FirmCORe enables detection of business collaboration chances from profiles
FirmCORe: A Benchmark for Structured Reasoning about Inter-Firm Collaboration Opportunities
Artificial Intelligence
Summary
Finding business partners is hard because many connections between companies are private or scattered across places. The authors created FirmCORe, a special dataset where pairs of company profiles are labeled to show if a partnership opportunity exists and details about it. They tested language AI models on this dataset and found the models can spot possible partnerships fairly well, but struggle with identifying the exact type of collaboration or who plays what role. This work helps make business collaboration discovery more systematic, especially for smaller companies.
What this means in practice
- •For business intelligence teams: Automate screening of firm profiles to detect potential collaboration opportunities beyond just similar businesses.
- •For strategic partnership managers: Gain insights on likely collaboration types and roles between companies using AI models trained on FirmCORe data.
Authors
Tian Du, Tiantong Wu, Yafei Wang, Mengyu Liu, Xingyan Chen, Mu Wang
Abstract
Comprehensive structured data on inter-firm relationships is often scarce or inaccessible because many relationships are privately negotiated, selectively disclosed, and fragmented across proprietary databases. This scarcity hinders the discovery of collaboration opportunities, particularly for startups and small and medium-sized enterprises. Firm profiles are readily available, but collaboration potential cannot be inferred from business similarity alone, since similar firms may be competitors, whereas dissimilar firms may offer complementary products, technologies, channels, capabilities, or capital. We present FirmCORe (Inter-Firm Collaboration Opportunity Reasoning), a human-annotated benchmark for pairwise reasoning over weakly structured firm profiles, comprising 2,805 labeled firm pairs. Given two firm profiles, a model must determine whether the available evidence supports a collaboration opportunity and, for positive pairs, jointly predict its strength, primary collaboration type, and role direction. FirmCORe also provides parallel Chinese- and English-language evaluation sets containing identical instances and gold labels, enabling controlled analysis of input-language sensitivity. Experiments with representative locally deployed and hosted large language models (LLMs) show that the strongest model achieves a macro-F1 score of 74.51 for opportunity detection but only 61.57% exact match across all four output fields. Language effects vary across models, and high cross-language agreement can mask errors shared across languages. These results indicate that current LLMs are substantially more reliable at detecting broad collaboration opportunities than at identifying their specific types and role directions.