While VideoQA Transformer models demonstrate competitive performance on standard benchmarks, the reasons behind their success are not fully understood. Do these models jointly capture and leverage the rich multimodal structures and dynamics from video and text? Or are they merely exploiting shortcuts to achieve high scores? Hence, we design $\textit{QUAG}$ (QUadrant AveraGe), a lightweight and non-parametric probe, to critically analyze multimodal representations. QUAG facilitates combined dataset-model study by systematic ablation of model's coupled multimodal understanding during inference. Surprisingly, it demonstrates that the models manage to maintain high performance even under multimodal impairment. We extend QUAG to design "QUAG-attention", a simplistic and less-expressive replacement of self-attention. We find that the models with QUAG-attention achieve similar performance with significantly less mulops without any finetuning. These findings indicate that the current VideoQA benchmarks and metrics do not penalize models that find shortcuts and discount joint multimodal understanding. Motivated by this, we propose the $\textit{CLAVI}$ (Counterfactual in LAnguage and VIdeo), a diagnostic dataset for coupled multimodal understanding in VideoQA. CLAVI consists of temporal questions and videos that are augmented to curate balanced counterfactuals in language and video domains. We evaluate models on CLAVI and find that all models achieve high performance on multimodal shortcut instances, but most of them have poor performance on the counterfactual instances that necessitate joint multimodal understanding. Overall, with the multimodal representation analysis using QUAG and diagnostic analysis using CLAVI, we show that many VideoQA models are incapable of learning multimodal representations and that their success on standard datasets is an illusion of joint multimodal understanding.
相關內容
While large language models (LLMs) already achieve strong performance on standard generic summarization benchmarks, their performance on more complex summarization task settings is less studied. Therefore, we benchmark LLMs on instruction controllable text summarization, where the model input consists of both a source article and a natural language requirement for the desired summary characteristics. To this end, we curate an evaluation-only dataset for this task setting and conduct human evaluation on 5 LLM-based summarization systems. We then benchmark LLM-based automatic evaluation for this task with 4 different evaluation protocols and 11 LLMs, resulting in 40 evaluation methods in total. Our study reveals that instruction controllable text summarization remains a challenging task for LLMs, since (1) all LLMs evaluated still make factual and other types of errors in their summaries; (2) all LLM-based evaluation methods cannot achieve a strong alignment with human annotators when judging the quality of candidate summaries; (3) different LLMs show large performance gaps in summary generation and evaluation. We make our collected benchmark, InstruSum, publicly available to facilitate future research in this direction.
Machine Translation (MT) continues to improve in quality and adoption, yet the inadvertent perpetuation of gender bias remains a significant concern. Despite numerous studies into gender bias in translations from gender-neutral languages such as Turkish into more strongly gendered languages like English, there are no benchmarks for evaluating this phenomenon or for assessing mitigation strategies. To address this gap, we introduce GATE X-E, an extension to the GATE (Rarrick et al., 2023) corpus, that consists of human translations from Turkish, Hungarian, Finnish, and Persian into English. Each translation is accompanied by feminine, masculine, and neutral variants for each possible gender interpretation. The dataset, which contains between 1250 and 1850 instances for each of the four language pairs, features natural sentences with a wide range of sentence lengths and domains, challenging translation rewriters on various linguistic phenomena. Additionally, we present an English gender rewriting solution built on GPT-3.5 Turbo and use GATE X-E to evaluate it. We open source our contributions to encourage further research on gender debiasing.
In power systems, the incorporation of capacitors offers a wide range of established advantages. These benefits encompass the enhancement of the systems power factor, optimization of voltage profiles, increased capacity for current flow through cables and transformers, and the mitigation of losses attributed to the compensation of reactive power components. Different techniques have been applied to enhance the performance of the distribution system by reducing line losses. This paper focuses on reducing line losses through the optimal placement and sizing of capacitors. Optimal capacitor placement is analysed using load flow analysis with the Newton Raphson method. The placement of capacitor optimization is related to the sensitivity of the buses, which depends on the loss sensitivity factor. The optimal capacitor size is determined using Particle Swarm Optimization (PSO). The analysis is conducted using the IEEE 14 bus system in MATLAB. The results reveal that placing capacitors at the most sensitive bus locations leads to a significant reduction in line losses. Additionally, the optimal capacitor size has a substantial impact on improving the voltage profile and the power loss is reduced by 21.02 percent through the proposed method.
Watermarking generative models consists of planting a statistical signal (watermark) in a model's output so that it can be later verified that the output was generated by the given model. A strong watermarking scheme satisfies the property that a computationally bounded attacker cannot erase the watermark without causing significant quality degradation. In this paper, we study the (im)possibility of strong watermarking schemes. We prove that, under well-specified and natural assumptions, strong watermarking is impossible to achieve. This holds even in the private detection algorithm setting, where the watermark insertion and detection algorithms share a secret key, unknown to the attacker. To prove this result, we introduce a generic efficient watermark attack; the attacker is not required to know the private key of the scheme or even which scheme is used. Our attack is based on two assumptions: (1) The attacker has access to a "quality oracle" that can evaluate whether a candidate output is a high-quality response to a prompt, and (2) The attacker has access to a "perturbation oracle" which can modify an output with a nontrivial probability of maintaining quality, and which induces an efficiently mixing random walk on high-quality outputs. We argue that both assumptions can be satisfied in practice by an attacker with weaker computational capabilities than the watermarked model itself, to which the attacker has only black-box access. Furthermore, our assumptions will likely only be easier to satisfy over time as models grow in capabilities and modalities. We demonstrate the feasibility of our attack by instantiating it to attack three existing watermarking schemes for large language models: Kirchenbauer et al. (2023), Kuditipudi et al. (2023), and Zhao et al. (2023). The same attack successfully removes the watermarks planted by all three schemes, with only minor quality degradation.
