Evaluating, Synthesizing, and Enhancing for Customer Support Conversation
Abstract
A structured framework and datasets for training customer service agents using well-defined support strategies improve the quality of customer support interactions and problem resolution.
Effective customer support requires not only accurate problem solving but also structured and empathetic communication aligned with professional standards. However, existing dialogue datasets often lack strategic guidance, and real-world service data is difficult to access and annotate. To address this, we introduce the task of Customer Support Conversation (CSC), aimed at training customer service agents to respond using well-defined support strategies. We propose a structured CSC framework grounded in COPC guidelines, defining five conversational stages and twelve strategies to guide high-quality interactions. Based on this, we construct CSConv, an evaluation dataset of 1,855 real-world customer-agent conversations rewritten using LLMs to reflect deliberate strategy use, and annotated accordingly. Additionally, we develop a role-playing approach that simulates strategy-rich conversations using LLM-powered roles aligned with the CSC framework, resulting in the training dataset RoleCS. Experiments show that fine-tuning strong LLMs on RoleCS significantly improves their ability to generate high-quality, strategy-aligned responses on CSConv. Human evaluations further confirm gains in problem resolution. All code and data will be made publicly available at https://github.com/aliyun/qwen-dianjin.
Community
Key Points:
- Effective customer support demands both accurate problem-solving and structured, empathetic, professional communication.
- Limitations of existing resources: dialogue datasets lack strategic guidance; real-world service data is hard to access and annotate.
- Solution: Introduce the Customer Support Conversation (CSC) task to train agents in using defined support strategies, alongside a structured CSC framework (based on COPC guidelines) with 5 conversational stages and 12 strategies.
- Datasets:
- CSConv: An evaluation dataset with 1,855 real customer-agent conversations, rewritten via LLMs to reflect deliberate strategy use and annotated accordingly.
- RoleCS: A training dataset generated via role-playing with LLM-powered roles aligned to the CSC framework, simulating strategy-rich interactions.
- Results: Fine-tuning strong LLMs on RoleCS significantly enhances their ability to generate high-quality, strategy-aligned responses on CSConv; human evaluations confirm improved problem resolution.
- Resources: All code and data will be publicly available at https://github.com/aliyun/qwen-dianjin.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Toward Real-World Chinese Psychological Support Dialogues: CPsDD Dataset and a Co-Evolving Multi-Agent System (2025)
- From What to Respond to When to Respond: Timely Response Generation for Open-domain Dialogue Agents (2025)
- PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistants (2025)
- DRIVE: Disfluency-Rich Synthetic Dialog Data Generation Framework for Intelligent Vehicle Environments (2025)
- DialogueForge: LLM Simulation of Human-Chatbot Dialogue (2025)
- Conversational Intent-Driven GraphRAG: Enhancing Multi-Turn Dialogue Systems through Adaptive Dual-Retrieval of Flow Patterns and Context Semantics (2025)
- Enhancing the Preference Extractor in Multi-turn Dialogues: From Annotating Disasters to Accurate Preference Extraction (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 1
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper