Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains. Math Word Problems (MWPs) serve as a crucial benchmark for evaluating LLMs' reasoning abilities. While most research primarily focuses on improving accuracy, it often neglects understanding and addressing the underlying patterns of errors. Current error classification methods rely on static and predefined categories, which limit their ability to capture the full spectrum of error patterns in mathematical reasoning. To enable systematic error analysis, we collect error samples from 15 different LLMs of varying sizes across four distinct MWP datasets using multiple sampling strategies. Based on this extensive collection, we introduce MWPES-300K, a comprehensive dataset containing 304,865 error samples that cover diverse error patterns and reasoning paths. To reduce human bias and enable fine-grained analysis of error patterns, we propose a novel framework for automated dynamic error classification in mathematical reasoning. Experimental results demonstrate that dataset characteristics significantly shape error patterns, which evolve from basic to complex manifestations as model capabilities increase. With deeper insights into error patterns, we propose error-aware prompting that incorporates common error patterns as explicit guidance, leading to significant improvements in mathematical reasoning performance.

Battery-powered mobile devices (e.g., smartphones, AR/VR glasses, and various IoT devices) are increasingly being used for AI training due to their growing computational power and easy access to valuable, diverse, and real-time data. On-device training is highly energy-intensive, making accurate energy consumption estimation crucial for effective job scheduling and sustainable AI. However, the heterogeneity of devices and the complexity of models challenge the accuracy and generalizability of existing estimation methods. This paper proposes THOR, a generic approach for energy consumption estimation in deep neural network (DNN) training. First, we examine the layer-wise energy additivity property of DNNs and strategically partition the entire model into layers for fine-grained energy consumption profiling. Then, we fit Gaussian Process (GP) models to learn from layer-wise energy consumption measurements and estimate a DNN's overall energy consumption based on its layer-wise energy additivity property. We conduct extensive experiments with various types of models across different real-world platforms. The results demonstrate that THOR has effectively reduced the Mean Absolute Percentage Error (MAPE) by up to 30%. Moreover, THOR is applied in guiding energy-aware pruning, successfully reducing energy consumption by 50%, thereby further demonstrating its generality and potential.

Existing research primarily evaluates the values of LLMs by examining their stated inclinations towards specific values. However, the "Value-Action Gap," a phenomenon rooted in environmental and social psychology, reveals discrepancies between individuals' stated values and their actions in real-world contexts. To what extent do LLMs exhibit a similar gap between their stated values and their actions informed by those values? This study introduces ValueActionLens, an evaluation framework to assess the alignment between LLMs' stated values and their value-informed actions. The framework encompasses the generation of a dataset comprising 14.8k value-informed actions across twelve cultures and eleven social topics, and two tasks to evaluate how well LLMs' stated value inclinations and value-informed actions align across three different alignment measures. Extensive experiments reveal that the alignment between LLMs' stated values and actions is sub-optimal, varying significantly across scenarios and models. Analysis of misaligned results identifies potential harms from certain value-action gaps. To predict the value-action gaps, we also uncover that leveraging reasoned explanations improves performance. These findings underscore the risks of relying solely on the LLMs' stated values to predict their behaviors and emphasize the importance of context-aware evaluations of LLM values and value-action gaps.

This study analyzes and predicts air pollution in Asia, focusing on PM 2.5 levels from 2018 to 2023 across five regions: Central, East, South, Southeast, and West Asia. South Asia emerged as the most polluted region, with Bangladesh, India, and Pakistan consistently having the highest PM 2.5 levels and death rates, especially in Nepal, Pakistan, and India. East Asia showed the lowest pollution levels. K-means clustering categorized countries into high, moderate, and low pollution groups. The ARIMA model effectively predicted 2023 PM 2.5 levels (MAE: 3.99, MSE: 33.80, RMSE: 5.81, R: 0.86). The findings emphasize the need for targeted interventions to address severe pollution and health risks in South Asia.

Story understanding and generation have long been a challenging task in natural language processing (NLP), especially when dealing with various levels of instruction specificity. In this paper, we propose a novel approach called "Weak to Strong Instruction Tuning" for improving story generation by tuning models with instructions of varying clarity. We explore the potential of large language models (LLMs) to adapt to different types of instructions, weak and strong, and show that our method significantly enhances performance in story comprehension and generation. By leveraging the strength of instruction tuning, we train models to understand the nuances of story plots, characters, and themes while generating coherent and engaging narratives. Through extensive experiments on several benchmark datasets and comparison with state-of-the-art baselines, we demonstrate that our method outperforms existing techniques, yielding substantial improvements in both automatic evaluation metrics and human evaluations. Our work shows that adaptive instruction tuning can be a powerful tool in refining generative models for complex narrative tasks.