Evaluation is essential to understanding the value that digital creativity brings to people's experience, for example in terms of their enjoyment, creativity, and engagement. There is a substantial body of research on how to design and evaluate interactive arts and digital creativity applications. There is also extensive Human-Computer Interaction (HCI) literature on how to evaluate user interfaces and user experiences. However, it can be difficult for artists, practitioners, and researchers to navigate such a broad and disparate collection of materials when considering how to evaluate technology they create that is at the intersection of art and interaction. This chapter provides a guide to designing robust user studies of creative applications at the intersection of art, technology and interaction, which we refer to as Media and Arts Technology (MAT). We break MAT studies down into two main kinds: proof-of-concept and comparative studies. As MAT studies are exploratory in nature, their evaluation requires the collection and analysis of both qualitative data such as free text questionnaire responses, interviews, and observations, and also quantitative data such as questionnaires, number of interactions, and length of time spent interacting. This chapter draws on over 15 years of experience of designing and evaluating novel interactive systems to provide a concrete template on how to structure a study to evaluate MATs that is both rigorous and repeatable, and how to report study results that are publishable and accessible to a wide readership in art and science communities alike.
Outdoor advertising, such as roadside billboards, plays a significant role in marketing campaigns but can also be a distraction for drivers, potentially leading to accidents. In this study, we propose a pipeline for evaluating the significance of roadside billboards in videos captured from a driver's perspective. We have collected and annotated a new BillboardLamac dataset, comprising eight videos captured by drivers driving through a predefined path wearing eye-tracking devices. The dataset includes annotations of billboards, including 154 unique IDs and 155 thousand bounding boxes, as well as eye fixation data. We evaluate various object tracking methods in combination with a YOLOv8 detector to identify billboard advertisements with the best approach achieving 38.5 HOTA on BillboardLamac. Additionally, we train a random forest classifier to classify billboards into three classes based on the length of driver fixations achieving 75.8% test accuracy. An analysis of the trained classifier reveals that the duration of billboard visibility, its saliency, and size are the most influential features when assessing billboard significance.
In pace with developments in the research field of artificial intelligence, knowledge graphs (KGs) have attracted a surge of interest from both academia and industry. As a representation of semantic relations between entities, KGs have proven to be particularly relevant for natural language processing (NLP), experiencing a rapid spread and wide adoption within recent years. Given the increasing amount of research work in this area, several KG-related approaches have been surveyed in the NLP research community. However, a comprehensive study that categorizes established topics and reviews the maturity of individual research streams remains absent to this day. Contributing to closing this gap, we systematically analyzed 507 papers from the literature on KGs in NLP. Our survey encompasses a multifaceted review of tasks, research types, and contributions. As a result, we present a structured overview of the research landscape, provide a taxonomy of tasks, summarize our findings, and highlight directions for future work.
Predictions obtained by, e.g., artificial neural networks have a high accuracy but humans often perceive the models as black boxes. Insights about the decision making are mostly opaque for humans. Particularly understanding the decision making in highly sensitive areas such as healthcare or fifinance, is of paramount importance. The decision-making behind the black boxes requires it to be more transparent, accountable, and understandable for humans. This survey paper provides essential definitions, an overview of the different principles and methodologies of explainable Supervised Machine Learning (SML). We conduct a state-of-the-art survey that reviews past and recent explainable SML approaches and classifies them according to the introduced definitions. Finally, we illustrate principles by means of an explanatory case study and discuss important future directions.
Recent years have seen important advances in the quality of state-of-the-art models, but this has come at the expense of models becoming less interpretable. This survey presents an overview of the current state of Explainable AI (XAI), considered within the domain of Natural Language Processing (NLP). We discuss the main categorization of explanations, as well as the various ways explanations can be arrived at and visualized. We detail the operations and explainability techniques currently available for generating explanations for NLP model predictions, to serve as a resource for model developers in the community. Finally, we point out the current gaps and encourage directions for future work in this important research area.
This paper aims at revisiting Graph Convolutional Neural Networks by bridging the gap between spectral and spatial design of graph convolutions. We theoretically demonstrate some equivalence of the graph convolution process regardless it is designed in the spatial or the spectral domain. The obtained general framework allows to lead a spectral analysis of the most popular ConvGNNs, explaining their performance and showing their limits. Moreover, the proposed framework is used to design new convolutions in spectral domain with a custom frequency profile while applying them in the spatial domain. We also propose a generalization of the depthwise separable convolution framework for graph convolutional networks, what allows to decrease the total number of trainable parameters by keeping the capacity of the model. To the best of our knowledge, such a framework has never been used in the GNNs literature. Our proposals are evaluated on both transductive and inductive graph learning problems. Obtained results show the relevance of the proposed method and provide one of the first experimental evidence of transferability of spectral filter coefficients from one graph to another. Our source codes are publicly available at: //github.com/balcilar/Spectral-Designed-Graph-Convolutions
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191