InterCorpRel-LLM: Enhancing Financial Relational Understanding with Graph-Language Models
Qianyou Sun, Jiexin Zheng, Bohan Jin, Lihua Chen, Yijie Peng
TL;DR
InterCorpRel-LLM addresses the challenge of modeling inter-firm relationships by integrating graph structure with financial text through a GNN–LLM hybrid. The approach introduces a domain-specific dataset, a two-stage, parameter-efficient training paradigm, and an alignment module to fuse graph tokens with LLM inputs, achieving state-of-the-art performance on supply relation prediction (F1 up to 0.8543 inductive) and strong zero-shot competitor identification. The results demonstrate that careful alignment of structural and semantic cues, rather than mere model scale, yields robust inter-firm reasoning with practical implications for financial analysis and risk management. Overall, the work provides a scalable, domain-adaptive framework for mapping and reasoning about complex corporate networks in dynamic markets.
Abstract
Identifying inter-firm relationships such as supply and competitive ties is critical for financial analysis and corporate governance, yet remains challenging due to the scale, sparsity, and contextual dependence of corporate data. Graph-based methods capture structure but miss semantic depth, while large language models (LLMs) excel at text but remain limited in their ability to represent relational dependencies. To address this, we propose InterCorpRel-LLM, a cross-modal framework that integrates GNNs with LLMs, supported by a proprietary dataset derived from FactSet supply chain records and three tailored training tasks: company graph matching, industry classification, and supply relation prediction. This design enables effective joint modeling of structure and semantics. Experiments show that InterCorpRel-LLM substantially outperforms strong baselines, including GPT-5, on a supply relation identification task, achieving an F-score of 0.8543 vs. 0.2287 with only a 7B-parameter backbone and lightweight training. The model also generalizes to zero-shot competitor identification, underscoring its ability to capture nuanced inter-firm dynamics. Our framework thus provides analysts and strategists with a robust tool for mapping and reasoning about complex corporate networks, enhancing decision-making and risk management in dynamic markets.