Chronological Knowledge Retrieval: A Retrieval-Augmented Generation Approach to Construction Project Documentation

arXiv cs.CL / 4/17/2026

📰 NewsDeveloper Stack & InfrastructureTools & Practical UsageModels & Research

共有:

Key Points

The paper presents a Retrieval-Augmented Generation (RAG) system that enables conversational querying of complete construction meeting-minute archives to reconstruct decision histories.
It is designed to answer natural-language questions with semantic relevance and explicit time annotations, helping users track the chronology of evolving decisions.
The approach combines semantic retrieval with large language models to produce context-aware responses, addressing the limitations of manually searching raw documents.
The authors evaluate the system using an anonymized, industry-sourced dataset from a completed Belgium construction project, enhanced with expert-defined queries for systematic testing.
The dataset and an open-source implementation are released to support further research into time-annotated, conversational project documentation access.

Abstract

In large-scale construction projects, the continuous evolution of decisions generates extensive records, most often captured in meeting minutes. Since decisions may override previous ones, professionals often need to reconstruct the history of specific choices. Retrieving such information manually from raw archives is both labor-intensive and error-prone. From a user perspective, we address this challenge by enabling conversational access to the whole set of project meeting minutes. Professionals can pose natural-language questions and receive answers that are both semantically relevant and explicitly time-annotated, allowing them to follow the chronology of decisions. From a technical perspective, our solution employs a Retrieval-Augmented Generation (RAG) framework that integrates semantic search with large language models to ensure accurate and context-aware responses. We demonstrate the approach using an anonymized, industry-sourced dataset of meeting minutes from a completed construction project by a large company in Belgium. The dataset is annotated and enriched with expert-defined queries to support systematic evaluation. Both the dataset and the open-source implementation are made available to the community to foster further research on conversational access to time-annotated project documentation.