Large language models cross-domain named entity recognition task in the face of the scarcity of large language labeled data in a specific domain,due to the entity bias arising from the variation of entity information ...Large language models cross-domain named entity recognition task in the face of the scarcity of large language labeled data in a specific domain,due to the entity bias arising from the variation of entity information between different domains,which makes large language models prone to spurious correlations problems when dealing with specific domains and entities.In order to solve this problem,this paper proposes a cross-domain named entity recognition method based on causal graph structure enhancement,which captures the cross-domain invariant causal structural representations between feature representations of text sequences and annotation sequences by establishing a causal learning and intervention module,so as to improve the utilization of causal structural features by the large languagemodels in the target domains,and thus effectively alleviate the false entity bias triggered by the false relevance problem;meanwhile,through the semantic feature fusion module,the semantic information of the source and target domains is effectively combined.The results show an improvement of 2.47%and 4.12%in the political and medical domains,respectively,compared with the benchmark model,and an excellent performance in small-sample scenarios,which proves the effectiveness of causal graph structural enhancement in improving the accuracy of cross-domain entity recognition and reducing false correlations.展开更多
Could a causal discontinuity lead to an explanation of fluctuations in the CMBR radiation spectrum? Is this argument valid if there is some third choice of set structure (for instance do self-referential sets fall int...Could a causal discontinuity lead to an explanation of fluctuations in the CMBR radiation spectrum? Is this argument valid if there is some third choice of set structure (for instance do self-referential sets fall into one category or another)? The answer to this question may lie in (entangled) vortex structure of space time, along the lines of structure similar to that generate in the laboratory by Ruutu. Self-referential sets may be part of the generated vortex structure, and we will endeavor to find if this can be experimentally investigated. If the causal set argument and its violation via this procedure holds, we have the view that what we see a space time “drum” effect with the causal discontinuity forming the head of a “drum” for a region of about 10<sup>10</sup> bits of “information” before our present universe up to the instant of the big bang itself for a time region less than t~10<sup>-44 </sup>seconds in duration, with a region of increasing bits of “information” going up to 10<sup>120</sup> due to vortex filament condensed matter style forming through a symmetry breaking phase transition. We address the issue of what this has to do with Bicep 2, the question of scalar-tensor gravity versus general relativity, how to avoid the detection of dust generated Gravity wave signals as what ruined the Bicep 2 experiment and some issues information flow and causal structure has for our CMBR data as seen in an overall summary of these issues in Appendix X, of this document. Appendix XI mentions how to differentiate between scalar-tensor gravity, and general relativity whereas Appendix XII, discusses how to avoid the Bicep 2 mistake again. While Appendix VIII gives us a simple data for a graviton power burst which we find instructive. We stress again, the importance of obtaining clean data sets so as to help us in the eventual detection of gravitational waves which we regard as decisively important and which we think by 2025 or so which will be an important test to discriminate in a full experimental sense the choice of general relativity and other gravity theories, for the evolution of cosmology. Finally, Appendix VII brings up a model for production for gravitons, which is extremely simple. Based upon a formula given in a reference, by Weinberg, in 1971, we chose it due to its illustrative convenience and ties in with Bosonic particles.展开更多
Artificial intelligence generated content(AIGC)has emerged as an indispensable tool for producing large-scale content in various forms,such as images,thanks to the significant role that AI plays in imitation and produ...Artificial intelligence generated content(AIGC)has emerged as an indispensable tool for producing large-scale content in various forms,such as images,thanks to the significant role that AI plays in imitation and production.However,interpretability and controllability remain challenges.Existing AI methods often face challenges in producing images that are both flexible and controllable while considering causal relationships within the images.To address this issue,we have developed a novel method for causal controllable image generation(CCIG)that combines causal representation learning with bi-directional generative adversarial networks(GANs).This approach enables humans to control image attributes while considering the rationality and interpretability of the generated images and also allows for the generation of counterfactual images.The key of our approach,CCIG,lies in the use of a causal structure learning module to learn the causal relationships between image attributes and joint optimization with the encoder,generator,and joint discriminator in the image generation module.By doing so,we can learn causal representations in image’s latent space and use causal intervention operations to control image generation.We conduct extensive experiments on a real-world dataset,CelebA.The experimental results illustrate the effectiveness of CCIG.展开更多
GARCH models play an extremely important role in financial time series.However,the parameter estimation of the multivariate GARCH model is challenging because the parameter number is square of the dimension of the mod...GARCH models play an extremely important role in financial time series.However,the parameter estimation of the multivariate GARCH model is challenging because the parameter number is square of the dimension of the model.In this paper,the model of structural vector autoregressive moving⁃average(ARMA)with GARCH is discussed and an efficient multivariate impulse response estimation method is proposed.First,the causal structure of the model was identified and the independent component of error term vector was estimated by DirectLiNGAM algorithm.Then,the relationship between conditional heteroscedasticity of the independent component of error term vector and that of residual vector was constructed,and the estimation of the impulse response of conditional volatility of multivariate GARCH models was translated to the estimation of the impulse response of error term vector.The independency among the independent components was translated to the impulse response estimation of the univariate case and the causal structure was maintained.Finally,the proposed estimation method was used to estimate the volatility of stock market,which proved that the method is computational efficient.展开更多
基金supported by National Natural Science Foundation of China Joint Fund for Enterprise Innovation Development(U23B2029)National Natural Science Foundation of China(62076167,61772020)+1 种基金Key Scientific Research Project of Higher Education Institutions in Henan Province(24A520058,24A520060,23A520022)Postgraduate Education Reform and Quality Improvement Project of Henan Province(YJS2024AL053).
