Saved in:
Bibliographic Details
Main Authors: Reddy, Karan, Pal, Mayukha
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.02532
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909720945623040
author Reddy, Karan
Pal, Mayukha
author_facet Reddy, Karan
Pal, Mayukha
contents Standard transformer-based language models, while powerful for general text, often struggle with the fine-grained syntax and entity relationships in complex technical, engineering documents. To address this, we propose the Contextual Graph Transformer (CGT), a hybrid neural architecture that combines Graph Neural Networks (GNNs) and Transformers for domain-specific question answering. CGT constructs a dynamic graph over input tokens using sequential, skip-gram, and semantic similarity edges, which is processed by GATv2Conv layers for local structure learning. These enriched embeddings are then passed to a Transformer encoder to capture global dependencies. Unlike generic large models, technical domains often require specialized language models with stronger contextualization and structure awareness. CGT offers a parameter-efficient solution for such use cases. Integrated into a Retrieval-Augmented Generation (RAG) pipeline, CGT outperforms baselines like GPT-2 and BERT, achieving 24.7% higher accuracy than GPT-2 with 62.4% fewer parameters. This gain stems from CGTs ability to jointly model structural token interactions and long-range semantic coherence. The model is trained from scratch using a two-phase approach: pretraining on general text followed by fine-tuning on domain-specific manuals. This highlights CGTs adaptability to technical language, enabling better grounding, entity tracking, and retrieval-augmented responses in real-world applications.
format Preprint
id arxiv_https___arxiv_org_abs_2508_02532
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Contextual Graph Transformer: A Small Language Model for Enhanced Engineering Document Information Extraction
Reddy, Karan
Pal, Mayukha
Computation and Language
Machine Learning
Standard transformer-based language models, while powerful for general text, often struggle with the fine-grained syntax and entity relationships in complex technical, engineering documents. To address this, we propose the Contextual Graph Transformer (CGT), a hybrid neural architecture that combines Graph Neural Networks (GNNs) and Transformers for domain-specific question answering. CGT constructs a dynamic graph over input tokens using sequential, skip-gram, and semantic similarity edges, which is processed by GATv2Conv layers for local structure learning. These enriched embeddings are then passed to a Transformer encoder to capture global dependencies. Unlike generic large models, technical domains often require specialized language models with stronger contextualization and structure awareness. CGT offers a parameter-efficient solution for such use cases. Integrated into a Retrieval-Augmented Generation (RAG) pipeline, CGT outperforms baselines like GPT-2 and BERT, achieving 24.7% higher accuracy than GPT-2 with 62.4% fewer parameters. This gain stems from CGTs ability to jointly model structural token interactions and long-range semantic coherence. The model is trained from scratch using a two-phase approach: pretraining on general text followed by fine-tuning on domain-specific manuals. This highlights CGTs adaptability to technical language, enabling better grounding, entity tracking, and retrieval-augmented responses in real-world applications.
title Contextual Graph Transformer: A Small Language Model for Enhanced Engineering Document Information Extraction
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2508.02532