MétaCan
Menu
Back to cohort
Record W4411473534 · doi:10.7771/3067-4883.1757

Using Large Language Models to Identify Project Risks for Sustainable Operations

2025· article· en· W4411473534 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueCIB Conferences · 2025
Typearticle
Languageen
FieldDecision Sciences
TopicConstruction Project Management and Performance
Canadian institutionsUniversity of Alberta
Fundersnot available
KeywordsRisk analysis (engineering)Computer scienceBusiness

Abstract

fetched live from OpenAlex

Risk identification in construction projects is crucial for sustainable operations. However, it is often hindered by omissions and participant subjectivity. This study explores the application of large language models (LLMs) in identifying risks and impacted activities within construction projects. The methodology includes developing a RiskGPT agent, fine-tuning it with prompt words, augmenting it with structural knowledge, and evaluating its application on real projects. Preliminary results from a case study demonstrate the potential benefits and challenges of using LLMs in this context. Despite the generalization tendency and occasional technical issues, LLMs show promise in augmenting human expertise and providing a robust foundation for risk management in construction projects. Future research should focus on improving training data quality, enhancing contextual understanding, and refining the integration of LLM outputs with human insights to maximize their practical applicability.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesScholarly communication
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.808
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0010.000
Scholarly communication0.0010.001
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.339
GPT teacher head0.515
Teacher spread0.176 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it