文摘Large language models cross-domain named entity recognition task in the face of the scarcity of large language labeled data in a specific domain,due to the entity bias arising from the variation of entity information between different domains,which makes large language models prone to spurious correlations problems when dealing with specific domains and entities.In order to solve this problem,this paper proposes a cross-domain named entity recognition method based on causal graph structure enhancement,which captures the cross-domain invariant causal structural representations between feature representations of text sequences and annotation sequences by establishing a causal learning and intervention module,so as to improve the utilization of causal structural features by the large languagemodels in the target domains,and thus effectively alleviate the false entity bias triggered by the false relevance problem;meanwhile,through the semantic feature fusion module,the semantic information of the source and target domains is effectively combined.The results show an improvement of 2.47%and 4.12%in the political and medical domains,respectively,compared with the benchmark model,and an excellent performance in small-sample scenarios,which proves the effectiveness of causal graph structural enhancement in improving the accuracy of cross-domain entity recognition and reducing false correlations.
文摘Could a causal discontinuity lead to an explanation of fluctuations in the CMBR radiation spectrum? Is this argument valid if there is some third choice of set structure (for instance do self-referential sets fall into one category or another)? The answer to this question may lie in (entangled) vortex structure of space time, along the lines of structure similar to that generate in the laboratory by Ruutu. Self-referential sets may be part of the generated vortex structure, and we will endeavor to find if this can be experimentally investigated. If the causal set argument and its violation via this procedure holds, we have the view that what we see a space time “drum” effect with the causal discontinuity forming the head of a “drum” for a region of about 10<sup>10</sup> bits of “information” before our present universe up to the instant of the big bang itself for a time region less than t~10<sup>-44 </sup>seconds in duration, with a region of increasing bits of “information” going up to 10<sup>120</sup> due to vortex filament condensed matter style forming through a symmetry breaking phase transition. We address the issue of what this has to do with Bicep 2, the question of scalar-tensor gravity versus general relativity, how to avoid the detection of dust generated Gravity wave signals as what ruined the Bicep 2 experiment and some issues information flow and causal structure has for our CMBR data as seen in an overall summary of these issues in Appendix X, of this document. Appendix XI mentions how to differentiate between scalar-tensor gravity, and general relativity whereas Appendix XII, discusses how to avoid the Bicep 2 mistake again. While Appendix VIII gives us a simple data for a graviton power burst which we find instructive. We stress again, the importance of obtaining clean data sets so as to help us in the eventual detection of gravitational waves which we regard as decisively important and which we think by 2025 or so which will be an important test to discriminate in a full experimental sense the choice of general relativity and other gravity theories, for the evolution of cosmology. Finally, Appendix VII brings up a model for production for gravitons, which is extremely simple. Based upon a formula given in a reference, by Weinberg, in 1971, we chose it due to its illustrative convenience and ties in with Bosonic particles.
基金Project supported by the National Major Science and Technology Projects of China(No.2022YFB3303302)the National Natural Science Foundation of China(Nos.61977012 and 62207007)the Central Universities Project in China at Chongqing University(Nos.2021CDJYGRH011 and 2020CDJSK06PT14)。
文摘Artificial intelligence generated content(AIGC)has emerged as an indispensable tool for producing large-scale content in various forms,such as images,thanks to the significant role that AI plays in imitation and production.However,interpretability and controllability remain challenges.Existing AI methods often face challenges in producing images that are both flexible and controllable while considering causal relationships within the images.To address this issue,we have developed a novel method for causal controllable image generation(CCIG)that combines causal representation learning with bi-directional generative adversarial networks(GANs).This approach enables humans to control image attributes while considering the rationality and interpretability of the generated images and also allows for the generation of counterfactual images.The key of our approach,CCIG,lies in the use of a causal structure learning module to learn the causal relationships between image attributes and joint optimization with the encoder,generator,and joint discriminator in the image generation module.By doing so,we can learn causal representations in image’s latent space and use causal intervention operations to control image generation.We conduct extensive experiments on a real-world dataset,CelebA.The experimental results illustrate the effectiveness of CCIG.
基金Sponsored by the National Natural Science Foundation of China(Grant No.61573014)
文摘GARCH models play an extremely important role in financial time series.However,the parameter estimation of the multivariate GARCH model is challenging because the parameter number is square of the dimension of the model.In this paper,the model of structural vector autoregressive moving⁃average(ARMA)with GARCH is discussed and an efficient multivariate impulse response estimation method is proposed.First,the causal structure of the model was identified and the independent component of error term vector was estimated by DirectLiNGAM algorithm.Then,the relationship between conditional heteroscedasticity of the independent component of error term vector and that of residual vector was constructed,and the estimation of the impulse response of conditional volatility of multivariate GARCH models was translated to the estimation of the impulse response of error term vector.The independency among the independent components was translated to the impulse response estimation of the univariate case and the causal structure was maintained.Finally,the proposed estimation method was used to estimate the volatility of stock market,which proved that the method is computational efficient.
