Large Language Models for Coagulant Dosage Prediction: A Systematic Investigation of Generalization, Rationale Patterns and Hallucination
Water · 09.05.2026 · 18 (10) · 1132
DOI: 10.3390/w18101132 ↗Kurz gefasst
Fachartikel in der Zeitschrift Water, online erschienen am 09.05.2026. Verfasst von Xiujuan Li und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China.
Abstract (Originalsprache)
Precise coagulant dosage control is essential for stable drinking-water treatment, yet conventional machine learning (ML) methods can be sensitive to data conditions. This study evaluates a large language model (LLM)-based in-context workflow for this tabular prediction task using the DeepSeek family, benchmarked against XGBoost, ANN, SVM, and k-NN under a shared chronological protocol. We examined performance across feature configurations, training-pool conditions, and outlier subsets. On the HQ-WTP case dataset, full-feature input outperformed temperature-only input, indicating the value of multivariate information. Performance responses to training-pool condition were model-dependent, with no universal optimum. Under the fixed protocol, in the full-feature test setting, the strongest tabular baseline showed the strongest test performance, while DeepSeek-Reasoner and DeepSeek-Chat showed intermediate performance, and DeepSeek-R1-Distill-Qwen-32B showed relatively lower stability. DeepSeek-Reasoner reached its best test performance at the 1/2 condition. We also coded narrative rationale patterns in generated responses and performed a protocol-based hallucination audit. DeepSeek-Reasoner showed comparatively lower hallucination incidence and more stable error behavior in this benchmark. These analyses are interpreted as response-level reliability evidence rather than verification of internal computational mechanisms. Overall, the study provides transparent, case-specific benchmark evidence for LLM-assisted decision support, while broader deployment claims require strict hallucination control, human-in-the-loop safeguards, and independent multi-site validation.
Förderung
- National Key Research and Development Program of China
Zitieren
APA
Li, X., Zhou, Y., Wang, C., & Liu, J. (2026). Large Language Models for Coagulant Dosage Prediction: A Systematic Investigation of Generalization, Rationale Patterns and Hallucination. Water, 18(10), 1132. https://doi.org/10.3390/w18101132
Vancouver
Li X, Zhou Y, Wang C, Liu J. Large Language Models for Coagulant Dosage Prediction: A Systematic Investigation of Generalization, Rationale Patterns and Hallucination. Water. 2026;18(10):1132. doi:10.3390/w18101132
BibTeX
@article{Li2026,
author = {Li, Xiujuan and Zhou, Yisu and Wang, Chunhui and Liu, Jingqing},
title = {Large Language Models for Coagulant Dosage Prediction: A Systematic Investigation of Generalization, Rationale Patterns and Hallucination},
journal = {Water},
year = {2026},
volume = {18},
number = {10},
pages = {1132},
doi = {10.3390/w18101132}
}
EUVIMED