A Consensus-Driven Multi-LLM Pipeline for Missing-Person Investigations

TL;DR

The Guardian LLM Pipeline is presented, a multi-model system in which LLMs are used for intelligent information extraction and processing related to missing-person search operations, emphasizing conservative, auditable use of LLMs as structured extractors and labelers rather than unconstrained end-to-end decision makers.

Abstract

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.

Figures (6)

• Figure 1: Guardian System Architecture with two distinct but interconnected systems
• Figure 2: Guardian LLM Pipeline Overview and Consensus Routing
• Figure 3: Centralized Consensus Mechanism and Conflict Resolution Workflow
• Figure 4: Prompt Governance and Template-Based LLM Interaction
• Figure 5: Excerpt from the Llama LLM JSON Output