This study investigates the forecasting accuracy of human experts versus Large Language Models (LLMs) in the retail sector, particularly during standard and promotional sales periods. Utilizing a controlled experimental setup with 123 human forecasters and five LLMs, including ChatGPT4, ChatGPT3.5, Bard, Bing, and Llama2, we evaluated forecasting precision through Mean Absolute Percentage Error. Our analysis centered on the effect of the following factors on forecasters performance: the supporting statistical model (baseline and advanced), whether the product was on promotion, and the nature of external impact. The findings indicate that LLMs do not consistently outperform humans in forecasting accuracy and that advanced statistical forecasting models do not uniformly enhance the performance of either human forecasters or LLMs. Both human and LLM forecasters exhibited increased forecasting errors, particularly during promotional periods and under the influence of positive external impacts. Our findings call for careful consideration when integrating LLMs into practical forecasting processes.

Perception of offensiveness is inherently subjective, shaped by the lived experiences and socio-cultural values of the perceivers. Recent years have seen substantial efforts to build AI-based tools that can detect offensive language at scale, as a means to moderate social media platforms, and to ensure safety of conversational AI technologies such as ChatGPT and Bard. However, existing approaches treat this task as a technical endeavor, built on top of data annotated for offensiveness by a global crowd workforce without any attention to the crowd workers' provenance or the values their perceptions reflect. We argue that cultural and psychological factors play a vital role in the cognitive processing of offensiveness, which is critical to consider in this context. We re-frame the task of determining offensiveness as essentially a matter of moral judgment -- deciding the boundaries of ethically wrong vs. right language within an implied set of socio-cultural norms. Through a large-scale cross-cultural study based on 4309 participants from 21 countries across 8 cultural regions, we demonstrate substantial cross-cultural differences in perceptions of offensiveness. More importantly, we find that individual moral values play a crucial role in shaping these variations: moral concerns about Care and Purity are significant mediating factors driving cross-cultural differences. These insights are of crucial importance as we build AI models for the pluralistic world, where the values they espouse should aim to respect and account for moral values in diverse geo-cultural contexts.

This paper tackles the intricate challenge of improving the quality of nighttime images under hazy and low-light conditions. Overcoming issues including nonuniform illumination glows, texture blurring, glow effects, color distortion, noise disturbance, and overall, low light have proven daunting. Despite the inherent difficulties, this paper introduces a pioneering solution named Nighttime Dehazing, Low-Light Enhancement, and Light Suppression (NDELS). NDELS utilizes a unique network that combines three essential processes to enhance visibility, brighten low-light regions, and effectively suppress glare from bright light sources. In contrast to limited progress in nighttime dehazing, unlike its daytime counterpart, NDELS presents a comprehensive and innovative approach. The efficacy of NDELS is rigorously validated through extensive comparisons with eight state-of-the-art algorithms across four diverse datasets. Experimental results showcase the superior performance of our method, demonstrating its outperformance in terms of overall image quality, including color and edge enhancement. Quantitative (PSNR, SSIM) and qualitative metrics (CLIPIQA, MANIQA, TRES), measure these results.

We introduce AnyHome, a framework that translates open-vocabulary descriptions, ranging from simple labels to elaborate paragraphs, into well-structured and textured 3D indoor scenes at a house-scale. Inspired by cognition theories, AnyHome employs an amodal structured representation to capture 3D spatial cues from textual narratives and then uses egocentric inpainting to enrich these scenes. To this end, we begin by using specially designed template prompts for Large Language Models (LLMs), which enable precise control over the textual input. We then utilize intermediate representations to maintain the spatial structure's consistency, ensuring that the 3D scenes align closely with the textual description. Then, we apply a Score Distillation Sampling process to refine the placement of objects. Lastly, an egocentric inpainting process is incorporated to enhance the realism and appearance of the scenes. AnyHome stands out due to its hierarchical structured representation combined with the versatility of open-vocabulary text interpretation. This allows for extensive customization of indoor scenes at various levels of granularity. We demonstrate that AnyHome can reliably generate a range of diverse indoor scenes, characterized by their detailed spatial structures and textures, all corresponding to the free-form textual inputs.

The expanding application of Artificial Intelligence (AI) in scientific fields presents unprecedented opportunities for discovery and innovation. However, this growth is not without risks. AI models in science, if misused, can amplify risks like creation of harmful substances, or circumvention of established regulations. In this study, we aim to raise awareness of the dangers of AI misuse in science, and call for responsible AI development and use in this domain. We first itemize the risks posed by AI in scientific contexts, then demonstrate the risks by highlighting real-world examples of misuse in chemical science. These instances underscore the need for effective risk management strategies. In response, we propose a system called SciGuard to control misuse risks for AI models in science. We also propose a red-teaming benchmark SciMT-Safety to assess the safety of different systems. Our proposed SciGuard shows the least harmful impact in the assessment without compromising performance in benign tests. Finally, we highlight the need for a multidisciplinary and collaborative effort to ensure the safe and ethical use of AI models in science. We hope that our study can spark productive discussions on using AI ethically in science among researchers, practitioners, policymakers, and the public, to maximize benefits and minimize the risks of misuse.

