Debt Collection Negotiations with Large Language Models: An Evaluation System and Optimizing Decision Making with Multi-Agent
Year: 2025
Type: conference-paper
Abstract: Debt collection negotiations (DCN) are vital for managing non-performing loans (NPLs) and reducing creditor losses.Traditional methods are labor-intensive, while large language models (LLMs) offer promising automation potential.However, prior systems lacked dynamic negotiation and real-time decisionmaking capabilities.This paper explores LLMs in automating DCN and proposes a novel evaluation framework with 13 metrics across 4 aspects.Our experiments reveal that LLMs tend to over-concede compared to human negotiators.To address this, we propose the Multi-Agent Debt Negotiation (MADeN) framework, incorporating planning and judging modules to improve decision rationality.We also apply post-training techniques, including DPO with rejection sampling, to optimize performance.Our studies provide valuable insights for practitioners and researchers seeking to enhance efficiency and outcomes in this domain.Our work is accessible
Authors: Xiaofeng Wang, Zhixin Zhang, Jin Guang Zheng, Yiming Ai, Rui Wang
Institutions: Shanghai Jiao Tong University, Ant Group (China)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Funder: Ant Group
OpenAlex ID: W4412888394