This study focuses on media bias detection, crucial in today's era of influential social media platforms shaping individual attitudes and opinions. In contrast to prior work that primarily relies on training specific models tailored to particular datasets, resulting in limited adaptability and subpar performance on out-of-domain data, we introduce a general bias detection framework, IndiVec, built upon large language models. IndiVec begins by constructing a fine-grained media bias database, leveraging the robust instruction-following capabilities of large language models and vector database techniques. When confronted with new input for bias detection, our framework automatically selects the most relevant indicator from the vector database and employs majority voting to determine the input's bias label. IndiVec excels compared to previous methods due to its adaptability (demonstrating consistent performance across diverse datasets from various sources) and explainability (providing explicit top-k indicators to interpret bias predictions). Experimental results on four political bias datasets highlight IndiVec's significant superiority over baselines. Furthermore, additional experiments and analysis provide profound insights into the framework's effectiveness.
相關內容
The pursuit of higher data rates and efficient spectrum utilization in modern communication technologies necessitates novel solutions. In order to provide insights into improving spectral efficiency and reducing latency, this study investigates the maximum channel coding rate (MCCR) of finite block length (FBL) multiple-input multiple-output (MIMO) faster-than-Nyquist (FTN) channels. By optimizing power allocation, we derive the system's MCCR expression. Simulation results are compared with the existing literature to reveal the benefits of FTN in FBL transmission.
Learning robust and scalable visual representations from massive multi-view video data remains a challenge in computer vision and autonomous driving. Existing pre-training methods either rely on expensive supervised learning with 3D annotations, limiting the scalability, or focus on single-frame or monocular inputs, neglecting the temporal information. We propose MIM4D, a novel pre-training paradigm based on dual masked image modeling (MIM). MIM4D leverages both spatial and temporal relations by training on masked multi-view video inputs. It constructs pseudo-3D features using continuous scene flow and projects them onto 2D plane for supervision. To address the lack of dense 3D supervision, MIM4D reconstruct pixels by employing 3D volumetric differentiable rendering to learn geometric representations. We demonstrate that MIM4D achieves state-of-the-art performance on the nuScenes dataset for visual representation learning in autonomous driving. It significantly improves existing methods on multiple downstream tasks, including BEV segmentation (8.7% IoU), 3D object detection (3.5% mAP), and HD map construction (1.4% mAP). Our work offers a new choice for learning representation at scale in autonomous driving. Code and models are released at //github.com/hustvl/MIM4D
Achieving robust uncertainty quantification for deep neural networks represents an important requirement in many real-world applications of deep learning such as medical imaging where it is necessary to assess the reliability of a neural network's prediction. Bayesian neural networks are a promising approach for modeling uncertainties in deep neural networks. Unfortunately, generating samples from the posterior distribution of neural networks is a major challenge. One significant advance in that direction would be the incorporation of adaptive step sizes, similar to modern neural network optimizers, into Monte Carlo Markov chain sampling algorithms without significantly increasing computational demand. Over the past years, several papers have introduced sampling algorithms with claims that they achieve this property. However, do they indeed converge to the correct distribution? In this paper, we demonstrate that these methods can have a substantial bias in the distribution they sample, even in the limit of vanishing step sizes and at full batch size.
This study explores the critical role of open government data (OGD) portals in fostering transparency and collaboration between diverse stakeholders. Recognizing the challenges of usability, communication with diverse populations, and strategic value creation, this paper develops an integrated framework for evaluating OGD portal effectiveness that accommodates user diversity (regardless of their data literacy and language), evaluates collaboration and participation, and the ability of users to explore and understand the data provided through them. The framework is validated by applying it to 33 national portals across European Union and Gulf Cooperation Council (GCC) countries, as a result of which we rank OGD portals, identify some good practices that lower-performing portals can learn from, and common shortcomings. Notably, the study unveils the competitive and innovative nature of GCC OGD portals, pinpointing specific improvement areas such as multilingual support and data understandability. The findings underscore the growing trend of exposing data quality metrics and advocate for enhanced two-way communication channels between users and portal representatives. Overall, the study contributes to accelerating the development of user-friendly, collaborative, and sustainable OGD portals while addressing gaps identified in previous research.
Much research has highlighted the impressive capabilities of large language models (LLMs), like GPT and Bard, for solving introductory programming exercises. Recent work has shown that LLMs can effectively solve a range of more complex object-oriented programming (OOP) exercises with text-based specifications. This raises concerns about academic integrity, as students might use these models to complete assignments unethically, neglecting the development of important skills such as program design, problem-solving, and computational thinking. To address this, we propose an innovative approach to formulating OOP tasks using diagrams and videos, as a way to foster problem-solving and deter students from a copy-and-prompt approach in OOP courses. We introduce a novel notation system for specifying OOP assignments, encompassing structural and behavioral requirements, and assess its use in a classroom setting over a semester. Student perceptions of this approach are explored through a survey (n=56). Generally, students responded positively to diagrams and videos, with video-based projects being better received than diagram-based exercises. This notation appears to have several benefits, with students investing more effort in understanding the diagrams and feeling more motivated to engage with the video-based projects. Furthermore, students reported being less inclined to rely on LLM-based code generation tools for these diagram and video-based exercises. Experiments with GPT-4 and Bard's vision abilities revealed that they currently fall short in interpreting these diagrams to generate accurate code solutions.
