Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lee, Yoonjin, Kim, Munhee, Choi, Hanbi, Park, Juhyeon, Lyoo, Seungho, Park, Woojin
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2510.17108
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912819226607616
author Lee, Yoonjin
Kim, Munhee
Choi, Hanbi
Park, Juhyeon
Lyoo, Seungho
Park, Woojin
author_facet Lee, Yoonjin
Kim, Munhee
Choi, Hanbi
Park, Juhyeon
Lyoo, Seungho
Park, Woojin
contents This study investigated LLM-based automation for analyzing non-financial data in corporate credit evaluation. Two systems were developed and compared: a Single-Agent System (SAS), in which one LLM agent infers favorable and adverse repayment signals, and a Popperian Multi-agent Debate System (PMADS), which structures the dual-perspective analysis as adversarial argumentation under the Karl Popper Debate protocol. Evaluation addressed three fronts: (i) work productivity compared with human experts; (ii) perceived report quality and usability, rated by credit risk professionals for system-generated reports; and (iii) reasoning characteristics quantified via reasoning-tree analysis. Both systems drastically reduced task completion time relative to human experts. Professionals rated SAS reports as adequate, while PMADS reports exceeded neutral benchmarks and scored significantly higher in explanatory adequacy, practical applicability, and usability. Reasoning-tree analysis showed PMADS produced deeper, more elaborated structures, whereas SAS yielded single-layered trees. These findings suggest that structured multi-agent debate enhances analytical rigor and perceived usefulness, though at the cost of longer computation time. Overall, the results demonstrate that reasoning-centered automation represents a promising approach for developing useful AI systems in decision-critical financial contexts.
format Preprint
id arxiv_https___arxiv_org_abs_2510_17108
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Structured Debate Improves Corporate Credit Reasoning in Financial AI
Lee, Yoonjin
Kim, Munhee
Choi, Hanbi
Park, Juhyeon
Lyoo, Seungho
Park, Woojin
Artificial Intelligence
This study investigated LLM-based automation for analyzing non-financial data in corporate credit evaluation. Two systems were developed and compared: a Single-Agent System (SAS), in which one LLM agent infers favorable and adverse repayment signals, and a Popperian Multi-agent Debate System (PMADS), which structures the dual-perspective analysis as adversarial argumentation under the Karl Popper Debate protocol. Evaluation addressed three fronts: (i) work productivity compared with human experts; (ii) perceived report quality and usability, rated by credit risk professionals for system-generated reports; and (iii) reasoning characteristics quantified via reasoning-tree analysis. Both systems drastically reduced task completion time relative to human experts. Professionals rated SAS reports as adequate, while PMADS reports exceeded neutral benchmarks and scored significantly higher in explanatory adequacy, practical applicability, and usability. Reasoning-tree analysis showed PMADS produced deeper, more elaborated structures, whereas SAS yielded single-layered trees. These findings suggest that structured multi-agent debate enhances analytical rigor and perceived usefulness, though at the cost of longer computation time. Overall, the results demonstrate that reasoning-centered automation represents a promising approach for developing useful AI systems in decision-critical financial contexts.
title Structured Debate Improves Corporate Credit Reasoning in Financial AI
topic Artificial Intelligence
url https://arxiv.org/abs/2510.17108