多大模型协作分析走失案，提升早期搜寻效率
A Consensus-Driven Multi-LLM Pipeline for Missing-Person Investigations
- 用多个专用大模型分步处理线索，再由共识引擎统一判断
- 基于精选数据微调，准确提取关键信息并减少错误
- 适合公安刑侦、应急搜救等需要严谨决策的场景
走失人员调查的前72小时至关重要。Guardian 是一个端到端系统，旨在支持走失儿童调查与早期搜索规划。本文提出 Guardian LLM Pipeline，一种多模型协同系统，利用大模型对走失人员搜寻任务中的信息进行智能提取与处理。该管道通过任务专用的大模型实现端到端执行，并引入共识大模型引擎，对比多个模型输出并解决分歧。系统进一步通过基于QLoRA的微调增强性能，使用精心构建的数据集进行训练。设计遵循弱监督与大模型辅助标注的先前研究，强调大模型作为结构化信息提取器和标注器的保守、可审计使用，而非无约束的端到端决策者。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。