Open Source Software Field Research: Spanning Social and Practice Networks for Re-Entering the Field
Sociotechnical research increasingly includes the social sub-networks that emerge from large-scale sociotechnical infrastructure, including the infrastructure for building open source software. This paper addresses these numerous sub-networks as advantageous for researchers. It provides a methodological synthesis focusing on how researchers can best span adjacent social sub-networks during engaged field research. Specifically, we describe practices and artifacts that aid movement from one social subsystem within a more extensive technical infrastructure to another. To surface the importance of spanning sub-networks, we incorporate a discussion of social capital and the role of technical infrastructure in its development for sociotechnical researchers. We then characterize a five-step process for spanning social sub-networks during engaged field research: commitment, context mapping, jargon competence, returning value, and bridging. We then present our experience studying corporate open source software projects and the role of that experience in accelerating our work in open source scientific software research as described through the lens of bridging social capital. Based on our analysis, we offer recommendations for engaging in fieldwork in adjacent social sub-networks that share a technical context and discussion of how the relationship between social and technically acquired social capital is a missing but critical methodological dimension for research on large-scale sociotechnical research.
Kernel techniques are among the most influential approaches in data science and statistics. Under mild conditions, the reproducing kernel Hilbert space associated to a kernel is capable of encoding the independence of $M\ge 2$ random variables. Probably the most widespread independence measure relying on kernels is the so-called Hilbert-Schmidt independence criterion (HSIC; also referred to as distance covariance in the statistics literature). Despite various existing HSIC estimators designed since its introduction close to two decades ago, the fundamental question of the rate at which HSIC can be estimated is still open. In this work, we prove that the minimax optimal rate of HSIC estimation on $\mathbb R^d$ for Borel measures containing the Gaussians with continuous bounded translation-invariant characteristic kernels is $\mathcal O\!\left(n^{-1/2}\right)$. Specifically, our result implies the optimality in the minimax sense of many of the most-frequently used estimators (including the U-statistic, the V-statistic, and the Nystr\"om-based one) on $\mathbb R^d$.
We study the problem of post-selection predictive inference in an online fashion. To avoid devoting resources to unimportant units, a preliminary selection of the current individual before reporting its prediction interval is common and meaningful in online predictive tasks. Since the online selection causes a temporal multiplicity in the selected prediction intervals, it is important to control the real-time false coverage-statement rate (FCR) to measure the averaged miscoverage error. We develop a general framework named CAS (Calibration after Adaptive Selection) that can wrap around any prediction model and online selection rule to output post-selection prediction intervals. If the current individual is selected, we first perform an adaptive selection on historical data to construct a calibration set, then output a conformal prediction interval for the unobserved label. We provide tractable constructions for the calibration set for popular online selection rules. We proved that CAS can achieve an exact selection-conditional coverage guarantee in the finite-sample and distribution-free regimes. For the decision-driven selection rule, including most online multiple-testing procedures, CAS can exactly control the real-time FCR below the target level without any distributional assumptions. For the online selection with symmetric thresholds, we establish the error bound for the control gap of FCR under mild distributional assumptions. To account for the distribution shift in online data, we also embed CAS into some recent dynamic conformal prediction methods and examine the long-run FCR control. Numerical results on both synthetic and real data corroborate that CAS can effectively control FCR around the target level and yield more narrowed prediction intervals over existing baselines across various settings.
We present an extensive, in-depth analysis of the eye tracking capabilities of the Meta Quest Pro virtual reality headset using a dataset of eye movement recordings collected from 78 participants. In addition to presenting classical signal quality metrics--spatial accuracy, spatial precision and linearity--in ideal settings, we also study the impact of background luminance and headset slippage on device performance. We additionally present a user-centered analysis of eye tracking signal quality, where we highlight the potential differences in user experience as a function of device performance. This work contributes to a growing understanding of eye tracking signal quality in virtual reality headsets, where the performance of applications such as gaze-based interaction, foveated rendering, and social gaze are directly dependent on the quality of eye tracking signal.
Small data challenges have emerged in many learning problems, since the success of deep neural networks often relies on the availability of a huge amount of labeled data that is expensive to collect. To address it, many efforts have been made on training complex models with small data in an unsupervised and semi-supervised fashion. In this paper, we will review the recent progresses on these two major categories of methods. A wide spectrum of small data models will be categorized in a big picture, where we will show how they interplay with each other to motivate explorations of new ideas. We will review the criteria of learning the transformation equivariant, disentangled, self-supervised and semi-supervised representations, which underpin the foundations of recent developments. Many instantiations of unsupervised and semi-supervised generative models have been developed on the basis of these criteria, greatly expanding the territory of existing autoencoders, generative adversarial nets (GANs) and other deep networks by exploring the distribution of unlabeled data for more powerful representations. While we focus on the unsupervised and semi-supervised methods, we will also provide a broader review of other emerging topics, from unsupervised and semi-supervised domain adaptation to the fundamental roles of transformation equivariance and invariance in training a wide spectrum of deep networks. It is impossible for us to write an exclusive encyclopedia to include all related works. Instead, we aim at exploring the main ideas, principles and methods in this area to reveal where we are heading on the journey towards addressing the small data challenges in this big data era.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191