Arce: Augmented Roberta with Contextualized Elucidations for Ner in Automated Rule Checking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Jian, Dou, Jiabao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910002726305792
author Chen, Jian
Dou, Jiabao
author_facet Chen, Jian
Dou, Jiabao
contents Accurate information extraction from specialized texts is a critical challenge for automated rule checking (ARC) in the architecture, engineering, and construction (AEC) domain. While large language models (LLMs) possess strong reasoning capabilities, their deployment in resource-constrained AEC environments is often impractical. Conversely, standard efficient models struggle with the significant domain gap. Although this gap can be mitigated by pre-training on large, humancurated corpora, such approaches are labor-intensive and costly. To address this, we propose ARCE (Augmented RoBERTa with Contextualized Elucidations), a novel knowledge distillation framework that leverages LLMs to synthesize a task-oriented corpus, termed Cote, for incrementally pre-training smaller models. ARCE systematically explores the optimal strategy for knowledge transfer. Our extensive experiments demonstrate that ARCE establishes a new state-of-the-art on a benchmark AEC dataset, achieving a Macro-F1 score of 77.20% and outperforming both domain-specific baselines and fine-tuned LLMs. Crucially, our study reveals a less is more principle: simple, direct explanations prove significantly more effective for domain adaptation than complex, role-based rationales in the NER task, which tend to introduce semantic noise. The source code will be made publicly available upon acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2508_07286
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Arce: Augmented Roberta with Contextualized Elucidations for Ner in Automated Rule Checking
Chen, Jian
Dou, Jiabao
Computation and Language
Information Retrieval
Accurate information extraction from specialized texts is a critical challenge for automated rule checking (ARC) in the architecture, engineering, and construction (AEC) domain. While large language models (LLMs) possess strong reasoning capabilities, their deployment in resource-constrained AEC environments is often impractical. Conversely, standard efficient models struggle with the significant domain gap. Although this gap can be mitigated by pre-training on large, humancurated corpora, such approaches are labor-intensive and costly. To address this, we propose ARCE (Augmented RoBERTa with Contextualized Elucidations), a novel knowledge distillation framework that leverages LLMs to synthesize a task-oriented corpus, termed Cote, for incrementally pre-training smaller models. ARCE systematically explores the optimal strategy for knowledge transfer. Our extensive experiments demonstrate that ARCE establishes a new state-of-the-art on a benchmark AEC dataset, achieving a Macro-F1 score of 77.20% and outperforming both domain-specific baselines and fine-tuned LLMs. Crucially, our study reveals a less is more principle: simple, direct explanations prove significantly more effective for domain adaptation than complex, role-based rationales in the NER task, which tend to introduce semantic noise. The source code will be made publicly available upon acceptance.
title Arce: Augmented Roberta with Contextualized Elucidations for Ner in Automated Rule Checking
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2508.07286