Aligning Large Language Models (LLMs) with investor decision-making processes under herd behavior is a critical challenge in behavioral finance, which grapples with a fundamental limitation: the scarcity of real-user data needed for Supervised Fine-Tuning (SFT). While SFT can bridge the gap between LLM outputs and human behavioral patterns, its reliance on massive authentic data imposes substantial collection costs and privacy risks. We propose InvestAlign, a novel framework that constructs high-quality SFT datasets by leveraging theoretical solutions to similar and simple optimal investment problems rather than the complex scenarios. Our theoretical analysis demonstrates that training LLMs with InvestAlign-generated data achieves faster parameter convergence than using real-user data, suggesting superior learning efficiency. Furthermore, we develop InvestAgent, an LLM agent fine-tuned with InvestAlign, which shows significantly closer alignment to real-user data than pre-SFT models in both simple and complex investment problems. This highlights our proposed InvestAlign as a promising approach with the potential to address complex optimal investment problems and align LLMs with investor decision-making processes under herd behavior. Our code is publicly available at https://github.com/thu-social-network-research-group/InvestAlign.

In complex social environments, influential entities—such as governments, corporations, and public figures—face growing challenges in effectively managing both their reputation and influence during public engagement activities such as governance, service delivery, and crisis communication. In these interactions, the public forms perceptions and responds behaviorally, which can be reflected in two dynamic and interdependent attributes: reputation and influence. They are jointly shaped by the entity’s actual performance over time, such as the provision of products or services. Prior research has extensively examined the management of reputation and influence as separate issues, and often neglect their interactions. This study analyzes strategies based on the influential entity’s actual performance, accounting for the mutual interdependence between reputation and influence. Based on the reputation-influence co-evolution model, we propose a framework for determining the minimum time-invariant performance required to meet predefined thresholds for reputation and influence. We obtain the optimal strategy to satisfy both requirements. Simulation results on both real-world data and synthetic networks validate the proposed model and our theoretical analysis.

In social network, the existence of malicious users can create lots of detrimental consequences. To diminish their negative influences, it is necessary for rational users to identify and interact with each neighbor carefully to protect themselves from malicious ones. Therefore, it is crucial to establish a rule for users’ interaction in order to mitigate malicious users’ influences. In this paper, we propose a smart evolution model based on evolutionary game theory by introducing the reputation mechanism. The model takes into account both current reputation and instant incentives during users’ decision-making process. On the basis of whether users share reputation values with others, we introduce schemes without reciprocity principle and with the indirect reciprocity principle respectively. With the social norm and reputation updating policy, we theoretically analyze the evolutionary dynamics and corresponding ESSs by explicitly considering the effects of malicious users. Finally, simulations based on synthetic networks and real-world data are conducted to validate the effectiveness of the proposed smart evolution model.