An LLM-based Chain-of-Response Counter-Scam System

Kim, Heedou; Gim, Mogan; Choi, Donghee; Bae, Soonil; Lee, Hoonick; Kim, Mi-Young; Kang, Jaewoo

doi:10.24963/ijcai.2026/808

An LLM-based Chain-of-Response Counter-Scam System

Heedou Kim, Mogan Gim, Donghee Choi, Soonil Bae, Hoonick Lee, Mi-Young Kim, Jaewoo Kang

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. AI and Social Good. Pages 7266-7274.

https://doi.org/10.24963/ijcai.2026/808

Keywords

Natural Language Processing: Natural Language Processing
AI Ethics, Trust, Fairness: AI Ethics, Trust, Fairness
Agent-based and Multi-agent Systems: Agent-based and Multi-agent Systems
Multidisciplinary Topics and Applications: Multidisciplinary Topics and Applications

Abstract

The rapid evolution of online scams, driven by transnational networks and mass-produced social engineering scenarios, has exposed the speed limitations of conventional detection, necessitating tighter inter-agency coordination. While LLMs show promise in scam identification, their role in accelerating integrated response frameworks remains underexplored. We propose Counter-Scam, a unified LLM-based multi-agent framework that orchestrates end-to-end response from initial detection to crime investigation. The framework first proposes safe data guidelines, emphasizing non-public scam data and secure dataset construction via scam-specific NER. Developed with insights from 37 stakeholders to reduce delays and improve analytical efficiency, the system integrates CSRA (multi-agent mitigation), CSRT (nine role-aligned NLP tasks), and CSRD (a corpus of 185,300 scam cases and 38,587 knowledge entries). Experiments show that fine-tuned sLLMs surpass commercial models with over 10% in all CSRT tasks and a 0.24 F1 improvement in scam-specific NER. This proves the framework's capability for enabling rapid, collaborative mitigation of online scam.

Heedou Kim, Mogan Gim, Donghee Choi, Soonil Bae, Hoonick Lee, Mi-Young Kim, and Jaewoo Kang. 2026. An LLM-based Chain-of-Response Counter-Scam System. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 7266–7274. https://doi.org/10.24963/ijcai.2026/808

@inproceedings{ijcai2026p808,
  title     = {An LLM-based Chain-of-Response Counter-Scam System},
  author    = {Kim, Heedou and Gim, Mogan and Choi, Donghee and Bae, Soonil and Lee, Hoonick and Kim, Mi-Young and Kang, Jaewoo},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {7266--7274},
  year      = {2026},
  month     = {8},
  note      = {AI and Social Good},
  doi       = {10.24963/ijcai.2026/808},
  url       = {https://doi.org/10.24963/ijcai.2026/808},
}

TY  - CPAPER
TI  - An LLM-based Chain-of-Response Counter-Scam System
AU  - Kim, Heedou
AU  - Gim, Mogan
AU  - Choi, Donghee
AU  - Bae, Soonil
AU  - Lee, Hoonick
AU  - Kim, Mi-Young
AU  - Kang, Jaewoo
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 7266
EP  - 7274
DO  - 10.24963/ijcai.2026/808
UR  - https://doi.org/10.24963/ijcai.2026/808
ER  -