AI-powered systems have gained widespread popularity in various domains, including Autonomous Vehicles (AVs). However, ensuring their reliability and safety is challenging due to their complex nature. Conventional test adequacy metrics, designed to evaluate the effectiveness of traditional software testing, are often insufficient or impractical for these systems. White-box metrics, which are specifically designed for these systems, leverage neuron coverage information. These coverage metrics necessitate access to the underlying AI model and training data, which may not always be available. Furthermore, the existing adequacy metrics exhibit weak correlations with the ability to detect faults in the generated test suite, creating a gap that we aim to bridge in this study. In this paper, we introduce a set of black-box test adequacy metrics called "Test suite Instance Space Adequacy" (TISA) metrics, which can be used to gauge the effectiveness of a test suite. The TISA metrics offer a way to assess both the diversity and coverage of the test suite and the range of bugs detected during testing. Additionally, we introduce a framework that permits testers to visualise the diversity and coverage of the test suite in a two-dimensional space, facilitating the identification of areas that require improvement. We evaluate the efficacy of the TISA metrics by examining their correlation with the number of bugs detected in system-level simulation testing of AVs. A strong correlation, coupled with the short computation time, indicates their effectiveness and efficiency in estimating the adequacy of testing AVs.
相關內容
We present DIALIGHT, a toolkit for developing and evaluating multilingual Task-Oriented Dialogue (ToD) systems which facilitates systematic evaluations and comparisons between ToD systems using fine-tuning of Pretrained Language Models (PLMs) and those utilising the zero-shot and in-context learning capabilities of Large Language Models (LLMs). In addition to automatic evaluation, this toolkit features (i) a secure, user-friendly web interface for fine-grained human evaluation at both local utterance level and global dialogue level, and (ii) a microservice-based backend, improving efficiency and scalability. Our evaluations reveal that while PLM fine-tuning leads to higher accuracy and coherence, LLM-based systems excel in producing diverse and likeable responses. However, we also identify significant challenges of LLMs in adherence to task-specific instructions and generating outputs in multiple languages, highlighting areas for future research. We hope this open-sourced toolkit will serve as a valuable resource for researchers aiming to develop and properly evaluate multilingual ToD systems and will lower, currently still high, entry barriers in the field.
Domain Generalization (DG) aims to reduce domain shifts between domains to achieve promising performance on the unseen target domain, which has been widely practiced in medical image segmentation. Single-source domain generalization (SDG) is the most challenging setting that trains on only one source domain. Although existing methods have made considerable progress on SDG of medical image segmentation, the performances are still far from the applicable standards when faced with a relatively large domain shift. In this paper, we leverage the Segment Anything Model (SAM) to SDG to greatly improve the ability of generalization. Specifically, we introduce a parallel framework, the source images are sent into the SAM module and normal segmentation module respectively. To reduce the calculation resources, we apply a merging strategy before sending images to the SAM module. We extract the bounding boxes from the segmentation module and send the refined version as prompts to the SAM module. We evaluate our model on a classic DG dataset and achieve competitive results compared to other state-of-the-art DG methods. Furthermore, We conducted a series of ablation experiments to prove the effectiveness of the proposed method. The code is publicly available at //github.com/SARIHUST/SAMMed.
The emergence of Large Language Models (LLMs) such as ChatGPT and LLaMA encounter limitations in domain-specific tasks, with these models often lacking depth and accuracy in specialized areas, and exhibiting a decrease in general capabilities when fine-tuned, particularly analysis ability in small sized models. To address these gaps, we introduce ICE-GRT, utilizing Reinforcement Learning from Human Feedback (RLHF) grounded in Proximal Policy Optimization (PPO), demonstrating remarkable ability in in-domain scenarios without compromising general task performance. Our exploration of ICE-GRT highlights its understanding and reasoning ability to not only generate robust answers but also to provide detailed analyses of the reasons behind the answer. This capability marks a significant progression beyond the scope of Supervised Fine-Tuning models. The success of ICE-GRT is dependent on several crucial factors, including Appropriate Data, Reward Size Scaling, KL-Control, Advantage Normalization, etc. The ICE-GRT model exhibits state-of-the-art performance in domain-specific tasks and across 12 general Language tasks against equivalent size and even larger size LLMs, highlighting the effectiveness of our approach. We provide a comprehensive analysis of the ICE-GRT, underscoring the significant advancements it brings to the field of LLM.
Artificial neural networks (ANNs) have permeated various disciplinary domains, ranging from bioinformatics to financial analytics, where their application has become an indispensable facet of contemporary scientific research endeavors. However, the inherent limitations of traditional neural networks arise due to their relatively fixed network structures and activation functions. 1, The type of activation function is single and relatively fixed, which leads to poor "unit representation ability" of the network, and it is often used to solve simple problems with very complex networks; 2, the network structure is not adaptive, it is easy to cause network structure redundant or insufficient. To address the aforementioned issues, this study proposes a novel neural network called X-Net. By utilizing our designed Alternating Backpropagation mechanism, X-Net dynamically selects appropriate activation functions based on derivative information during training to enhance the network's representation capability for specific tasks. Simultaneously, it accurately adjusts the network structure at the neuron level to accommodate tasks of varying complexities and reduce computational costs. Through a series of experiments, we demonstrate the dual advantages of X-Net in terms of reducing model size and improving representation power. Specifically, in terms of the number of parameters, X-Net is only 3$\%$ of baselines on average, and only 1.4$\%$ under some tasks. In terms of representation ability, X-Net can achieve an average $R^2$=0.985 on the fitting task by only optimizing the activation function without introducing any parameters. Finally, we also tested the ability of X-Net to help scientific discovery on data from multiple disciplines such as society, energy, environment, and aerospace, and achieved concise and good results.
