PersonaBOT: Bringing Customer Personas to Life with LLMs and RAG
Muhammed Rizwan, Lars Carlsson, Mohammad Loni

TL;DR
This paper presents a method to generate synthetic customer personas using LLMs and integrate them into a RAG chatbot to enhance decision-making support, demonstrating improved accuracy and utility in business scenarios.
Contribution
It introduces a novel approach combining Few-Shot and Chain-of-Thought prompting to generate synthetic personas for RAG chatbots, improving scalability and response quality.
Findings
Few-Shot prompting yields more complete personas.
Chain-of-Thought is more efficient in response time.
Chatbot accuracy improved from 5.88 to 6.42 out of 10.
Abstract
The introduction of Large Language Models (LLMs) has significantly transformed Natural Language Processing (NLP) applications by enabling more advanced analysis of customer personas. At Volvo Construction Equipment (VCE), customer personas have traditionally been developed through qualitative methods, which are time-consuming and lack scalability. The main objective of this paper is to generate synthetic customer personas and integrate them into a Retrieval-Augmented Generation (RAG) chatbot to support decision-making in business processes. To this end, we first focus on developing a persona-based RAG chatbot integrated with verified personas. Next, synthetic personas are generated using Few-Shot and Chain-of-Thought (CoT) prompting techniques and evaluated based on completeness, relevance, and consistency using McNemar's test. In the final step, the chatbot's knowledge base is…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
