Extensive work has been devoted to improving the safety mechanism of Large Language Models (LLMs). However, in specific scenarios, LLMs still generate harmful responses when faced with malicious instructions, a phenomenon referred to as "Jailbreak Attack". In our research, we introduce a novel jailbreak attack method (\textbf{RADIAL}), which consists of two steps: 1) Inherent Response Tendency Analysis: we analyze the inherent affirmation and rejection tendency of LLMs to react to real-world instructions. 2) Real-World Instructions-Driven Jailbreak: based on our analysis, we strategically choose several real-world instructions and embed malicious instructions into them to amplify the LLM's potential to generate harmful responses. On three open-source human-aligned LLMs, our method achieves excellent jailbreak attack performance for both Chinese and English malicious instructions. Besides, we guided detailed ablation experiments and verified the effectiveness of our core idea "Inherent Response Tendency Analysis". Our exploration also exposes the vulnerability of LLMs to being induced into generating more detailed harmful responses in subsequent rounds of dialogue.
相關內容
CONTEXT The R programming language has a huge and active community, especially in the area of statistical computing. Its interpreted nature allows for several interesting constructs, like the manipulation of functions at run-time, that hinder the static analysis of R programs. At the same time, there is a lack of existing research regarding how these features, or even the R language as a whole are used in practice. OBJECTIVE In this paper, we conduct a large-scale, static analysis of more than 50 million lines of real-world R programs and packages to identify their characteristics and the features that are actually used. Moreover, we compare the similarities and differences between the scripts of R users and the implementations of package authors. We provide insights for static analysis tools like the lintr package as well as potential interpreter optimizations and uncover areas for future research. METHOD We analyze 4230 R scripts submitted alongside publications and the sources of 19450 CRAN packages for over 350000 R files, collecting and summarizing quantitative information for features of interest. RESULTS We find a high frequency of name-based indexing operations, assignments, and loops, but a low frequency for most of R's reflective functions. Furthermore, we find neither testing functions nor many calls to R's foreign function interface (FFI) in the publication submissions. CONCLUSION R scripts and package sources differ, for example, in their size, the way they include other packages, and their usage of R's reflective capabilities. We provide features that are used frequently and should be prioritized by static analysis tools, like operator assignments, function calls, and certain reflective functions like load.
Instruction finetuning on a variety of image-text instruction data is the key to obtaining a versatile Multimodal Large Language Model (MLLM), and different configurations of the instruction data can lead to finetuned models with different capabilities. However, we have discovered that data conflicts are inevitable when mixing instruction data from distinct domains, which can result in performance drops for tasks of a specific domain. To address this issue, we propose to apply a sparse mixture of LoRA experts for instruction finetuning MLLMs. Within the Transformer layers, we extend the popular Low-Rank Adaption (LoRA) method by creating a set of LoRA experts specifically for the MLP layer, and route each token to the top-1 expert based on a routing function, allowing adaptive choices for tokens from different domains. Since the LoRA experts are sparsely activated, the training and inference cost are kept roughly constant compared to the original LoRA method. By replacing the plain-LoRA finetuing of LLaVA-1.5, our final model is named LLaVA-MoLE. Extensive experiments proved that LLaVA-MoLE effectively mitigates the data conflict issue when mixing multiple distinct instruction datasets with various configurations, and achieves consistent performance gains over the strong plain-LoRA baselines. Most importantly, on the mixed datasets, LLaVA-MoLE can even outperform the plain-LoRA baseline trained with twice the samples.
The present study puts forward a novel biographical knowledge graph (KG) on Prof. S. R. Ranganathan, one of the pioneering figures in the Library and Information Science (LIS) domain. It has been found that most of the relevant facts about Ranganathan exist in a variety of resources (e.g., books, essays, journal articles, websites, blogs, etc.), offering information in a fragmented and piecemeal way. With this dedicated KG (henceforth known as RKG), we hope to furnish a 360-degree view of his life and achievements. To the best of our knowledge, such a dedicated representation is unparalleled in its scope and coverage: using state-of-the-art technology for anyone to openly access, use/re-use, and contribute. Inspired by Ranganathan's theories and ideas, the KG was developed using a "facet-based methodology" at two levels: in the identification of the vital biographical aspects and the development of the ontological model. Finally, with this study, we call for a community-driven effort to enhance the KG and pay homage to the Father of Library Science on the hundredth anniversary of his revitalizing the LIS domain through his enduring participation.
