Search for: All records

A significant body of research is dedicated to developing language models that can detect various types of online abuse, for example, hate speech, cyberbullying. However, there is a disconnect between platform policies, which often consider the author's intention as a criterion for content moderation, and the current capabilities of detection models, which typically lack efforts to capture intent. This paper examines the role of intent in the moderation of abusive content. Specifically, we review state-of-the-art detection models and benchmark training datasets to assess their ability to capture intent. We propose changes to the design and development of automated detection and moderation systems to improve alignment with ethical and policy conceptualizations of these abuses. 

We present a novel symbolic reasoning engine for SQL which can efficiently generate an inputIfornqueriesP₁, ⋯,P_n, such that their outputs onIsatisfy a given property (expressed in SMT). This is useful in different contexts, such as disproving equivalence of two SQL queries and disambiguating a set of queries. Our first idea is to reason about an under-approximation of eachP_i— that is, a subset ofP_i’s input-output behaviors. While it makes our approach both semantics-aware and lightweight, this idea alone is incomplete (as a fixed under-approximation might miss some behaviors of interest). Therefore, our second idea is to perform search over an expressive family of under-approximations (which collectively cover all program behaviors of interest), thereby making our approach complete. We have implemented these ideas in a tool, Polygon, and evaluated it on over 30,000 benchmarks across two tasks (namely, SQL equivalence refutation and query disambiguation). Our evaluation results show that Polygon significantly outperforms all prior techniques. 

With the increasing prevalence of online learning, adapting education to diverse learner needs remains a persistent challenge. Recent advancements in artificial intelligence (AI), particularly large language models (LLMs), promise powerful tools and capabilities to enhance personalized learning in online educational environments. In this work, we explore how LLMs can improve personalized learning experiences by catering to individual user needs toward enhancing the overall quality of online education. We designed personalization guidelines based on the growing literature on personalized learning to ground LLMs in generating tailored learning plans. To operationalize these guidelines, we implemented LearnMate, an LLM-based system that generates personalized learning plans and provides users with real-time learning support. We discuss the implications and future directions of this work, aiming to move beyond the traditional one-size-fits-all approach by integrating LLM-based personalized support into online learning environments. 

Automated planning is traditionally the domain of experts, utilized in fields like manufacturing and healthcare with the aid of expert planning tools. Recent advancements in LLMs have made planning more accessible to everyday users due to their potential to assist users with complex planning tasks. However, LLMs face several application challenges within end-user planning, including consistency, accuracy, and user trust issues. This paper introduces VeriPlan, a system that applies formal verification techniques, specifically model checking, to enhance the reliability and flexibility of LLMs for end-user planning. In addition to the LLM planner, VeriPlan includes three additional core features—a rule translator, flexibility sliders, and a model checker—that engage users in the verification process. Through a user study (𝑛 = 12), we evaluate VeriPlan, demonstrating improvements in the perceived quality, usability, and user satisfaction of LLMs. Our work shows the effective integration of formal verification and user-control features with LLMs for end-user planning tasks. 

Abstract Nature provides many examples of the benefits of nanoscopic surface structures in areas of adhesion and antifouling. Herein, the design, fabrication, and characterization of liquid crystal elastomer (LCE) films are presented with nanowire surface structures that exhibit tunable stimuli‐responsive deformations and enhanced adhesion properties. The LCE films are shown to curl toward the side with the nanowires when stimulated by heat or organic solvent vapors. In contrast, when a droplet of the same solvent is placed on the film, it curls away from the nanowire side due to nanowire‐induced capillary forces that cause unequal swelling. This characteristic curling deformation is shown to be reversible and can be optimized to match curved substrates, maximizing adhesive shear forces. By using chemical modification, the LCE nanowire films can be given underwater superoleophobicity, enabling oil repellency under a range of harsh conditions. This is combined with the nanowire‐induced frictional asymmetry and the reversible shape deformation to create an underwater droplet mixing robot, capable of performing chemical reactions in aqueous environments. These findings demonstrate the potential of nanowire‐augmented LCE films for advanced applications in soft robotics, adaptive adhesion, and easy chemical modification, with implications for designing responsive materials that integrate mechanical flexibility with surface functionality. 

The task of SQL query equivalence checking is important in various real-world applications (including query rewriting and automated grading) that involve complex queries with integrity constraints; yet, state-of-the-art techniques are very limited in their capability of reasoning about complex features (e.g., those that involve sorting, case statement, rich integrity constraints, etc.) in real-life queries. To the best of our knowledge, we propose the first SMT-based approach and its implementation, VeriEQL, capable of proving and disproving bounded equivalence of complex SQL queries. VeriEQL is based on a new logical encoding that models query semantics over symbolic tuples using the theory of integers with uninterpreted functions. It is simple yet highly practical -- our comprehensive evaluation on over 20,000 benchmarks shows that VeriEQL outperforms all state-of-the-art techniques by more than one order of magnitude in terms of the number of benchmarks that can be proved or disproved. VeriEQL can also generate counterexamples that facilitate many downstream tasks (such as finding serious bugs in systems like MySQL and Apache Calcite). 

Exploratory data analysis can uncover interesting data insights from data. Current methods utilize interestingness measures designed based on system designers' perspectives, thus inherently restricting the insights to their defined scope. These systems, consequently, may not adequately represent a broader range of user interests. Furthermore, most existing approaches that formulate interestingness measure are rule-based, which makes them inevitably brittle and often requires holistic re-design when new user needs are discovered. This paper presents a data-driven technique for deriving an interestingness measure that learns from annotated data. We further develop an innovative annotation algorithm that significantly reduces the annotation cost, and an insight synthesis algorithm based on the Markov Chain Monte Carlo method for efficient discovery of interesting insights. We consolidate these ideas into a system. Our experimental outcomes and user studies demonstrate that DAISY can effectively discover a broad range of interesting insights, thereby substantially advancing the current state-of-the-art.