The reasoning abilities of Large Language Models (LLMs) can be improved by structurally denoising their weights, yet existing techniques primarily focus on denoising the feed-forward network (FFN) of the transformer block, and can not efficiently utilise the Multi-head Attention (MHA) block, which is the core of transformer architectures. To address this issue, we propose a novel intuitive framework that, at its very core, performs MHA compression through a multi-head tensorisation process and the Tucker decomposition. This enables both higher-dimensional structured denoising and compression of the MHA weights, by enforcing a shared higher-dimensional subspace across the weights of the multiple attention heads. We demonstrate that this approach consistently enhances the reasoning capabilities of LLMs across multiple benchmark datasets, and for both encoder-only and decoder-only architectures, while achieving compression rates of up to $\sim 250$ times in the MHA weights, all without requiring any additional data, training, or fine-tuning. Furthermore, we show that the proposed method can be seamlessly combined with existing FFN-only-based denoising techniques to achieve further improvements in LLM reasoning performance.

Artificial intelligence (AI) has potential to revolutionize the field of oncology by enhancing the precision of cancer diagnosis, optimizing treatment strategies, and personalizing therapies for a variety of cancers. This review examines the limitations of conventional diagnostic techniques and explores the transformative role of AI in diagnosing and treating cancers such as lung, breast, colorectal, liver, stomach, esophageal, cervical, thyroid, prostate, and skin cancers. The primary objective of this paper is to highlight the significant advancements that AI algorithms have brought to oncology within the medical industry. By enabling early cancer detection, improving diagnostic accuracy, and facilitating targeted treatment delivery, AI contributes to substantial improvements in patient outcomes. The integration of AI in medical imaging, genomic analysis, and pathology enhances diagnostic precision and introduces a novel, less invasive approach to cancer screening. This not only boosts the effectiveness of medical facilities but also reduces operational costs. The study delves into the application of AI in radiomics for detailed cancer characterization, predictive analytics for identifying associated risks, and the development of algorithm-driven robots for immediate diagnosis. Furthermore, it investigates the impact of AI on addressing healthcare challenges, particularly in underserved and remote regions. The overarching goal of this platform is to support the development of expert recommendations and to provide universal, efficient diagnostic procedures. By reviewing existing research and clinical studies, this paper underscores the pivotal role of AI in improving the overall cancer care system. It emphasizes how AI-enabled systems can enhance clinical decision-making and expand treatment options, thereby underscoring the importance of AI in advancing precision oncology

Convolutional Neural Networks (CNNs) are pivotal in image classification tasks due to their robust feature extraction capabilities. However, their high computational and memory requirements pose challenges for deployment in resource-constrained environments. This paper introduces a methodology to construct lightweight CNNs while maintaining competitive accuracy. The approach integrates two stages of training; dual-input-output model and transfer learning with progressive unfreezing. The dual-input-output model train on original and augmented datasets, enhancing robustness. Progressive unfreezing is applied to the unified model to optimize pre-learned features during fine-tuning, enabling faster convergence and improved model accuracy. The methodology was evaluated on three benchmark datasets; handwritten digit MNIST, fashion MNIST, and CIFAR-10. The proposed model achieved a state-of-the-art accuracy of 99% on the handwritten digit MNIST and 89% on fashion MNIST, with only 14,862 parameters and a model size of 0.17 MB. While performance on CIFAR-10 was comparatively lower (65% with less than 20,00 parameters), the results highlight the scalability of this method. The final model demonstrated fast inference times and low latency, making it suitable for real-time applications. Future directions include exploring advanced augmentation techniques, improving architectural scalability for complex datasets, and extending the methodology to tasks beyond classification. This research underscores the potential for creating efficient, scalable, and task-specific CNNs for diverse applications.

Mechanistic interpretability is the program of explaining what AI systems are doing in terms of their internal mechanisms. I analyze some aspects of the program, along with setting out some concrete challenges and assessing progress to date. I argue for the importance of propositional interpretability, which involves interpreting a system's mechanisms and behavior in terms of propositional attitudes: attitudes (such as belief, desire, or subjective probability) to propositions (e.g. the proposition that it is hot outside). Propositional attitudes are the central way that we interpret and explain human beings and they are likely to be central in AI too. A central challenge is what I call thought logging: creating systems that log all of the relevant propositional attitudes in an AI system over time. I examine currently popular methods of interpretability (such as probing, sparse auto-encoders, and chain of thought methods) as well as philosophical methods of interpretation (including those grounded in psychosemantics) to assess their strengths and weaknesses as methods of propositional interpretability.

Dozens of patients have been killed in a drone attack on one of the last functioning hospitals in el-Fasher in Sudan's Darfur region. While it was not immediately clear who targeted the Saudi Hospital on Friday, medical sources quoted by AFP news agency said the same building was hit by a Rapid Support Forces (RSF) drone "a few weeks ago". Friday's attack killed at least 30 patients in the emergency department, the report added. Regional governor Mini Minawi posted graphic images of bloodied bodies on his X account on Saturday, saying that the attack "exterminated" more than 70 patients, including women and children. The Sudanese army has been at war with the paramilitary RSF, who have seized nearly the entire vast western region of Darfur, since April 2023.