Digital circuits, despite having been studied for nearly a century and used at scale for about half that time, have until recently evaded a fully compositional theoretical understanding, in which arbitrary circuits may be freely composed together without consulting their internals. Recent work remedied this theoretical shortcoming by showing how digital circuits can be presented compositionally as morphisms in a freely generated symmetric traced category. However, this was done informally; in this paper we refine and expand the previous work in several ways, culminating in the presentation of three sound and complete semantics for digital circuits: denotational, operational and algebraic. For the denotational semantics, we establish a correspondence between stream functions with certain properties and circuits constructed syntactically. For the operational semantics, we present the reductions required to model how a circuit processes a value, including the addition of a new reduction for eliminating non-delay-guarded feedback; this leads to an adequate notion of observational equivalence for digital circuits. Finally, we define a new family of equations for translating circuits into bisimilar circuits of a 'normal form', leading to a complete algebraic semantics for sequential circuits
Sign-Perturbed Sum (SPS) is a powerful finite-sample system identification algorithm which can construct confidence regions for the true data generating system with exact coverage probabilities, for any finite sample size. SPS was developed in a series of papers and it has a wide range of applications, from general linear systems, even in a closed-loop setup, to nonlinear and nonparametric approaches. Although several theoretical properties of SPS were proven in the literature, the sample complexity of the method was not analysed so far. This paper aims to fill this gap and provides the first results on the sample complexity of SPS. Here, we focus on scalar linear regression problems, that is we study the behaviour of SPS confidence intervals. We provide high probability upper bounds, under three different sets of assumptions, showing that the sizes of SPS confidence intervals shrink at a geometric rate around the true parameter, if the observation noises are subgaussian. We also show that similar bounds hold for the previously proposed outer approximation of the confidence region. Finally, we present simulation experiments comparing the theoretical and the empirical convergence rates.
Large Language Models (LLMs) have exhibited remarkable success in long-form context comprehension tasks. However, their capacity to generate long contents, such as reports and articles, remains insufficiently explored. Current benchmarks do not adequately assess LLMs' ability to produce informative and comprehensive content, necessitating a more rigorous evaluation approach. In this study, we introduce \textsc{ProxyQA}, a framework for evaluating long-form text generation, comprising in-depth human-curated \textit{meta-questions} spanning various domains. Each meta-question contains corresponding \textit{proxy-questions} with annotated answers. LLMs are prompted to generate extensive content in response to these meta-questions. Utilizing an evaluator and incorporating generated content as background context, \textsc{ProxyQA} evaluates the quality of generated content based on the evaluator's performance in answering the \textit{proxy-questions}. We examine multiple LLMs, emphasizing \textsc{ProxyQA}'s demanding nature as a high-quality assessment tool. Human evaluation demonstrates that evaluating through \textit{proxy-questions} is a highly self-consistent and human-criteria-correlated validation method. The dataset and leaderboard will be available at \url{//github.com/Namco0816/ProxyQA}.
