n>Our system builds on the framework of Lew et al. (2023) and integrates with its language model probabilistic programming language.
  arXiv  Detail & Related papers  (2025-04-17T17:49:40Z)
• RigoChat 2: an adapted language model to Spanish using a bounded dataset and reduced hardware [0.33707099470112734]
  Large Language Models (LLMs) have become a key element of modern artificial intelligence.<n>We present our use case, RigoChat 2, illustrating how LLMs can be adapted to achieve superior results in Spanish-language tasks.
  arXiv  Detail & Related papers  (2025-03-11T08:53:53Z)
• Enhancing Code Generation for Low-Resource Languages: No Silver Bullet [55.39571645315926]
  Large Language Models (LLMs) rely on large and diverse datasets to learn syntax, semantics, and usage patterns of programming languages.<n>For low-resource languages, the limited availability of such data hampers the models' ability to generalize effectively.<n>We present an empirical study investigating the effectiveness of several approaches for boosting LLMs' performance on low-resource languages.
  arXiv  Detail & Related papers  (2025-01-31T12:23:28Z)
• Building an Efficient Multilingual Non-Profit IR System for the Islamic Domain Leveraging Multiprocessing Design in Rust [0.0]
  This work focuses on the development of a multilingual non-profit IR system for the Islamic domain. By employing methods like continued pre-training for domain adaptation and language reduction to decrease model size, a lightweight multilingual retrieval model was prepared.
  arXiv  Detail & Related papers  (2024-11-09T11:37:18Z)
• In-Context Language Learning: Architectures and Algorithms [73.93205821154605]
  We study ICL through the lens of a new family of model problems we term in context language learning (ICLL) We evaluate a diverse set of neural sequence models on regular ICLL tasks.
  arXiv  Detail & Related papers  (2024-01-23T18:59:21Z)
• A Survey of Large Language Models [81.06947636926638]
  Language modeling has been widely studied for language understanding and generation in the past two decades. Recently, pre-trained language models (PLMs) have been proposed by pre-training Transformer models over large-scale corpora. To discriminate the difference in parameter scale, the research community has coined the term large language models (LLM) for the PLMs of significant size.
  arXiv  Detail & Related papers  (2023-03-31T17:28:46Z)
• A Cohesive Distillation Architecture for Neural Language Models [0.0]
  A recent trend in Natural Language Processing is the exponential growth in Language Model (LM) size. This study investigates methods for Knowledge Distillation (KD) to provide efficient alternatives to large-scale models.
  arXiv  Detail & Related papers  (2023-01-12T08:01:53Z)
• I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation [89.38161262164586]
  We study generative models of commonsense knowledge, focusing on the task of generating generics. We introduce I2D2, a novel commonsense distillation framework that loosely follows the Symbolic Knowledge Distillation of West et al. Our study leads to a new corpus of generics, Gen-A-tomic, that is the largest and highest quality available to date.
  arXiv  Detail & Related papers  (2022-12-19T04:47:49Z)
• Deep learning applied to computational mechanics: A comprehensive review, state of the art, and the classics [77.34726150561087]
  Recent developments in artificial neural networks, particularly deep learning (DL), are reviewed in detail. Both hybrid and pure machine learning (ML) methods are discussed. History and limitations of AI are recounted and discussed, with particular attention at pointing out misstatements or misconceptions of the classics.
  arXiv  Detail & Related papers  (2022-12-18T02:03:00Z)

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.