Pub Date : 1900-01-01DOI: 10.54364/aaiml.2021.1112
R. Sear, R. Leahy, N. J. Restrepo, Y. Lupu, N. Johnson
Any uptick in new misinformation that casts doubt on COVID-19 mitigation strategies, such as vaccine boosters and masks, could reverse society’s recovery from the pandemic both nationally and globally. This study demonstrates howmachine learning language models can automatically generate new COVID-19 and vaccine misinformation that appears fresh and realistic (i.e. human-generated) even to subject matter experts. The study uses the latest version of theGPTmodel that is public and freely available, GPT-2, and inputs publicly available text collected from social media communities that are known for their high levels of health misinformation. The same team of subject matter experts that classified the original social media data used as input, are then asked to categorize the GPT-2 output without knowing about its automated origin. None of them successfully identified all the synthetic text strings as being a product of the machine model. This presents a clear warning for social media platforms: an unlimited volume of fresh and seemingly human-produced misinformation can be created perpetually on social media using current, off-the-shelf machine learning algorithms that run continually. We then offer a solution: a statistical approach that detects differences in the dynamics of this output as compared to typical human behavior.
{"title":"Machine Learning Language Models: Achilles Heel for Social Media Platforms and a Possible Solution","authors":"R. Sear, R. Leahy, N. J. Restrepo, Y. Lupu, N. Johnson","doi":"10.54364/aaiml.2021.1112","DOIUrl":"https://doi.org/10.54364/aaiml.2021.1112","url":null,"abstract":"Any uptick in new misinformation that casts doubt on COVID-19 mitigation strategies, such as vaccine boosters and masks, could reverse society’s recovery from the pandemic both nationally and globally. This study demonstrates howmachine learning language models can automatically generate new COVID-19 and vaccine misinformation that appears fresh and realistic (i.e. human-generated) even to subject matter experts. The study uses the latest version of theGPTmodel that is public and freely available, GPT-2, and inputs publicly available text collected from social media communities that are known for their high levels of health misinformation. The same team of subject matter experts that classified the original social media data used as input, are then asked to categorize the GPT-2 output without knowing about its automated origin. None of them successfully identified all the synthetic text strings as being a product of the machine model. This presents a clear warning for social media platforms: an unlimited volume of fresh and seemingly human-produced misinformation can be created perpetually on social media using current, off-the-shelf machine learning algorithms that run continually. We then offer a solution: a statistical approach that detects differences in the dynamics of this output as compared to typical human behavior.","PeriodicalId":373878,"journal":{"name":"Adv. Artif. Intell. Mach. Learn.","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121352832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.54364/aaiml.2021.1107
Maximilian Becker, Nadia Burkart, Pascal Birnstill, J. Beyerer
The field of Explainable Artificial Intelligence (XAI) tries to make learned models more understandable. One type of explanation for such models are counterfactual explanations. Counterfactual explanations explain the decision for a specific instance, the factual, by providing a similar instance which leads to a different decision, the counterfactual. In this work a new approaches around the idea of counterfactuals was developed. It generates a data structure over the feature space of a classification problem to accelerate the search for counterfactuals and augments them with global explanations. The approach maps the feature space by hierarchically dividing it into regions which belong to the same class. It is applicable in any case where predictions can be generated for input data, even without direct access to the model. The framework works well for lower-dimensional problems but becomes unpractical due to high computation times at around 12 to 15 dimensions.
{"title":"A Step Towards Global Counterfactual Explanations: Approximating the Feature Space Through Hierarchical Division and Graph Search","authors":"Maximilian Becker, Nadia Burkart, Pascal Birnstill, J. Beyerer","doi":"10.54364/aaiml.2021.1107","DOIUrl":"https://doi.org/10.54364/aaiml.2021.1107","url":null,"abstract":"The field of Explainable Artificial Intelligence (XAI) tries to make learned models more understandable. One type of explanation for such models are counterfactual explanations. Counterfactual explanations explain the decision for a specific instance, the factual, by providing a similar instance which leads to a different decision, the counterfactual. In this work a new approaches around the idea of counterfactuals was developed. It generates a data structure over the feature space of a classification problem to accelerate the search for counterfactuals and augments them with global explanations. The approach maps the feature space by hierarchically dividing it into regions which belong to the same class. It is applicable in any case where predictions can be generated for input data, even without direct access to the model. The framework works well for lower-dimensional problems but becomes unpractical due to high computation times at around 12 to 15 dimensions.","PeriodicalId":373878,"journal":{"name":"Adv. Artif. Intell. Mach. Learn.","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115113694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：