This research delves into the current literature on bias in Natural Language Processing Models and the techniques proposed to mitigate the problem of bias, including why it is important to tackle bias in the first place. Additionally, these techniques are further analysed in the light of newly developed models that tower in size over past editions. To achieve those aims, the authors of this paper conducted their research on GPT3 by OpenAI, the largest NLP model available to consumers today. With 175 billion parameters in contrast to BERTs 340 million, GPT3 is the perfect model to test the common pitfalls of NLP models. Tests were conducted through the development of an Applicant Tracking System using GPT3. For the sake of feasibility and time constraints, the tests primarily focused on gender bias, rather than all or multiple types of bias. Finally, current mitigation techniques are considered and tested to measure their degree of functionality.
相關內容
Multimodal datasets are a critical component in recent breakthroughs such as Stable Diffusion and GPT-4, yet their design does not receive the same research attention as model architectures or training algorithms. To address this shortcoming in the ML ecosystem, we introduce DataComp, a testbed for dataset experiments centered around a new candidate pool of 12.8 billion image-text pairs from Common Crawl. Participants in our benchmark design new filtering techniques or curate new data sources and then evaluate their new dataset by running our standardized CLIP training code and testing the resulting model on 38 downstream test sets. Our benchmark consists of multiple compute scales spanning four orders of magnitude, which enables the study of scaling trends and makes the benchmark accessible to researchers with varying resources. Our baseline experiments show that the DataComp workflow leads to better training sets. In particular, our best baseline, DataComp-1B, enables training a CLIP ViT-L/14 from scratch to 79.2% zero-shot accuracy on ImageNet, outperforming OpenAI's CLIP ViT-L/14 by 3.7 percentage points while using the same training procedure and compute. We release DataComp and all accompanying code at www.datacomp.ai.
The rapid growth of decentralized digital currencies, enabled by blockchain technology, has ushered in a new era of peer-to-peer transactions, revolutionizing the global economy. Cryptocurrency wallets, serving as crucial endpoints for these transactions, have become increasingly prevalent. However, the escalating value and usage of these wallets also expose them to significant security risks and challenges. This research aims to comprehensively explore the security aspects of cryptocurrency wallets. It provides a taxonomy of wallet types, analyzes their design and implementation, identifies common vulnerabilities and attacks, and discusses defense mechanisms and mitigation strategies. The taxonomy covers custodial, non-custodial, hot, and cold wallets, highlighting their unique characteristics and associated security considerations. The security analysis scrutinizes the theoretical and practical aspects of wallet design, while assessing the efficacy of existing security measures and protocols. Notable wallet attacks, such as Binance, Mt. Gox are examined to understand their causes and consequences. Furthermore, the paper surveys defense mechanisms, transaction monitoring, evaluating their effectiveness in mitigating threats.
Chain-of-thought (CoT) prompting has been shown to empirically improve the accuracy of large language models (LLMs) on various question answering tasks. While understanding why CoT prompting is effective is crucial to ensuring that this phenomenon is a consequence of desired model behavior, little work has addressed this; nonetheless, such an understanding is a critical prerequisite for responsible model deployment. We address this question by leveraging gradient-based feature attribution methods which produce saliency scores that capture the influence of input tokens on model output. Specifically, we probe several open-source LLMs to investigate whether CoT prompting affects the relative importances they assign to particular input tokens. Our results indicate that while CoT prompting does not increase the magnitude of saliency scores attributed to semantically relevant tokens in the prompt compared to standard few-shot prompting, it increases the robustness of saliency scores to question perturbations and variations in model output.
Many automated test generation techniques have been developed to aid developers with writing tests. To facilitate full automation, most existing techniques aim to either increase coverage, or generate exploratory inputs. However, existing test generation techniques largely fall short of achieving more semantic objectives, such as generating tests to reproduce a given bug report. Reproducing bugs is nonetheless important, as our empirical study shows that the number of tests added in open source repositories due to issues was about 28% of the corresponding project test suite size. Meanwhile, due to the difficulties of transforming the expected program semantics in bug reports into test oracles, existing failure reproduction techniques tend to deal exclusively with program crashes, a small subset of all bug reports. To automate test generation from general bug reports, we propose LIBRO, a framework that uses Large Language Models (LLMs), which have been shown to be capable of performing code-related tasks. Since LLMs themselves cannot execute the target buggy code, we focus on post-processing steps that help us discern when LLMs are effective, and rank the produced tests according to their validity. Our evaluation of LIBRO shows that, on the widely studied Defects4J benchmark, LIBRO can generate failure reproducing test cases for 33% of all studied cases (251 out of 750), while suggesting a bug reproducing test in first place for 149 bugs. To mitigate data contamination, we also evaluate LIBRO against 31 bug reports submitted after the collection of the LLM training data terminated: LIBRO produces bug reproducing tests for 32% of the studied bug reports. Overall, our results show LIBRO has the potential to significantly enhance developer efficiency by automatically generating tests from bug reports.
Network operators and researchers frequently use Internet measurement platforms (IMPs), such as RIPE Atlas, RIPE RIS, or RouteViews for, e.g., monitoring network performance, detecting routing events, topology discovery, or route optimization. To interpret the results of their measurements and avoid pitfalls or wrong generalizations, users must understand a platform's limitations. To this end, this paper studies an important limitation of IMPs, the \textit{bias}, which exists due to the non-uniform deployment of the vantage points. Specifically, we introduce a generic framework to systematically and comprehensively quantify the multi-dimensional (e.g., across location, topology, network types, etc.) biases of IMPs. Using the framework and open datasets, we perform a detailed analysis of biases in IMPs that confirms well-known (to the domain experts) biases and sheds light on less-known or unexplored biases. To facilitate IMP users to obtain awareness of and explore bias in their measurements, as well as further research and analyses (e.g., methods for mitigating bias), we publicly share our code and data, and provide online tools (API, Web app, etc.) that calculate and visualize the bias in measurement setups.
