Reconstruction of Criminal Event Timelines from Property Crime Investigation Documents Based on a Hybrid LLM-Rule Pipeline
Applied Sciences · 25.10.2026 · 16 (21) · 10566
DOI: 10.3390/app162110566 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 25.10.2026. Verfasst von Gwang-Jae Won und 3 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and ICT.
Abstract (Originalsprache)
Fact-finding in criminal proceedings reconstructs past events into a coherent narrative based on fragmented evidence and testimony, yet remains vulnerable to cognitive confirmation bias. While automating timeline construction using large language models (LLMs) offers decision support, confidentiality-critical local models are prone to temporal hallucinations, inverting causal orders or generating groundless timestamps. To mitigate these vulnerabilities, this study proposes Deep-ARC (Analysis, Reconstruction, and Contradiction detection for criminal timeline construction), a hybrid LLM-rule pipeline that algorithmically regulates model reasoning through legal domain schemas and deterministic rule logic. Deep-ARC injects statutory crime element schemas to categorize event phases and enforces phase-aware boundary clamping grounded on explicit timestamps, systematically resolving sequential contradictions during missing time inference. In proof-of-concept experiments focusing on corporate property crimes (breach of trust and embezzlement) with Gemma-4-31B, Deep-ARC achieved a Micro PMR (exact sequence match ratio) of 0.343 and a Kendall’s Tau (τ) of 0.861, representing an approximate fourfold improvement over the unconstrained baseline and demonstrating higher sequencing consistency than large-scale commercial LLMs. These results indicate that coupling domain-specific structural constraints with deterministic algorithms offers an effective and robust strategy for providing an objective chronological sequence to assist fact-finding without relying exclusively on parameter scaling.
Förderung
- Ministry of Science and ICT
Zitieren
APA
Won, G., Park, R., Tschoy, J., & Lee, Y. (2026). Reconstruction of Criminal Event Timelines from Property Crime Investigation Documents Based on a Hybrid LLM-Rule Pipeline. Applied Sciences, 16(21), 10566. https://doi.org/10.3390/app162110566
Vancouver
Won G, Park R, Tschoy J, Lee Y. Reconstruction of Criminal Event Timelines from Property Crime Investigation Documents Based on a Hybrid LLM-Rule Pipeline. Applied Sciences. 2026;16(21):10566. doi:10.3390/app162110566
BibTeX
@article{Won2026,
author = {Won, Gwang-Jae and Park, Ro-Seop and Tschoy, June and Lee, Yong-Tae},
title = {Reconstruction of Criminal Event Timelines from Property Crime Investigation Documents Based on a Hybrid LLM-Rule Pipeline},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {21},
pages = {10566},
doi = {10.3390/app162110566}
}
EUVIMED