Interpreting and Steering LLM Agents for Social Simulations
本文探讨了通过提示操控、SAE特征导向和探针导向三种方法提高基于大语言模型的社会模拟的可解释性和可控性，以更好地理解人类行为。
0 citationsRead paper
Selected work
Representative Papers
Homophily and transitivity in dynamic network formation
研究解决动态网络形成中同质性和传递性问题，通过构建模型分析参数可识别性，并提出一种模拟估计方法。
0 citationsRead paper
Simultaneous Clustered Orthogonalization
研究提出了同时聚类正交化方法，解决了在向量自回归中如何在保持经济意义的集群内相关性的同时跨集群施加正交性的问题。
0 citationsRead paper
ORQA: An Occupation-Realistic Question and Answer Framework for LLM Professional Knowledge
本文提出ORQA框架，通过连接O*NET职业与可信网站生成问题答案对，以测试大型语言模型的职业知识水平，解决了现有方法难以规模化和成本高的问题。
0 citationsRead paper
Scalable Clustered Network Connectedness with Control Variables: Theory and Application to Global Banking
We extend the clustered connectedness framework of Buchwalter, Diebold and Yilmaz (2026) in two complementary directions that improve the robustness and interpretability of cross-cluster connectedness. First, we develop a diagnostic for residual ordering sensitivity by characterizing the distribution of cluster-level net connectedness across all admissible identification orderings and, in particular, by pairing first- and last-position orderings while holding fixed the relative ordering of all other clusters. Second, we introduce a dedicated cluster of control variables to absorb variation associated with observed common macro-financial factors while preserving the computational scalability of the clustered framework. The control cluster is fixed first, and bank innovations are residualized with respect to it before the remaining bank clusters are permuted and orthogonalized as usual, leaving the number of admissible bank-cluster identification strategies unchanged. Under the maintained recursive assumption that control-cluster innovations are contemporaneously exogenous to bank-cluster innovations, the remaining cross-cluster connectedness among the bank clusters can be interpreted as bank-to-bank transmission net of those observed common-factor shocks. We apply the methodology to seventy-one global banks grouped into seven regional clusters over 2003--2024. The treatment of common macro-financial factors materially affects both system-wide cross-group connectedness and cluster-level net positions. Placing the controls in a dedicated first cluster also substantially reduces paired first-versus-last ordering sensitivity across all seven bank clusters, with especially large reductions for the United States and the European clusters.
0 citationsRead paper
Recent publications
Latest Papers
Interpreting and Steering LLM Agents for Social Simulations
本文探讨了通过提示操控、SAE特征导向和探针导向三种方法提高基于大语言模型的社会模拟的可解释性和可控性，以更好地理解人类行为。
0 citationsRead paper
Homophily and transitivity in dynamic network formation
研究解决动态网络形成中同质性和传递性问题，通过构建模型分析参数可识别性，并提出一种模拟估计方法。
0 citationsRead paper
Simultaneous Clustered Orthogonalization
研究提出了同时聚类正交化方法，解决了在向量自回归中如何在保持经济意义的集群内相关性的同时跨集群施加正交性的问题。
0 citationsRead paper
ORQA: An Occupation-Realistic Question and Answer Framework for LLM Professional Knowledge
本文提出ORQA框架，通过连接O*NET职业与可信网站生成问题答案对，以测试大型语言模型的职业知识水平，解决了现有方法难以规模化和成本高的问题。
0 citationsRead paper
Scalable Clustered Network Connectedness with Control Variables: Theory and Application to Global Banking
We extend the clustered connectedness framework of Buchwalter, Diebold and Yilmaz (2026) in two complementary directions that improve the robustness and interpretability of cross-cluster connectedness. First, we develop a diagnostic for residual ordering sensitivity by characterizing the distribution of cluster-level net connectedness across all admissible identification orderings and, in particular, by pairing first- and last-position orderings while holding fixed the relative ordering of all other clusters. Second, we introduce a dedicated cluster of control variables to absorb variation associated with observed common macro-financial factors while preserving the computational scalability of the clustered framework. The control cluster is fixed first, and bank innovations are residualized with respect to it before the remaining bank clusters are permuted and orthogonalized as usual, leaving the number of admissible bank-cluster identification strategies unchanged. Under the maintained recursive assumption that control-cluster innovations are contemporaneously exogenous to bank-cluster innovations, the remaining cross-cluster connectedness among the bank clusters can be interpreted as bank-to-bank transmission net of those observed common-factor shocks. We apply the methodology to seventy-one global banks grouped into seven regional clusters over 2003--2024. The treatment of common macro-financial factors materially affects both system-wide cross-group connectedness and cluster-level net positions. Placing the controls in a dedicated first cluster also substantially reduces paired first-versus-last ordering sensitivity across all seven bank clusters, with especially large reductions for the United States and the European clusters.
0 citationsRead paper