Causal Interventions Reveal Typologically Organized Syntactic Mechanisms in Multilingual Language Models
本文使用因果干预方法研究多语言模型中的句法机制，发现跨语言机制转移与语言类型相似度有关，为跨语言句法结构提供新假设。
0 citationsRead paper
Selected work
Representative Papers
Parameter-Level Attribution of Symmetry in Trained Networks Though Parameter-Wise Functional Sensitivity
研究通过参数级功能敏感性解决网络训练后对称性问题，提出一种方法在参数空间实现函数空间中的群作用。
0 citationsRead paper
Identification and Inference for Causal Effects in Extremes under General Conditions
本文研究极端事件中的因果关系识别，通过分析因果尾系数（CTC）来解决在存在重尾混淆变量情况下的因果推断问题。
0 citationsRead paper
APICURON: a reactive infrastructure for credit attribution across distributed research data ecosystems
为解决生物数据管理中贡献未被充分认可的问题，APICURON平台通过实时记录和转换策展事件为可验证的工作单元，提供了一种信用归属机制。
0 citationsRead paper
Information leakage from data revisions in retrospective forecasts
This study addresses a critical yet often overlooked source of information leakage in retrospective evaluations of AI-driven forecasting systems: the failure to account for data revisions. The authors systematically demonstrate how this oversight leads to inflated performance estimates and present, for the first time, a cross-domain cautionary framework to mitigate such biases. Through retrospective predictive analysis, explicit modeling of data revision processes, and rigorous evaluation protocols, they reveal that a previously reported AI system’s purported superiority over the CDC ensemble model stems not from genuine predictive gains but from information leakage introduced by unadjusted historical data revisions. These findings establish essential methodological corrections and evaluation standards for future research in AI-based forecasting, ensuring more reliable and reproducible assessments of predictive performance.
0 citationsRead paper
Recent publications
Latest Papers
Causal Interventions Reveal Typologically Organized Syntactic Mechanisms in Multilingual Language Models
本文使用因果干预方法研究多语言模型中的句法机制，发现跨语言机制转移与语言类型相似度有关，为跨语言句法结构提供新假设。
0 citationsRead paper
Parameter-Level Attribution of Symmetry in Trained Networks Though Parameter-Wise Functional Sensitivity
研究通过参数级功能敏感性解决网络训练后对称性问题，提出一种方法在参数空间实现函数空间中的群作用。
0 citationsRead paper
Identification and Inference for Causal Effects in Extremes under General Conditions
本文研究极端事件中的因果关系识别，通过分析因果尾系数（CTC）来解决在存在重尾混淆变量情况下的因果推断问题。
0 citationsRead paper
APICURON: a reactive infrastructure for credit attribution across distributed research data ecosystems
为解决生物数据管理中贡献未被充分认可的问题，APICURON平台通过实时记录和转换策展事件为可验证的工作单元，提供了一种信用归属机制。
0 citationsRead paper
Information leakage from data revisions in retrospective forecasts
This study addresses a critical yet often overlooked source of information leakage in retrospective evaluations of AI-driven forecasting systems: the failure to account for data revisions. The authors systematically demonstrate how this oversight leads to inflated performance estimates and present, for the first time, a cross-domain cautionary framework to mitigate such biases. Through retrospective predictive analysis, explicit modeling of data revision processes, and rigorous evaluation protocols, they reveal that a previously reported AI system’s purported superiority over the CDC ensemble model stems not from genuine predictive gains but from information leakage introduced by unadjusted historical data revisions. These findings establish essential methodological corrections and evaluation standards for future research in AI-based forecasting, ensuring more reliable and reproducible assessments of predictive performance.
0 citationsRead paper