Recent advancements in diffusion models and large language models (LLMs) have significantly propelled the field of AIGC. Text-to-Audio (TTA), a burgeoning AIGC application designed to generate audio from natural language prompts, is attracting increasing attention. However, existing TTA studies often struggle with generation quality and text-audio alignment, especially for complex textual inputs. Drawing inspiration from state-of-the-art Text-to-Image (T2I) diffusion models, we introduce Auffusion, a TTA system adapting T2I model frameworks to TTA task, by effectively leveraging their inherent generative strengths and precise cross-modal alignment. Our objective and subjective evaluations demonstrate that Auffusion surpasses previous TTA approaches using limited data and computational resource. Furthermore, previous studies in T2I recognizes the significant impact of encoder choice on cross-modal alignment, like fine-grained details and object bindings, while similar evaluation is lacking in prior TTA works. Through comprehensive ablation studies and innovative cross-attention map visualizations, we provide insightful assessments of text-audio alignment in TTA. Our findings reveal Auffusion's superior capability in generating audios that accurately match textual descriptions, which further demonstrated in several related tasks, such as audio style transfer, inpainting and other manipulations. Our implementation and demos are available at //auffusion.github.io.
Despite recent initiatives aimed at improving accessibility, the field of digital accessibility remains markedly behind contemporary advancements in the software industry as a large number of real world software and web applications continue to fall short of accessibility requirements. A persisting skills deficit within the existing technology workforce has been an enduring impediment, hindering organizations from delivering truly accessible software products. This, in turn, elevates the risk of isolating and excluding a substantial portion of potential users. In this paper, we report lessons learned from a training program for teaching digital accessibility using the Communities of Practice (CoP) framework to industry professionals. We recruited 66 participants from a large multi-national software company and assigned them to two groups: one participating in a CoP and the other using self-paced learning. We report experiences from designing the training program, conducting the actual training, and assessing the efficiency of the two approaches. Based on these findings, we provide recommendations for practitioners in Learning and Development teams and educators in designing accessibility courses for industry professionals.
In open-domain Question Answering (QA), dense retrieval is crucial for finding relevant passages for answer generation. Typically, contrastive learning is used to train a retrieval model that maps passages and queries to the same semantic space. The objective is to make similar ones closer and dissimilar ones further apart. However, training such a system is challenging due to the false negative issue, where relevant passages may be missed during data annotation. Hard negative sampling, which is commonly used to improve contrastive learning, can introduce more noise in training. This is because hard negatives are those closer to a given query, and thus more likely to be false negatives. To address this issue, we propose a novel contrastive confidence regularizer for Noise Contrastive Estimation (NCE) loss, a commonly used loss for dense retrieval. Our analysis shows that the regularizer helps dense retrieval models be more robust against false negatives with a theoretical guarantee. Additionally, we propose a model-agnostic method to filter out noisy negative passages in the dataset, improving any downstream dense retrieval models. Through experiments on three datasets, we demonstrate that our method achieves better retrieval performance in comparison to existing state-of-the-art dense retrieval systems.
Collecting supporting evidence from large corpora of text (e.g., Wikipedia) is of great challenge for open-domain Question Answering (QA). Especially, for multi-hop open-domain QA, scattered evidence pieces are required to be gathered together to support the answer extraction. In this paper, we propose a new retrieval target, hop, to collect the hidden reasoning evidence from Wikipedia for complex question answering. Specifically, the hop in this paper is defined as the combination of a hyperlink and the corresponding outbound link document. The hyperlink is encoded as the mention embedding which models the structured knowledge of how the outbound link entity is mentioned in the textual context, and the corresponding outbound link document is encoded as the document embedding representing the unstructured knowledge within it. Accordingly, we build HopRetriever which retrieves hops over Wikipedia to answer complex questions. Experiments on the HotpotQA dataset demonstrate that HopRetriever outperforms previously published evidence retrieval methods by large margins. Moreover, our approach also yields quantifiable interpretations of the evidence collection process.
Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of large DNNs in low-power devices with limited compute resources. Recent research improves DNN models by reducing the memory requirement, energy consumption, and number of operations without significantly decreasing the accuracy. This paper surveys the progress of low-power deep learning and computer vision, specifically in regards to inference, and discusses the methods for compacting and accelerating DNN models. The techniques can be divided into four major categories: (1) parameter quantization and pruning, (2) compressed convolutional filters and matrix factorization, (3) network architecture search, and (4) knowledge distillation. We analyze the accuracy, advantages, disadvantages, and potential solutions to the problems with the techniques in each category. We also discuss new evaluation metrics as a guideline for future research.
User engagement is a critical metric for evaluating the quality of open-domain dialogue systems. Prior work has focused on conversation-level engagement by using heuristically constructed features such as the number of turns and the total time of the conversation. In this paper, we investigate the possibility and efficacy of estimating utterance-level engagement and define a novel metric, {\em predictive engagement}, for automatic evaluation of open-domain dialogue systems. Our experiments demonstrate that (1) human annotators have high agreement on assessing utterance-level engagement scores; (2) conversation-level engagement scores can be predicted from properly aggregated utterance-level engagement scores. Furthermore, we show that the utterance-level engagement scores can be learned from data. These scores can improve automatic evaluation metrics for open-domain dialogue systems, as shown by correlation with human judgements. This suggests that predictive engagement can be used as a real-time feedback for training better dialogue models.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191