Multi-Agent Collaboration for Hallucination Correction in Complaint Management

Creative Commons License

Çeldir O. M., Dalkiliç G.

2025 9th International Symposium on Innovative Approaches in Smart Technologies (ISAS), Gaziantep, Türkiye, 27 - 28 Haziran 2025, sa.66241, ss.1-8, (Tam Metin Bildiri)

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/isas66241.2025.11101785
  • Basıldığı Şehir: Gaziantep
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.1-8
  • Dokuz Eylül Üniversitesi Adresli: Evet

Özet

Large language models (LLMs) can mimic people with different areas of expertise and, in this way, offer a common solution process for problems with agents having various expert perspectives. This study presents an approach that creates automatic responses to customer complaints using multi-agent collaboration in LLMs. In the proposed structure, agents with different expertise were allowed to develop solutions to the problem through brainstorming. An end-to-end complaint management process was imitated. The results produced by Claude-3.5-Haiku, Gemini-1.5-Flash, and GPT-4o were evaluated using a self-evaluation technique according to ISO 9001 standards. Claude showed higher scores in the results than the other two language models. The developed hybrid method scored higher by ∼2% on average.