Large language models have shown impressive results for multi-hop mathematical reasoning when the input question is only textual. Many mathematical reasoning problems, however, contain both text and image. With the ever-increasing adoption of vision language models (VLMs), understanding their reasoning abilities for such problems is crucial. In this paper, we evaluate the reasoning capabilities of VLMs along various axes through the lens of geometry problems. We procedurally create a synthetic dataset of geometry questions with controllable difficulty levels along multiple axes, thus enabling a systematic evaluation. The empirical results obtained using our benchmark for state-of-the-art VLMs indicate that these models are not as capable in subjects like geometry (and, by generalization, other topics requiring similar reasoning) as suggested by previous benchmarks. This is made especially clear by the construction of our benchmark at various depth levels, since solving higher-depth problems requires long chains of reasoning rather than additional memorized knowledge. We release the dataset for further research in this area.
Over the last couple of decades in the lending industry, financial disintermediation has occurred on a global scale. Traditionally, even for small supply of funds, banks would act as the conduit between the funds and the borrowers. It has now been possible to overcome some of the obstacles associated with such supply of funds with the advent of online platforms like Kiva, Prosper, LendingClub. Kiva for example, works with Micro Finance Institutions (MFIs) in developing countries to build Internet profiles of borrowers with a brief biography, loan requested, loan term, and purpose. Kiva, in particular, allows lenders to fund projects in different sectors through group or individual funding. Traditional research studies have investigated various factors behind lender preferences purely from the perspective of loan attributes and only until recently have some cross-country cultural preferences been investigated. In this paper, we investigate lender perceptions of economic factors of the borrower countries in relation to their preferences towards loans associated with different sectors. We find that the influence from economic factors and loan attributes can have substantially different roles to play for different sectors in achieving faster funding. We formally investigate and quantify the hidden biases prevalent in different loan sectors using recent tools from causal inference and regression models that rely on Bayesian variable selection methods. We then extend these models to incorporate fairness constraints based on our empirical analysis and find that such models can still achieve near comparable results with respect to baseline regression models.
Pathogenic Social Media (PSM) accounts such as terrorist supporter accounts and fake news writers have the capability of spreading disinformation to viral proportions. Early detection of PSM accounts is crucial as they are likely to be key users to make malicious information "viral". In this paper, we adopt the causal inference framework along with graph-based metrics in order to distinguish PSMs from normal users within a short time of their activities. We propose both supervised and semi-supervised approaches without taking the network information and content into account. Results on a real-world dataset from Twitter accentuates the advantage of our proposed frameworks. We show our approach achieves 0.28 improvement in F1 score over existing approaches with the precision of 0.90 and F1 score of 0.63.
Pathogenic Social Media (PSM) accounts such as terrorist supporters exploit large communities of supporters for conducting attacks on social media. Early detection of these accounts is crucial as they are high likely to be key users in making a harmful message "viral". In this paper, we make the first attempt on utilizing causal inference to identify PSMs within a short time frame around their activity. We propose a time-decay causality metric and incorporate it into a causal community detection-based algorithm. The proposed algorithm is applied to groups of accounts sharing similar causality features and is followed by a classification algorithm to classify accounts as PSM or not. Unlike existing techniques that take significant time to collect information such as network, cascade path, or content, our scheme relies solely on action log of users. Results on a real-world dataset from Twitter demonstrate effectiveness and efficiency of our approach. We achieved precision of 0.84 for detecting PSMs only based on their first 10 days of activity; the misclassified accounts were then detected 10 days later.
Pathogenic social media accounts such as terrorist supporters exploit communities of supporters for conducting attacks on social media. Early detection of PSM accounts is crucial as they are likely to be key users in making a harmful message "viral". This paper overviews my recent doctoral work on utilizing causal inference to identify PSM accounts within a short time frame around their activity. The proposed scheme (1) assigns time-decay causality scores to users, (2) applies a community detection-based algorithm to group of users sharing similar causality scores and finally (3) deploys a classification algorithm to classify accounts. Unlike existing techniques that require network structure, cascade path, or content, our scheme relies solely on action log of users.
High-order parametric models that include terms for feature interactions are applied to various data mining tasks, where ground truth depends on interactions of features. However, with sparse data, the high- dimensional parameters for feature interactions often face three issues: expensive computation, difficulty in parameter estimation and lack of structure. Previous work has proposed approaches which can partially re- solve the three issues. In particular, models with factorized parameters (e.g. Factorization Machines) and sparse learning algorithms (e.g. FTRL-Proximal) can tackle the first two issues but fail to address the third. Regarding to unstructured parameters, constraints or complicated regularization terms are applied such that hierarchical structures can be imposed. However, these methods make the optimization problem more challenging. In this work, we propose Strongly Hierarchical Factorization Machines and ANOVA kernel regression where all the three issues can be addressed without making the optimization problem more difficult. Experimental results show the proposed models significantly outperform the state-of-the-art in two data mining tasks: cold-start user response time prediction and stock volatility prediction.
Human trafficking is one of the most atrocious crimes and among the challenging problems facing law enforcement which demands attention of global magnitude. In this study, we leverage textual data from the website "Backpage"- used for classified advertisement- to discern potential patterns of human trafficking activities which manifest online and identify advertisements of high interest to law enforcement. Due to the lack of ground truth, we rely on a human analyst from law enforcement, for hand-labeling a small portion of the crawled data. We extend the existing Laplacian SVM and present S3VM-R, by adding a regularization term to exploit exogenous information embedded in our feature space in favor of the task at hand. We train the proposed method using labeled and unlabeled data and evaluate it on a fraction of the unlabeled data, herein referred to as unseen data, with our expert's further verification. Results from comparisons between our method and other semi-supervised and supervised approaches on the labeled data demonstrate that our learner is effective in identifying advertisements of high interest to law enforcement
Each day, approximately 500 missing persons cases occur that go unsolved/unresolved in the United States. The non-profit organization known as the Find Me Group (FMG), led by former law enforcement professionals, is dedicated to solving or resolving these cases. This paper introduces the Missing Person Intelligence Synthesis Toolkit (MIST) which leverages a data-driven variant of geospatial abductive inference. This system takes search locations provided by a group of experts and rank-orders them based on the probability assigned to areas based on the prior performance of the experts taken as a group. We evaluate our approach compared to the current practices employed by the Find Me Group and found it significantly reduces the search area - leading to a reduction of 31 square miles over 24 cases we examined in our experiments. Currently, we are using MIST to aid the Find Me Group in an active missing person case.
Human trafficking is among the most challenging law enforcement problems which demands persistent fight against from all over the globe. In this study, we leverage readily available data from the website "Backpage"-- used for classified advertisement-- to discern potential patterns of human trafficking activities which manifest online and identify most likely trafficking related advertisements. Due to the lack of ground truth, we rely on two human analysts --one human trafficking victim survivor and one from law enforcement, for hand-labeling the small portion of the crawled data. We then present a semi-supervised learning approach that is trained on the available labeled and unlabeled data and evaluated on unseen data with further verification of experts.