Fine-Tuning Llama 2 Large Language Models for Detecting Online Sexual Predatory Chats and Abusive Texts
Open accessAbstract
This paper proposes an approach to detection of online harmful content using the open-source pretrained Llama 2 model, recently released by Meta GenAI.We fine-tune the LLM using datasets with different sizes, imbalance degrees, and languages.Based on the power of LLMs, our approach is generic and automated without a manual search for a synergy between feature extraction and classifier design steps like conventional methods.Experimental results show a strong performance of the proposed approach, which is proficient and consistent across three distinct datasets with five sets of experiments.This study's outcomes indicate that the proposed method can be implemented in real-world applications (even with non-English languages) for flagging sexual predators, offensive or toxic content, and hate speech in online discussions and comments to maintain respectful digital communities.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Experimental evidence suggests that routers learn to route inputs according to data clusters, demonstrating their potential in real-world applications.
“Experimental evidence suggests that routers learn to route inputs according to data clusters, demonstrating their potential in real-world applications [295], [289].”
From From Google Gemini to OpenAI Q* (Q-Star): A Survey on Reshaping the Generative Artificial Intelligence (AI) Research Landscape (2025) · cites this paper as [295]
Recent advancements in MoE models, such as those in Switch Transformer, have highlighted significant benefits of intelligent routing, allowing scale up model sizes while keeping compute time constant.
“Recent advancements in MoE models, such as those in the Switch Transformer, have highlighted the significant benefits of intelligent routing, when the router's ability to intelligently route tokens to appropriate experts confers considerable advantages to MoE models, allowing them to scale up model sizes while keeping compute time constant [295], [296], [297].”
From From Google Gemini to OpenAI Q* (Q-Star): A Survey on Reshaping the Generative Artificial Intelligence (AI) Research Landscape (2025) · cites this paper as [295]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Llama 2: Open Foundation and Fine-Tuned Chat Models
Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.09288 · Cited by 2,604 · see citing works
LoRA: Low-Rank Adaptation of Large Language Models
Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2021) · arXiv · doi:10.48550/arxiv.2106.09685 · Cited by 2,523 · see citing works
Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning
Lialin, V., Deshpande, V., Yao, X., & Rumshisky, A. (2023) · arXiv · doi:10.48550/arxiv.2303.15647 · Cited by 88 · see citing works
Flagged first, then by citations
Research works printed but not linked: 6
- Parisa Rezaee Borj, Kiran Raja, and Patrick Bours. Detecting online grooming by sim- ple contrastive chat embeddings. In 9th ACM Int. Workshop on Security and Privacy Analytics, pages 57-65, 2023.
- Muhammad Pervez Akhter, Zheng Jiangbin, Irfan Raza Naqvi, Mohammed Abdelmajeed, and Muhammad Tariq Sadiq. Automatic detection of offensive language for Urdu and Roman Urdu. IEEE Access, 8:91213-91226, 2020.
- Kanishk Verma, Maja Popović, Alexandros Poulis, Yelena Cherkasova, Angela Mazzone, Tijana Milosevic, Brian Davis, et al. Leveraging machine translation for cross-lingual fine-grained cyberbullying classification amongst pre-adolescents. Natural Language Engi- neering, pages 1-23, 2022.
- Armen Aghajanyan, Sonal Gupta, and Luke Zettlemoyer. Intrinsic dimensionality explains the effectiveness of language model fine-tuning. In 59th Annual Meeting of the ACL, volume 1, pages 7319-7328, 2021.
- Giacomo Inches and Fabio Crestani. Overview of the international sexual predator iden- tification competition at PAN-2012. In CLEF (Online Working Notes/Labs/Workshop), volume 30, 2012.
- Muhammad Pervez Akhter, Zheng Jiangbin, Irfan Raza Naqvi, Mohammed AbdelMajeed, and Tehseen Zia. Abusive language detection from social media comments using conven- tional machine learning and deep learning approaches. Multimedia Systems, pages 1-16, 2021.
Cited by
Sorted by citations
McIntosh, T. R., Susnjak, T., Liu, T., Watters, P., Xu, D., Liu, D., & Halgamuge, M. N. (2025) · Technologies · doi:10.3390/technologies13020051 · Cited by 102 · see citing works
A Survey of Generative AI for Detecting Pedophilia Crimes
Silva, F., Silva, R. R., & Bernardino, J. (2025) · Applied Sciences · doi:10.3390/app15137105 · Cited by 4 · see citing works
- Authors
- Nguyen, T. T., Wilson, C., & Dalins, J.
- Affiliations
- Monash University (AU)
- Australian Federal Police (AU)
- Venue
- ESANN 2024 proceesdings
- Publisher
- Ciaco - i6doc.com
- Published
- 2024
- Pages
- 613-618
- OpenAlex
- W4402364221
- Cited by
- 43
- References
- 3
- Citations by year
- 2026: 7 · 2025: 19 · 2024: 15 · 2023: 2
- FWCI
- 12.08
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by-nc-nd)
- arXiv (Cornell University)
- Funders
- National Computational Infrastructure
- Australian Government
- National Cancer Institute
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Text and Document Classification Technologies
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Keywords
- Llama 2, fine-tuning, online sexual predators, toxic content, hate speech, class imbalance, multilingual text classification
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
