亚洲男人的天堂2018av,欧美草比,久久久久久免费视频精选,国色天香在线看免费,久久久久亚洲av成人片仓井空

We expose a surprising failure of generalization in auto-regressive large language models (LLMs). If a model is trained on a sentence of the form "A is B", it will not automatically generalize to the reverse direction "B is A". This is the Reversal Curse. For instance, if a model is trained on "Olaf Scholz was the ninth Chancellor of Germany", it will not automatically be able to answer the question, "Who was the ninth Chancellor of Germany?". Moreover, the likelihood of the correct answer ("Olaf Scholz") will not be higher than for a random name. Thus, models exhibit a basic failure of logical deduction and do not generalize a prevalent pattern in their training set (i.e. if "A is B'' occurs, "B is A" is more likely to occur). We provide evidence for the Reversal Curse by finetuning GPT-3 and Llama-1 on fictitious statements such as "Uriah Hawthorne is the composer of 'Abyssal Melodies'" and showing that they fail to correctly answer "Who composed 'Abyssal Melodies?'". The Reversal Curse is robust across model sizes and model families and is not alleviated by data augmentation. We also evaluate ChatGPT (GPT-3.5 and GPT-4) on questions about real-world celebrities, such as "Who is Tom Cruise's mother? [A: Mary Lee Pfeiffer]" and the reverse "Who is Mary Lee Pfeiffer's son?". GPT-4 correctly answers questions like the former 79% of the time, compared to 33% for the latter. This shows a failure of logical deduction that we hypothesize is caused by the Reversal Curse. Code is available at //github.com/lukasberglund/reversal_curse.

Hand-crafted image quality metrics, such as PSNR and SSIM, are commonly used to evaluate model privacy risk under reconstruction attacks. Under these metrics, reconstructed images that are determined to resemble the original one generally indicate more privacy leakage. Images determined as overall dissimilar, on the other hand, indicate higher robustness against attack. However, there is no guarantee that these metrics well reflect human opinions, which, as a judgement for model privacy leakage, are more trustworthy. In this paper, we comprehensively study the faithfulness of these hand-crafted metrics to human perception of privacy information from the reconstructed images. On 5 datasets ranging from natural images, faces, to fine-grained classes, we use 4 existing attack methods to reconstruct images from many different classification models and, for each reconstructed image, we ask multiple human annotators to assess whether this image is recognizable. Our studies reveal that the hand-crafted metrics only have a weak correlation with the human evaluation of privacy leakage and that even these metrics themselves often contradict each other. These observations suggest risks of current metrics in the community. To address this potential risk, we propose a learning-based measure called SemSim to evaluate the Semantic Similarity between the original and reconstructed images. SemSim is trained with a standard triplet loss, using an original image as an anchor, one of its recognizable reconstructed images as a positive sample, and an unrecognizable one as a negative. By training on human annotations, SemSim exhibits a greater reflection of privacy leakage on the semantic level. We show that SemSim has a significantly higher correlation with human judgment compared with existing metrics. Moreover, this strong correlation generalizes to unseen datasets, models and attack methods.

Neural networks drive the success of natural language processing. A fundamental property of language is its compositional structure, allowing humans to produce forms for new meanings systematically. However, unlike humans, neural networks notoriously struggle with systematic generalization, and do not necessarily benefit from compositional structure in emergent communication simulations. This poses a problem for using neural networks to simulate human language learning and evolution, and suggests crucial differences in the biases of the different learning systems. Here, we directly test how neural networks compare to humans in learning and generalizing different input languages that vary in their degree of structure. We evaluate the memorization and generalization capabilities of a pre-trained language model GPT-3.5 (analagous to an adult second language learner) and recurrent neural networks trained from scratch (analaogous to a child first language learner). Our results show striking similarities between deep neural networks and adult human learners, with more structured linguistic input leading to more systematic generalization and to better convergence between neural networks and humans. These findings suggest that all the learning systems are sensitive to the structure of languages in similar ways with compositionality being advantageous for learning. Our findings draw a clear prediction regarding children's learning biases, as well as highlight the challenges of automated processing of languages spoken by small communities. Notably, the similarity between humans and machines opens new avenues for research on language learning and evolution.

Generative Artificial Intelligence (GenAI) in Education has in a few short months moved from being the topic of discussion around speculative education futures to a very concrete reality. It is clear that the future of education, as all industries, is collaboration with GenAI. GenAI attributes make it well suited for social and constructivist approaches to learning that value collaboration, community and the construction of knowledge and skills through active learning. This article presents an approach to designing education in collaboration with GenAI, based on digital education frameworks adapted for this new hybrid of the AI age.

Multimodal Large Language Models (MLLMs) that integrate text and other modalities (especially vision) have achieved unprecedented performance in various multimodal tasks. However, due to the unsolved adversarial robustness problem of vision models, MLLMs can have more severe safety and security risks by introducing the vision inputs. In this work, we study the adversarial robustness of Google's Bard, a competitive chatbot to ChatGPT that released its multimodal capability recently, to better understand the vulnerabilities of commercial MLLMs. By attacking white-box surrogate vision encoders or MLLMs, the generated adversarial examples can mislead Bard to output wrong image descriptions with a 22% success rate based solely on the transferability. We show that the adversarial examples can also attack other MLLMs, e.g., a 26% attack success rate against Bing Chat and a 86% attack success rate against ERNIE bot. Moreover, we identify two defense mechanisms of Bard, including face detection and toxicity detection of images. We design corresponding attacks to evade these defenses, demonstrating that the current defenses of Bard are also vulnerable. We hope this work can deepen our understanding on the robustness of MLLMs and facilitate future research on defenses. Our code is available at //github.com/thu-ml/Attack-Bard.

