Data contamination has garnered increased attention in the era of large language models (LLMs) due to the reliance on extensive internet-derived training corpora. The issue of training corpus overlap with evaluation benchmarks--referred to as contamination--has been the focus of significant recent research. This body of work aims to identify contamination, understand its impacts, and explore mitigation strategies from diverse perspectives. However, comprehensive studies that provide a clear pathway from foundational concepts to advanced insights are lacking in this nascent field. Therefore, we present a comprehensive survey in the field of data contamination, laying out the key issues, methodologies, and findings to date, and highlighting areas in need of further research and development. In particular, we begin by examining the effects of data contamination across various stages and forms. We then provide a detailed analysis of current contamination detection methods, categorizing them to highlight their focus, assumptions, strengths, and limitations. We also discuss mitigation strategies, offering a clear guide for future research. This survey serves as a succinct overview of the most recent advancements in data contamination research, providing a straightforward guide for the benefit of future research endeavors.

The rapid growth in the size of deep learning models strains the capabilities of traditional dense computation paradigms. Leveraging sparse computation has become increasingly popular for training and deploying large-scale models, but existing deep learning frameworks lack extensive support for sparse operations. To bridge this gap, we introduce Scorch, a library that seamlessly integrates efficient sparse tensor computation into the PyTorch ecosystem, with an initial focus on inference workloads on CPUs. Scorch provides a flexible and intuitive interface for sparse tensors, supporting diverse sparse data structures. Scorch introduces a compiler stack that automates key optimizations, including automatic loop ordering, tiling, and format inference. Combined with a runtime that adapts its execution to both dense and sparse data, Scorch delivers substantial speedups over hand-written PyTorch Sparse (torch.sparse) operations without sacrificing usability. More importantly, Scorch enables efficient computation of complex sparse operations that lack hand-optimized PyTorch implementations. This flexibility is crucial for exploring novel sparse architectures. We demonstrate Scorch's ease of use and performance gains on diverse deep learning models across multiple domains. With only minimal code changes, Scorch achieves 1.05-5.78x speedups over PyTorch Sparse on end-to-end tasks. Scorch's seamless integration and performance gains make it a valuable addition to the PyTorch ecosystem. We believe Scorch will enable wider exploration of sparsity as a tool for scaling deep learning and inform the development of other sparse libraries.

Real-world KBQA applications require models that are (1) robust -- e.g., can differentiate between answerable and unanswerable questions, and (2) low-resource -- do not require large training data. Towards this goal, we propose the novel task of few-shot transfer for KBQA with unanswerable questions. We present FUn-FuSIC that extends the state-of-the-art (SoTA) few-shot transfer model for answerable-only KBQA to handle unanswerability. It iteratively prompts an LLM to generate logical forms for the question by providing feedback using a diverse suite of syntactic, semantic and execution guided checks, and adapts self-consistency to assess confidence of the LLM to decide answerability. Experiments over newly constructed datasets show that FUn-FuSIC outperforms suitable adaptations of the SoTA model for KBQA with unanswerability, and the SoTA model for answerable-only few-shot-transfer KBQA.

Large language models (LLMs) are increasingly being used in human-centered social scientific tasks, such as data annotation, synthetic data creation, and engaging in dialog. However, these tasks are highly subjective and dependent on human factors, such as one's environment, attitudes, beliefs, and lived experiences. Thus, employing LLMs (which do not have such human factors) in these tasks may result in a lack of variation in data, failing to reflect the diversity of human experiences. In this paper, we examine the role of prompting LLMs with human-like personas and asking the models to answer as if they were a specific human. This is done explicitly, with exact demographics, political beliefs, and lived experiences, or implicitly via names prevalent in specific populations. The LLM personas are then evaluated via (1) subjective annotation task (e.g., detecting toxicity) and (2) a belief generation task, where both tasks are known to vary across human factors. We examine the impact of explicit vs. implicit personas and investigate which human factors LLMs recognize and respond to. Results show that LLM personas show mixed results when reproducing known human biases, but generate generally fail to demonstrate implicit biases. We conclude that LLMs lack the intrinsic cognitive mechanisms of human thought, while capturing the statistical patterns of how people speak, which may restrict their effectiveness in complex social science applications.

Correctly capturing the symmetry transformations of data can lead to efficient models with strong generalization capabilities, though methods incorporating symmetries often require prior knowledge. While recent advancements have been made in learning those symmetries directly from the dataset, most of this work has focused on the discriminative setting. In this paper, we take inspiration from group theoretic ideas to construct a generative model that explicitly aims to capture the data's approximate symmetries. This results in a model that, given a prespecified broad set of possible symmetries, learns to what extent, if at all, those symmetries are actually present. Our model can be seen as a generative process for data augmentation. We provide a simple algorithm for learning our generative model and empirically demonstrate its ability to capture symmetries under affine and color transformations, in an interpretable way. Combining our symmetry model with standard generative models results in higher marginal test-log-likelihoods and improved data efficiency.

