A Consensus-Driven Multi-LLM Pipeline for Missing-Person Investigations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908875438948352 |
|---|---|
| author | Castillo, Joshua Mukkamala, Ravi |
| author_facet | Castillo, Joshua Mukkamala, Ravi |
| contents | The first 72 hours of a missing-person investigation are critical for successful recovery. Guardian is an end-to-end system designed to support missing-child investigation and early search planning. This paper presents the Guardian LLM Pipeline, a multi-model system in which LLMs are used for intelligent information extraction and processing related to missing-person search operations. The pipeline coordinates end-to-end execution across task-specialized LLM models and invokes a consensus LLM engine that compares multiple model outputs and resolves disagreements. The pipeline is further strengthened by QLoRA-based fine-tuning, using curated datasets. The presented design aligns with prior work on weak supervision and LLM-assisted annotation, emphasizing conservative, auditable use of LLMs as structured extractors and labelers rather than unconstrained end-to-end decision makers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_08954 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Consensus-Driven Multi-LLM Pipeline for Missing-Person Investigations Castillo, Joshua Mukkamala, Ravi Artificial Intelligence Computation and Language Distributed, Parallel, and Cluster Computing Information Retrieval Machine Learning The first 72 hours of a missing-person investigation are critical for successful recovery. Guardian is an end-to-end system designed to support missing-child investigation and early search planning. This paper presents the Guardian LLM Pipeline, a multi-model system in which LLMs are used for intelligent information extraction and processing related to missing-person search operations. The pipeline coordinates end-to-end execution across task-specialized LLM models and invokes a consensus LLM engine that compares multiple model outputs and resolves disagreements. The pipeline is further strengthened by QLoRA-based fine-tuning, using curated datasets. The presented design aligns with prior work on weak supervision and LLM-assisted annotation, emphasizing conservative, auditable use of LLMs as structured extractors and labelers rather than unconstrained end-to-end decision makers. |
| title | A Consensus-Driven Multi-LLM Pipeline for Missing-Person Investigations |
| topic | Artificial Intelligence Computation and Language Distributed, Parallel, and Cluster Computing Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2603.08954 |