A Cost-Effective LLM-based Approach to Identify Wildlife Trafficking in Online Marketplaces

2025-04-29

AI Summary

Addressing the high cost and poor generalizability of acquiring high-quality labeled data for detecting illegal online wildlife trade, this paper proposes a lightweight annotation paradigm that integrates LLM-generated pseudo-labels with active learning sampling, enhanced by domain-adapted prompt engineering and supervised fine-tuning of RoBERTa/DeBERTa models. The approach substantially reduces reliance on manual annotation while preserving semantic diversity and model generalization capability. Experimental results demonstrate a classifier F1-score of 95%, significantly outperforming direct LLM inference, with over 80% reduction in annotation cost. The system has been deployed and validated in real-world law enforcement analytics scenarios, delivering a scalable, low-cost, and high-accuracy technical solution for combating cyber-enabled wildlife crime.

Technology Category

• Machine Learning: Active Learning
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Wildlife trafficking remains a critical global issue, significantly impacting biodiversity, ecological stability, and public health. Despite efforts to combat this illicit trade, the rise of e-commerce platforms has made it easier to sell wildlife products, putting new pressure on wild populations of endangered and threatened species. The use of these platforms also opens a new opportunity: as criminals sell wildlife products online, they leave digital traces of their activity that can provide insights into trafficking activities as well as how they can be disrupted. The challenge lies in finding these traces. Online marketplaces publish ads for a plethora of products, and identifying ads for wildlife-related products is like finding a needle in a haystack. Learning classifiers can automate ad identification, but creating them requires costly, time-consuming data labeling that hinders support for diverse ads and research questions. This paper addresses a critical challenge in the data science pipeline for wildlife trafficking analytics: generating quality labeled data for classifiers that select relevant data. While large language models (LLMs) can directly label advertisements, doing so at scale is prohibitively expensive. We propose a cost-effective strategy that leverages LLMs to generate pseudo labels for a small sample of the data and uses these labels to create specialized classification models. Our novel method automatically gathers diverse and representative samples to be labeled while minimizing the labeling costs. Our experimental evaluation shows that our classifiers achieve up to 95% F1 score, outperforming LLMs at a lower cost. We present real use cases that demonstrate the effectiveness of our approach in enabling analyses of different aspects of wildlife trafficking.

Problem

• Identifying wildlife trafficking ads in online marketplaces efficiently
• Reducing costly data labeling for wildlife product ad classification
• Leveraging LLMs for cost-effective pseudo-labeling to train classifiers

Innovation

• Leverages LLMs for pseudo-labeling small data samples
• Creates specialized classifiers from pseudo labels
• Minimizes labeling costs while maintaining high accuracy