A Cost-Effective LLM-based Approach to Identify Wildlife Trafficking in Online Marketplaces
Summary: Cost-efficient data labeling for wildlife-ad detection using LLM-generated pseudo labels on a diverse, small sample to train specialized classifiers. A sampling-driven pipeline reduces labeling costs while maintaining coverage, achieving up to 95% F1 and enabling scalable analysis of wildlife trafficking in online marketplaces. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Juliana Silva Barbosa (New York University)
- 2. Ulhas Gondhali (John Jay College of Criminal Justice)
- 3. Gohar Petrossian (John Jay College of Criminal Justice)
- 4. Kinshuk Sharma (Indiana University Indianapolis)
- 5. Sunandan Chakraborty (Indiana University Indianapolis)
- 6. Jennifer Jacquet (University of Miami)
- 7. Juliana Freire (New York University)
BibTeX Citation
@inproceedings{barbosa_sigmod25,
title = {{A Cost-Effective LLM-based Approach to Identify Wildlife Trafficking in Online Marketplaces}},
author = {Barbosa, Juliana Silva and Gondhali, Ulhas and Petrossian, Gohar and Sharma, Kinshuk and Chakraborty, Sunandan and Jacquet, Jennifer and Freire, Juliana},
series = {{SIGMOD} '25},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3725256},
url = {https://dl.acm.org/doi/10.1145/3725256},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 9 of 9 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 329 | Can Foundation Models Wrangle Your Data? | 2023 | VLDB | 0.00020858443 |
| 1,120 | Snuba: Automating Weak Supervision to Label Training Data | 2019 | VLDB | 0.00011946047 |
| 1,932 | CHORUS: Foundation Models for Unified Data Discovery and Exploration | 2024 | VLDB | 9.34643e-05 |
| 3,473 | Unicorn: A Unified Multi-tasking Model for Supporting Matching Tasks in Data Integration | 2023 | SIGMOD | 7.2728706e-05 |
| 3,736 | Snorkel: Fast Training Set Generation for Information Extraction | 2017 | SIGMOD | 7.0642592e-05 |
| 4,543 | GOGGLES: Automatic Image Labeling with Affinity Coding | 2020 | SIGMOD | 6.5470116e-05 |
| 4,867 | Selective Data Acquisition in the Wild for Model Charging | 2022 | VLDB | 6.3749346e-05 |
| 5,746 | Optimizing Data Acquisition to Enhance Machine Learning Performance | 2024 | VLDB | 6.0083431e-05 |
| 6,937 | Inspector Gadget: A Data Programming-based Labeling System for Industrial Images | 2021 | VLDB | 5.6397218e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 3,729 | Protecting Data Markets from Strategic Buyers | 2022 | SIGMOD |
| 2 | 9,487 | LLM-PBE: Assessing Data Privacy in Large Language Models | 2024 | VLDB |
| 3 | 11,767 | Self-Training for Label-Efficient Information Extraction from Semi-Structured Web-Pages | 2023 | VLDB |
| 4 | 10,841 | Bolt-on, Verifiable Provenance for LLM-Powered Data Processing | 2026 | VLDB |
| 5 | 11,164 | Sentence to Model: Cost-Effective Data Collection LLM Agent | 2025 | SIGMOD |
| 6 | 8,316 | ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries | 2025 | VLDB |
| 7 | 11,061 | LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning | 2026 | VLDB |
| 8 | 1,362 | Towards Model-based Pricing for Machine Learning in a Data Marketplace | 2019 | SIGMOD |
| 9 | 8,997 | Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees | 2026 | SIGMOD |
| 10 | 10,527 | In-context Clustering-based Entity Resolution with Large Language Models: A Design Space Exploration | 2026 | SIGMOD |