UMBRELLA is an open, large-scale IoT ecosystem deployed across South Gloucestershire, UK. It is intended to accelerate innovation across multiple technology domains. UMBRELLA is built to bridge the gap between existing specialised testbeds and address holistically real-world technological challenges in a System-of-Systems (SoS) fashion. UMBRELLA provides open access to real-world devices and infrastructure, enabling researchers and the industry to evaluate solutions for Smart Cities, Robotics, Wireless Communications, Edge Intelligence, and more. Key features include over 200 multi-sensor nodes installed on public infrastructure, a robotics arena with 20 mobile robots, a 5G network-in-a-box solution, and a unified backend platform for management, control and secure user access. The heterogeneity of hardware components, including diverse sensors, communication interfaces, and GPU-enabled edge devices, coupled with tools like digital twins, allows for comprehensive experimentation and benchmarking of innovative solutions not viable in lab environments. This paper provides a comprehensive overview of UMBRELLA's multi-domain architecture and capabilities, making it an ideal playground for Internet of Things (IoT) and Industrial IoT (IIoT) innovation. It discusses the challenges in designing, developing and operating UMBRELLA as an open, sustainable testbed and shares lessons learned to guide similar future initiatives. With its unique openness, heterogeneity, realism and tools, UMBRELLA aims to continue accelerating cutting-edge technology research, development and translation into real-world progress.
Accurate and comprehensive semantic segmentation of Bird's Eye View (BEV) is essential for ensuring safe and proactive navigation in autonomous driving. Although cooperative perception has exceeded the detection capabilities of single-agent systems, prevalent camera-based algorithms in cooperative perception neglect valuable information derived from historical observations. This limitation becomes critical during sensor failures or communication issues as cooperative perception reverts to single-agent perception, leading to degraded performance and incomplete BEV segmentation maps. This paper introduces TempCoBEV, a temporal module designed to incorporate historical cues into current observations, thereby improving the quality and reliability of BEV map segmentations. We propose an importance-guided attention architecture to effectively integrate temporal information that prioritizes relevant properties for BEV map segmentation. TempCoBEV is an independent temporal module that seamlessly integrates into state-of-the-art camera-based cooperative perception models. We demonstrate through extensive experiments on the OPV2V dataset that TempCoBEV performs better than non-temporal models in predicting current and future BEV map segmentations, particularly in scenarios involving communication failures. We show the efficacy of TempCoBEV and its capability to integrate historical cues into the current BEV map, improving predictions under optimal communication conditions by up to 2% and under communication failures by up to 19%. The code will be published on GitHub.
We propose Compact and Swift Segmenting 3D Gaussians(CoSSegGaussians), a method for compact 3D-consistent scene segmentation at fast rendering speed with only RGB images input. Previous NeRF-based segmentation methods have relied on time-consuming neural scene optimization. While recent 3D Gaussian Splatting has notably improved speed, existing Gaussian-based segmentation methods struggle to produce compact masks, especially in zero-shot segmentation. This issue probably stems from their straightforward assignment of learnable parameters to each Gaussian, resulting in a lack of robustness against cross-view inconsistent 2D machine-generated labels. Our method aims to address this problem by employing Dual Feature Fusion Network as Gaussians' segmentation field. Specifically, we first optimize 3D Gaussians under RGB supervision. After Gaussian Locating, DINO features extracted from images are applied through explicit unprojection, which are further incorporated with spatial features from the efficient point cloud processing network. Feature aggregation is utilized to fuse them in a global-to-local strategy for compact segmentation features. Experimental results show that our model outperforms baselines on both semantic and panoptic zero-shot segmentation task, meanwhile consumes less than 10\% inference time compared to NeRF-based methods. Code and more results will be available at //David-Dou.github.io/CoSSegGaussians.
The proliferation of Information and Communication Technologies (ICTs) has shown great promise in addressing educational challenges facing rural areas. However, the complex rural context poses significant challenges to the effective utilization of these technologies. This paper examines the empirical integration of live-streaming-based remote classrooms (LSRC) through a qualitative study in rural China. Our findings suggest that while LSRC enables rural students equal access to high-quality educational resources, its practical integration faces numerous challenges. In particular, we emphasize the crucial role of local teachers in addressing these challenges, ultimately achieving the desired improvement of students' learning outcomes. We also examine the impact of LSRC on the original rural education ecosystem. Building upon our findings, we call for a reconsideration of interaction paradigms and evaluation systems of ICT-mediated rural education, emphasizing the significance of rural teachers. We conclude by discussing the implications for future ICT-mediated technology interventions in rural settings.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191