arXiv subjects

Saika Wong

Publications and source records attributed to Saika Wong.

3 recordsLinked to original sources

arXiv2025

Automating construction contract review using knowledge graph-enhanced large language models

An effective and efficient review of construction contracts is essential for minimizing construction projects losses, but current methods are time-consuming and error-prone. Studies using methods based on Natural Language Processing (NLP) exist, but their scope is often limited to text classification or segmented label prediction. This paper investigates whether integrating Large Language Models (LLMs) and Knowledge Graphs (KGs) can enhance the accuracy and interpretability of automated contract risk identification. A tuning-free approach is proposed that integrates LLMs with a Nested Contract Knowledge Graph (NCKG) using a Graph Retrieval-Augmented Generation (GraphRAG) framework for contract knowledge retrieval and reasoning. Tested on international EPC contracts, the method achieves more accurate risk evaluation and interpretable risk summaries than baseline models. These findings demonstrate the potential of combining LLMs and KGs for reliable reasoning in tasks that are knowledge-intensive and specialized, such as contract review.

cs.AI↗

arXiv2025

Exploring psychophysiological methods for human-robot collaboration in construction

Psychophysiological methods present a promising approach to fostering enhanced mutual communication and collaboration between human workers and robots. Despite their potential, there is still limited understanding of how to effectively integrate psychophysiological methods to improve human-robot collaboration (HRC) in construction. This paper addresses this gap by critically reviewing the use of psychophysiological methods for HRC within construction environments, employing a concept-methodology-value philosophical framework. The analysis reveals that measuring brain activity using electroencephalography is the most widely used method, while most of the works are still at the proof of concept stage and lack empirical evidence. Three potential research directions were proposed: the integration of multi-modal psychophysiological signals, enriching the existing experimental settings for better generalizability, and leveraging advanced biocompatible or contactless technologies for effective signal detection. The findings should benefit subsequent exploration and practical applications of psychophysiological methods to enable better implementation of robots and support HRC in construction.

cs.RO↗

arXiv2023

Construction contract risk identification based on knowledge-augmented language model

Contract review is an essential step in construction projects to prevent potential losses. However, the current methods for reviewing construction contracts lack effectiveness and reliability, leading to time-consuming and error-prone processes. While large language models (LLMs) have shown promise in revolutionizing natural language processing (NLP) tasks, they struggle with domain-specific knowledge and addressing specialized issues. This paper presents a novel approach that leverages LLMs with construction contract knowledge to emulate the process of contract review by human experts. Our tuning-free approach incorporates construction contract domain knowledge to enhance language models for identifying construction contract risks. The use of a natural language when building the domain knowledge base facilitates practical implementation. We evaluated our method on real construction contracts and achieved solid performance. Additionally, we investigated how large language models employ logical thinking during the task and provide insights and recommendations for future research.

cs.AI↗