This approach directly targets and GNNs [30] are a category of artificial neural networks specifically rectifies imbalances at the data level. The proposed framework resolves designed to handle data as graphs. GNNs display remarkable adaptability issues such as neglecting graph structures during data generation in handling highly interconnected data of diverse sizes. This and creating synthetic structures usable with GNN-based classifiers versatility makes them suitable for a broad spectrum of domains in downstream tasks. It processes node and edge information and problem scenarios. Graphs can be categorized as either homogeneous concurrently, improving edge balance through node augmentation or heterogeneous based on the variety of nodes and edges and subgraph sampling. Additionally, our framework integrates a they encompass. Both types have been extensively researched for threshold strategy, aiding in determining optimal edge thresholds homogeneous graphs. Examples include the Graph Convolutional during training without time-consuming parameter adjustments.

Machine learning (ML) has gained significant adoption in Android malware detection to address the escalating threats posed by the rapid proliferation of malware attacks. However, recent studies have revealed the inherent vulnerabilities of ML-based detection systems to evasion attacks. While efforts have been made to address this critical issue, many of the existing defensive methods encounter challenges such as lower effectiveness or reduced generalization capabilities. In this paper, we introduce a novel Android malware detection method, MalPurifier, which exploits adversarial purification to eliminate perturbations independently, resulting in attack mitigation in a light and flexible way. Specifically, MalPurifier employs a Denoising AutoEncoder (DAE)-based purification model to preprocess input samples, removing potential perturbations from them and then leading to correct classification. To enhance defense effectiveness, we propose a diversified adversarial perturbation mechanism that strengthens the purification model against different manipulations from various evasion attacks. We also incorporate randomized "protective noises" onto benign samples to prevent excessive purification. Furthermore, we customize a loss function for improving the DAE model, combining reconstruction loss and prediction loss, to enhance feature representation learning, resulting in accurate reconstruction and classification. Experimental results on two Android malware datasets demonstrate that MalPurifier outperforms the state-of-the-art defenses, and it significantly strengthens the vulnerable malware detector against 37 evasion attacks, achieving accuracies over 90.91%. Notably, MalPurifier demonstrates easy scalability to other detectors, offering flexibility and robustness in its implementation.

This paper introduces RankMatch, an innovative approach for Semi-Supervised Label Distribution Learning (SSLDL). Addressing the challenge of limited labeled data, RankMatch effectively utilizes a small number of labeled examples in conjunction with a larger quantity of unlabeled data, reducing the need for extensive manual labeling in Deep Neural Network (DNN) applications. Specifically, RankMatch introduces an ensemble learning-inspired averaging strategy that creates a pseudo-label distribution from multiple weakly augmented images. This not only stabilizes predictions but also enhances the model's robustness. Beyond this, RankMatch integrates a pairwise relevance ranking (PRR) loss, capturing the complex inter-label correlations and ensuring that the predicted label distributions align with the ground truth. We establish a theoretical generalization bound for RankMatch, and through extensive experiments, demonstrate its superiority in performance against existing SSLDL methods.

Warning: This paper contains content that may be offensive or upsetting. There has been a significant increase in the usage of large language models (LLMs) in various applications, both in their original form and through fine-tuned adaptations. As a result, LLMs have gained popularity and are being widely adopted by a large user community. However, one of the concerns with LLMs is the potential generation of socially biased content. The existing evaluation methods have many constraints, and their results exhibit a limited degree of interpretability. In this work, we propose a bias evaluation framework named GPTBIAS that leverages the high performance of LLMs (e.g., GPT-4 \cite{openai2023gpt4}) to assess bias in models. We also introduce prompts called Bias Attack Instructions, which are specifically designed for evaluating model bias. To enhance the credibility and interpretability of bias evaluation, our framework not only provides a bias score but also offers detailed information, including bias types, affected demographics, keywords, reasons behind the biases, and suggestions for improvement. We conduct extensive experiments to demonstrate the effectiveness and usability of our bias evaluation framework.

Merging models fine-tuned from a common, extensively pre-trained large model but specialized for different tasks has been demonstrated as a cheap and scalable strategy to construct a multi-task model that performs well across diverse tasks. Recent research, exemplified by task arithmetic, highlights that this multi-task model can be derived through arithmetic operations on task vectors. Nevertheless, current merging techniques frequently resolve potential conflicts among parameters from task-specific models by evaluating individual attributes, such as the parameters' magnitude or sign, overlooking their collective impact on the overall functionality of the model. In this work, we propose the CONtinuous relaxation of disCRETE (Concrete) subspace learning method to identify a common low-dimensional subspace and utilize its shared information to track the interference problem without sacrificing much performance. Specifically, we model the problem as a bi-level optimization problem and introduce a meta-learning framework to find the Concrete subspace mask through gradient-based techniques. At the upper level, we focus on learning a shared Concrete mask to identify the subspace, while at the inner level, model merging is performed to maximize the performance of the merged model. We conduct extensive experiments on both vision domain and language domain, and the results demonstrate the effectiveness of our method. The code is available at https://github.com/tanganke/subspace_fusion