The swift advancement in the scale and capabilities of Large Language Models (LLMs) positions them as promising tools for a variety of downstream tasks. In addition to the pursuit of better performance and the avoidance of violent feedback on a certain prompt, to ensure the responsibility of the LLM, much attention is drawn to the robustness of LLMs. However, existing evaluation methods mostly rely on traditional question answering datasets with predefined supervised labels, which do not align with the superior generation capabilities of contemporary LLMs. To address this issue, we propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools to evaluate the robustness of LLMs, which we refer to as the Reward Model for Reasonable Robustness Evaluation (TREvaL). Our extensive empirical experiments have demonstrated that TREval provides an accurate method for evaluating the robustness of an LLM, especially when faced with more challenging open questions. Furthermore, our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations, which are commonplace in daily language usage. Notably, we were surprised to discover that robustness tends to decrease as fine-tuning (SFT and RLHF) is conducted. The code of TREval is available in //github.com/Harry-mic/TREval.

Recently, large language models (LLMs), particularly GPT-4, have demonstrated significant capabilities in various planning and reasoning tasks \cite{cheng2023gpt4,bubeck2023sparks}. Motivated by these advancements, there has been a surge of interest among researchers to harness the capabilities of GPT-4 for the automated design of quantitative factors that do not overlap with existing factor libraries, with an aspiration to achieve alpha returns \cite{webpagequant}. In contrast to these work, this study aims to examine the fidelity of GPT-4's comprehension of classic trading theories and its proficiency in applying its code interpreter abilities to real-world trading data analysis. Such an exploration is instrumental in discerning whether the underlying logic GPT-4 employs for trading is intrinsically reliable. Furthermore, given the acknowledged interpretative latitude inherent in most trading theories, we seek to distill more precise methodologies of deploying these theories from GPT-4's analytical process, potentially offering invaluable insights to human traders. To achieve this objective, we selected daily candlestick (K-line) data from specific periods for certain assets, such as the Shanghai Stock Index. Through meticulous prompt engineering, we guided GPT-4 to analyze the technical structures embedded within this data, based on specific theories like the Elliott Wave Theory. We then subjected its analytical output to manual evaluation, assessing its interpretative depth and accuracy vis-\`a-vis these trading theories from multiple dimensions. The results and findings from this study could pave the way for a synergistic amalgamation of human expertise and AI-driven insights in the realm of trading.

The Mat\'ern family of covariance functions is currently the most popularly used model in spatial statistics, geostatistics, and machine learning to specify the correlation between two geographical locations based on spatial distance. Compared to existing covariance functions, the Mat\'ern family has more flexibility in data fitting because it allows the control of the field smoothness through a dedicated parameter. Moreover, it generalizes other popular covariance functions. However, fitting the smoothness parameter is computationally challenging since it complicates the optimization process. As a result, some practitioners set the smoothness parameter at an arbitrary value to reduce the optimization convergence time. In the literature, studies have used various parameterizations of the Mat\'ern covariance function, assuming they are equivalent. This work aims at studying the effectiveness of different parameterizations under various settings. We demonstrate the feasibility of inferring all parameters simultaneously and quantifying their uncertainties on large-scale data using the ExaGeoStat parallel software. We also highlight the importance of the smoothness parameter by analyzing the Fisher information of the statistical parameters. We show that the various parameterizations have different properties and differ from several perspectives. In particular, we study the three most popular parameterizations in terms of parameter estimation accuracy, modeling accuracy and efficiency, prediction efficiency, uncertainty quantification, and asymptotic properties. We further demonstrate their differing performances under nugget effects and approximated covariance. Lastly, we give recommendations for parameterization selection based on our experimental results.

Compared with cheap addition operation, multiplication operation is of much higher computation complexity. The widely-used convolutions in deep neural networks are exactly cross-correlation to measure the similarity between input feature and convolution filters, which involves massive multiplications between float values. In this paper, we present adder networks (AdderNets) to trade these massive multiplications in deep neural networks, especially convolutional neural networks (CNNs), for much cheaper additions to reduce computation costs. In AdderNets, we take the $\ell_1$-norm distance between filters and input feature as the output response. The influence of this new similarity measure on the optimization of neural network have been thoroughly analyzed. To achieve a better performance, we develop a special back-propagation approach for AdderNets by investigating the full-precision gradient. We then propose an adaptive learning rate strategy to enhance the training procedure of AdderNets according to the magnitude of each neuron's gradient. As a result, the proposed AdderNets can achieve 74.9% Top-1 accuracy 91.7% Top-5 accuracy using ResNet-50 on the ImageNet dataset without any multiplication in convolution layer.

Object detection typically assumes that training and test data are drawn from an identical distribution, which, however, does not always hold in practice. Such a distribution mismatch will lead to a significant performance drop. In this work, we aim to improve the cross-domain robustness of object detection. We tackle the domain shift on two levels: 1) the image-level shift, such as image style, illumination, etc, and 2) the instance-level shift, such as object appearance, size, etc. We build our approach based on the recent state-of-the-art Faster R-CNN model, and design two domain adaptation components, on image level and instance level, to reduce the domain discrepancy. The two domain adaptation components are based on H-divergence theory, and are implemented by learning a domain classifier in adversarial training manner. The domain classifiers on different levels are further reinforced with a consistency regularization to learn a domain-invariant region proposal network (RPN) in the Faster R-CNN model. We evaluate our newly proposed approach using multiple datasets including Cityscapes, KITTI, SIM10K, etc. The results demonstrate the effectiveness of our proposed approach for robust object detection in various domain shift scenarios.