Deep learning has been rapidly employed in many applications revolutionizing many industries, but it is known to be vulnerable to adversarial attacks. Such attacks pose a serious threat to deep learning-based systems compromising their integrity, reliability, and trust. Interpretable Deep Learning Systems (IDLSes) are designed to make the system more transparent and explainable, but they are also shown to be susceptible to attacks. In this work, we propose a novel microbial genetic algorithm-based black-box attack against IDLSes that requires no prior knowledge of the target model and its interpretation model. The proposed attack is a query-efficient approach that combines transfer-based and score-based methods, making it a powerful tool to unveil IDLS vulnerabilities. Our experiments of the attack show high attack success rates using adversarial examples with attribution maps that are highly similar to those of benign samples which makes it difficult to detect even by human analysts. Our results highlight the need for improved IDLS security to ensure their practical reliability.
This paper presents a comprehensive and practical guide for practitioners and end-users working with Large Language Models (LLMs) in their downstream natural language processing (NLP) tasks. We provide discussions and insights into the usage of LLMs from the perspectives of models, data, and downstream tasks. Firstly, we offer an introduction and brief summary of current GPT- and BERT-style LLMs. Then, we discuss the influence of pre-training data, training data, and test data. Most importantly, we provide a detailed discussion about the use and non-use cases of large language models for various natural language processing tasks, such as knowledge-intensive tasks, traditional natural language understanding tasks, natural language generation tasks, emergent abilities, and considerations for specific tasks.We present various use cases and non-use cases to illustrate the practical applications and limitations of LLMs in real-world scenarios. We also try to understand the importance of data and the specific challenges associated with each NLP task. Furthermore, we explore the impact of spurious biases on LLMs and delve into other essential considerations, such as efficiency, cost, and latency, to ensure a comprehensive understanding of deploying LLMs in practice. This comprehensive guide aims to provide researchers and practitioners with valuable insights and best practices for working with LLMs, thereby enabling the successful implementation of these models in a wide range of NLP tasks. A curated list of practical guide resources of LLMs, regularly updated, can be found at \url{//github.com/Mooler0410/LLMsPracticalGuide}.
Over the past few years, the rapid development of deep learning technologies for computer vision has greatly promoted the performance of medical image segmentation (MedISeg). However, the recent MedISeg publications usually focus on presentations of the major contributions (e.g., network architectures, training strategies, and loss functions) while unwittingly ignoring some marginal implementation details (also known as "tricks"), leading to a potential problem of the unfair experimental result comparisons. In this paper, we collect a series of MedISeg tricks for different model implementation phases (i.e., pre-training model, data pre-processing, data augmentation, model implementation, model inference, and result post-processing), and experimentally explore the effectiveness of these tricks on the consistent baseline models. Compared to paper-driven surveys that only blandly focus on the advantages and limitation analyses of segmentation models, our work provides a large number of solid experiments and is more technically operable. With the extensive experimental results on both the representative 2D and 3D medical image datasets, we explicitly clarify the effect of these tricks. Moreover, based on the surveyed tricks, we also open-sourced a strong MedISeg repository, where each of its components has the advantage of plug-and-play. We believe that this milestone work not only completes a comprehensive and complementary survey of the state-of-the-art MedISeg approaches, but also offers a practical guide for addressing the future medical image processing challenges including but not limited to small dataset learning, class imbalance learning, multi-modality learning, and domain adaptation. The code has been released at: //github.com/hust-linyi/MedISeg
Current deep learning research is dominated by benchmark evaluation. A method is regarded as favorable if it empirically performs well on the dedicated test set. This mentality is seamlessly reflected in the resurfacing area of continual learning, where consecutively arriving sets of benchmark data are investigated. The core challenge is framed as protecting previously acquired representations from being catastrophically forgotten due to the iterative parameter updates. However, comparison of individual methods is nevertheless treated in isolation from real world application and typically judged by monitoring accumulated test set performance. The closed world assumption remains predominant. It is assumed that during deployment a model is guaranteed to encounter data that stems from the same distribution as used for training. This poses a massive challenge as neural networks are well known to provide overconfident false predictions on unknown instances and break down in the face of corrupted data. In this work we argue that notable lessons from open set recognition, the identification of statistically deviating data outside of the observed dataset, and the adjacent field of active learning, where data is incrementally queried such that the expected performance gain is maximized, are frequently overlooked in the deep learning era. Based on these forgotten lessons, we propose a consolidated view to bridge continual learning, active learning and open set recognition in deep neural networks. Our results show that this not only benefits each individual paradigm, but highlights the natural synergies in a common framework. We empirically demonstrate improvements when alleviating catastrophic forgetting, querying data in active learning, selecting task orders, while exhibiting robust open world application where previously proposed methods fail.
We propose a novel approach to multimodal sentiment analysis using deep neural networks combining visual analysis and natural language processing. Our goal is different than the standard sentiment analysis goal of predicting whether a sentence expresses positive or negative sentiment; instead, we aim to infer the latent emotional state of the user. Thus, we focus on predicting the emotion word tags attached by users to their Tumblr posts, treating these as "self-reported emotions." We demonstrate that our multimodal model combining both text and image features outperforms separate models based solely on either images or text. Our model's results are interpretable, automatically yielding sensible word lists associated with emotions. We explore the structure of emotions implied by our model and compare it to what has been posited in the psychology literature, and validate our model on a set of images that have been used in psychology studies. Finally, our work also provides a useful tool for the growing academic study of images - both photographs and memes - on social networks.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191