Developing human activity recognition (HAR) systems for smart homes is not straightforward due to varied layouts of the homes and their personalized settings, as well as idiosyncratic behaviors of residents. As such, off-the-shelf HAR systems are effective in limited capacity for an individual home, and HAR systems often need to be derived "from scratch", which comes with substantial efforts and often is burdensome to the resident. Previous work has successfully targeted the initial phase. At the end of this initial phase, we identify seed points. We build on bootstrapped HAR systems and introduce an effective updating and extension procedure for continuous improvement of HAR systems with the aim of keeping up with ever changing life circumstances. Our method makes use of the seed points identified at the end of the initial bootstrapping phase. A contrastive learning framework is trained using these seed points and labels obtained for the same. This model is then used to improve the segmentation accuracy of the identified prominent activities. Improvements in the activity recognition system through this procedure help model the majority of the routine activities in the smart home. We demonstrate the effectiveness of our procedure through experiments on the CASAS datasets that show the practical value of our approach.

Persona assignment has become a common strategy for customizing LLM use to particular tasks and contexts. In this study, we explore how perceptions of different nations change when LLMs are assigned specific nationality personas. We assign 193 different nationality personas (e.g., an American person) to four LLMs and examine how the LLM perceptions of countries change. We find that all LLM-persona combinations tend to favor Western European nations, though nation-personas push LLM behaviors to focus more on and view more favorably the nation-persona's own region. Eastern European, Latin American, and African nations are viewed more negatively by different nationality personas. Our study provides insight into how biases and stereotypes are realized within LLMs when adopting different national personas. In line with the "Blueprint for an AI Bill of Rights", our findings underscore the critical need for developing mechanisms to ensure LLMs uphold fairness and not over-generalize at a global scale.

Formal verification (FV) has witnessed growing significance with current emerging program synthesis by the evolving large language models (LLMs). However, current formal verification mainly resorts to symbolic verifiers or hand-craft rules, resulting in limitations for extensive and flexible verification. On the other hand, formal languages for automated theorem proving, such as Isabelle, as another line of rigorous verification, are maintained with comprehensive rules and theorems. In this paper, we propose FVEL, an interactive Formal Verification Environment with LLMs. Specifically, FVEL transforms a given code to be verified into Isabelle, and then conducts verification via neural automated theorem proving with an LLM. The joined paradigm leverages the rigorous yet abundant formulated and organized rules in Isabelle and is also convenient for introducing and adjusting cutting-edge LLMs. To achieve this goal, we extract a large-scale FVELER3. The FVELER dataset includes code dependencies and verification processes that are formulated in Isabelle, containing 758 theories, 29,125 lemmas, and 200,646 proof steps in total with in-depth dependencies. We benchmark FVELER in the FVEL environment by first fine-tuning LLMs with FVELER and then evaluating them on Code2Inv and SV-COMP. The results show that FVEL with FVELER fine-tuned Llama3- 8B solves 17.39% (69 -> 81) more problems, and Mistral-7B 12% (75 -> 84) more problems in SV-COMP. And the proportion of proof errors is reduced. Project page: https://fveler.github.io/.

State-of-the-art trainable machine translation evaluation metrics like xCOMET achieve high correlation with human judgment but rely on large encoders (up to 10.7B parameters), making them computationally expensive and inaccessible to researchers with limited resources. To address this issue, we investigate whether the knowledge stored in these large encoders can be compressed while maintaining quality. We employ distillation, quantization, and pruning techniques to create efficient xCOMET alternatives and introduce a novel data collection pipeline for efficient black-box distillation. Our experiments show that, using quantization, xCOMET can be compressed up to three times with no quality degradation. Additionally, through distillation, we create an xCOMET-lite metric, which has only 2.6% of xCOMET-XXL parameters, but retains 92.1% of its quality. Besides, it surpasses strong small-scale metrics like COMET-22 and BLEURT-20 on the WMT22 metrics challenge dataset by 6.4%, despite using 50% fewer parameters. All code, dataset, and models are available online.

Adversarial examples pose a security threat to many critical systems built on neural networks. While certified training improves robustness, it also decreases accuracy noticeably. Despite various proposals for addressing this issue, the significant accuracy drop remains. More importantly, it is not clear whether there is a certain fundamental limit on achieving robustness whilst maintaining accuracy. In this work, we offer a novel perspective based on Bayes errors. By adopting Bayes error to robustness analysis, we investigate the limit of certified robust accuracy, taking into account data distribution uncertainties. We first show that the accuracy inevitably decreases in the pursuit of robustness due to changed Bayes error in the altered data distribution. Subsequently, we establish an upper bound for certified robust accuracy, considering the distribution of individual classes and their boundaries. Our theoretical results are empirically evaluated on real-world datasets and are shown to be consistent with the limited success of existing certified training results, e.g., for CIFAR10, our analysis results in an upper bound (of certified robust accuracy) of 67.49\%, meanwhile existing approaches are only able to increase it from 53.89\% in 2017 to 62.84\% in 2023.