Compositional generalization is an important ability of language models and has many different manifestations. For data-to-text generation, previous research on this ability is limited to a single manifestation called Systematicity and lacks consideration of large language models (LLMs), which cannot fully cover practical application scenarios. In this work, we propose SPOR, a comprehensive and practical evaluation method for compositional generalization in data-to-text generation. SPOR includes four aspects of manifestations (Systematicity, Productivity, Order invariance, and Rule learnability) and allows high-quality evaluation without additional manual annotations based on existing datasets. We demonstrate SPOR on two different datasets and evaluate some existing language models including LLMs. We find that the models are deficient in various aspects of the evaluation and need further improvement. Our work shows the necessity for comprehensive research on different manifestations of compositional generalization in data-to-text generation and provides a framework for evaluation.

Natural language processing (NLP) has grown significantly since the advent of the Transformer architecture. Transformers have given birth to pre-trained large language models (PLMs). There has been tremendous improvement in the performance of NLP systems across several tasks. NLP systems are on par or, in some cases, better than humans at accomplishing specific tasks. However, it remains the norm that \emph{better quality datasets at the time of pretraining enable PLMs to achieve better performance, regardless of the task.} The need to have quality datasets has prompted NLP researchers to continue creating new datasets to satisfy particular needs. For example, the two top NLP conferences, ACL and EMNLP, accepted ninety-two papers in 2022, introducing new datasets. This work aims to uncover the trends and insights mined within these datasets. Moreover, we provide valuable suggestions to researchers interested in curating datasets in the future.

Robust optimisation is a well-established framework for optimising functions in the presence of uncertainty. The inherent goal of this problem is to identify a collection of inputs whose outputs are both desirable for the decision maker, whilst also being robust to the underlying uncertainties in the problem. In this work, we study the multi-objective case of this problem. We identify that the majority of all robust multi-objective algorithms rely on two key operations: robustification and scalarisation. Robustification refers to the strategy that is used to account for the uncertainty in the problem. Scalarisation refers to the procedure that is used to encode the relative importance of each objective to a scalar-valued reward. As these operations are not necessarily commutative, the order that they are performed in has an impact on the resulting solutions that are identified and the final decisions that are made. The purpose of this work is to give a thorough exposition on the effects of these different orderings and in particular highlight when one should opt for one ordering over the other. As part of our analysis, we showcase how many existing risk concepts can be integrated into the specification and solution of a robust multi-objective optimisation problem. Besides this, we also demonstrate how one can principally define the notion of a robust Pareto front and a robust performance metric based on our ``robustify and scalarise'' methodology. To illustrate the efficacy of these new ideas, we present two insightful case studies which are based on real-world data sets.

Differential Privacy (DP) is the current gold-standard for measuring privacy. Estimation problems under DP constraints appearing in the literature have largely focused on providing equal privacy to all users. We consider the problems of empirical mean estimation for univariate data and frequency estimation for categorical data, two pillars of data analysis in the industry, subject to heterogeneous privacy constraints. Each user, contributing a sample to the dataset, is allowed to have a different privacy demand. The dataset itself is assumed to be worst-case and we study both the problems in two different formulations -- the correlated and the uncorrelated setting. In the former setting, the privacy demand and the user data can be arbitrarily correlated while in the latter setting, there is no correlation between the dataset and the privacy demand. We prove some optimality results, under both PAC error and mean-squared error, for our proposed algorithms and demonstrate superior performance over other baseline techniques experimentally.

A squad of soldiers is under attack and pinned down by rockets in the close quarters of urban combat. One of them makes a call over his radio, and within moments a fleet of small autonomous drones equipped with explosives fly through the town square, entering buildings and scanning for enemies before detonating on command. One by one the suicide drones seek out and kill their targets. A voiceover on the video, a fictional ad for multibillion-dollar Israeli weapons company Elbit Systems, touts the AI-enabled drones' ability to "maximize lethality and combat tempo". While defense companies like Elbit promote their new advancements in artificial intelligence (AI) with sleek dramatizations, the technology they are developing is increasingly entering the real world.

Hand hygiene is one of the most efficient daily actions to prevent infectious diseases, such as Influenza, Malaria, and skin infections. We have been suggested to wash our hands under professional guidelines to prevent virus infection. However, several surveys show that very few people follow this suggestion. Thus we propose UWash, a wearable solution with smartwatches, to assess handwashing procedures for the purpose of raising users' awareness and cultivating habits of high-quality handwashing. We address the task of handwashing assessment from readings of motion sensors similar to the action segmentation problem in computer vision, and propose a simple and lightweight two-stream UNet-like network to achieve it effectively. Experiments over 51 subjects show that UWash achieves an accuracy of 92.27% on handwashing gesture recognition, <0.5 seconds error on onset/offset detection, and <5 points error on gesture scoring in the user-dependent setting, and keeps promising in the user-independent evaluation and the user-independent-location-independent evaluation. UWash even performs well on 10 random passersby in a hospital 9 months later. UWash is the first work that scores the handwashing quality by gesture sequences and is instructive to guide users in promoting hand hygiene in daily life. Code and data are avaliable at https://github.com/aiotgroup/UWash

Direct Preference Optimization (DPO) has proven effective at improving the performance of large language models (LLMs) on downstream tasks such as reasoning and alignment. In this work, we propose Step-Controlled DPO (SCDPO), a method for automatically providing stepwise error supervision by creating negative samples of mathematical reasoning rationales that start making errors at a specified step. By applying these samples in DPO training, SCDPO can better align the model to understand reasoning errors and output accurate reasoning steps. We apply SCDPO to both code-integrated and chain-of-thought solutions, empirically showing that it consistently improves the performance compared to naive DPO on three different SFT models, including one existing SFT model and two models we finetuned. Qualitative analysis of the credit assignment of SCDPO and DPO demonstrates the effectiveness of SCDPO at identifying errors in mathematical solutions. We then apply SCDPO to an InternLM2-20B model, resulting in a 20B model that achieves high scores of 88.5% on GSM8K and 58.1% on MATH, rivaling all other open-source LLMs, showing the great potential of our method.

In the architecture of deep learning models, inspired by biological neurons, activation functions (AFs) play a pivotal role. They significantly influence the performance of artificial neural networks. By modulating the non-linear properties essential for learning complex patterns, AFs are fundamental in both classification and regression tasks. This paper presents a comprehensive review of various types of AFs, including fixed-shape, parametric, adaptive, stochastic/probabilistic, non-standard, and ensemble/combining types. We begin with a systematic taxonomy and detailed classification frameworks that delineates the principal characteristics of AFs and organizes them based on their structural and functional distinctions. Our in-depth analysis covers primary groups such as sigmoid-based, ReLU-based, and ELU-based AFs, discussing their theoretical foundations, mathematical formulations, and specific benefits and limitations in different contexts. We also highlight key attributes of AFs such as output range, monotonicity, and smoothness. Furthermore, we explore miscellaneous AFs that do not conform to these categories but have shown unique advantages in specialized applications. Non-standard AFs are also explored, showcasing cutting-edge variations that challenge traditional paradigms and offer enhanced adaptability and model performance. We examine strategies for combining multiple AFs to leverage complementary properties. The paper concludes with a comparative evaluation of 12 state-of-the-art AFs, using rigorous statistical and experimental methodologies to assess their efficacy. This analysis not only aids practitioners in selecting and designing the most appropriate AFs for their specific deep learning tasks but also encourages continued innovation in AF development within the machine learning community.

Aspect-based sentiment Analysis (ABSA) identifies and evaluates sentiments toward specific aspects of entities within text, providing detailed insights beyond overall sentiment. However, Attention mechanisms and neural network models struggle with syntactic constraints, and the quadratic complexity of attention mechanisms hinders their adoption for capturing long-range dependencies between aspect and opinion words in ABSA. This complexity can lead to the misinterpretation of irrelevant con-textual words, restricting their effectiveness to short-range dependencies. Some studies have investigated merging semantic and syntactic approaches but face challenges in effectively integrating these methods. To address the above problems, we present MambaForGCN, a novel approach to enhance short and long-range dependencies between aspect and opinion words in ABSA. This innovative approach incorporates syntax-based Graph Convolutional Network (SynGCN) and MambaFormer (Mamba-Transformer) modules to encode input with dependency relations and semantic information. The Multihead Attention (MHA) and Mamba blocks in the MambaFormer module serve as channels to enhance the model with short and long-range dependencies between aspect and opinion words. We also introduce the Kolmogorov-Arnold Networks (KANs) gated fusion, an adaptively integrated feature representation system combining SynGCN and MambaFormer representations. Experimental results on three benchmark datasets demonstrate MambaForGCN's effectiveness, outperforming state-of-the-art (SOTA) baseline models.

Large Language Models (LLMs) have demonstrated exceptional proficiency in mathematical reasoning tasks due to their extensive parameter counts and training on vast datasets. Despite these capabilities, deploying LLMs is hindered by their computational demands. Distilling LLM mathematical reasoning into Smaller Language Models (SLMs) has emerged as a solution to this challenge, although these smaller models often suffer from errors in calculation and semantic understanding. Prior work has proposed Program-of-Thought Distillation (PoTD) to avoid calculation error. To further address semantic understanding errors, we propose Key-Point-Driven Mathematical Reasoning Distillation (KPDD). KPDD enhances the reasoning performance of SLMs by breaking down the problem-solving process into three stages: Core Question Extraction, Problem-Solving Information Extraction, and Step-by-Step Solution. This method is further divided into KPDD-CoT, which generates Chain-of-Thought rationales, and KPDD-PoT, which creates Program-of-Thought rationales. The experiment results show that KPDD-CoT significantly improves reasoning abilities, while KPDD-PoT achieves state-of-the-art performance in mathematical reasoning tasks. Our approach effectively mitigates misunderstanding errors, advancing the deployment of efficient and capable SLMs.