Red teaming is a common strategy for identifying weaknesses in generative language models (LMs), where adversarial prompts are produced that trigger an LM to generate unsafe responses. Red teaming is instrumental for both model alignment and evaluation, but is labor-intensive and difficult to scale when done by humans. In this paper, we present Gradient-Based Red Teaming (GBRT), a red teaming method for automatically generating diverse prompts that are likely to cause an LM to output unsafe responses. GBRT is a form of prompt learning, trained by scoring an LM response with a safety classifier and then backpropagating through the frozen safety classifier and LM to update the prompt. To improve the coherence of input prompts, we introduce two variants that add a realism loss and fine-tune a pretrained model to generate the prompts instead of learning the prompts directly. Our experiments show that GBRT is more effective at finding prompts that trigger an LM to generate unsafe responses than a strong reinforcement learning-based red teaming approach, and succeeds even when the LM has been fine-tuned to produce safer outputs.

Abstract-- The execution failure of cyber-physical systems (e.g., autonomous driving systems, unmanned aerial systems, and robotic systems) could result in the loss of life, severe injuries, large-scale environmental damage, property destruction, and major economic loss. Hence, such systems usually require a strong justification that they will effectively support critical requirements (e.g., safety, security, and reliability) for which they were designed. Thus, it is often mandatory to develop compelling assurance cases to support that justification and allow regulatory bodies to certify such systems. In such contexts, detecting assurance deficits, relying on patterns to improve the structure of assurance cases, improving existing assurance case notations, and (semi-)automating the generation of assurance cases are key to develop compelling assurance cases and foster consumer acceptance. We therefore explore challenges related to such assurance enablers and outline some potential directions that could be explored to tackle them.

In inverse problems, it is widely recognized that the incorporation of a sparsity prior yields a regularization effect on the solution. This approach is grounded on the a priori assumption that the unknown can be appropriately represented in a basis with a limited number of significant components, while most coefficients are close to zero. This occurrence is frequently observed in real-world scenarios, such as with piecewise smooth signals. In this study, we propose a probabilistic sparsity prior formulated as a mixture of degenerate Gaussians, capable of modeling sparsity with respect to a generic basis. Under this premise, we design a neural network that can be interpreted as the Bayes estimator for linear inverse problems. Additionally, we put forth both a supervised and an unsupervised training strategy to estimate the parameters of this network. To evaluate the effectiveness of our approach, we conduct a numerical comparison with commonly employed sparsity-promoting regularization techniques, namely LASSO, group LASSO, iterative hard thresholding, and sparse coding/dictionary learning. Notably, our reconstructions consistently exhibit lower mean square error values across all $1$D datasets utilized for the comparisons, even in cases where the datasets significantly deviate from a Gaussian mixture model.

Translation into severely low-resource languages has both the cultural goal of saving and reviving those languages and the humanitarian goal of assisting the everyday needs of local communities that are accelerated by the recent COVID-19 pandemic. In many humanitarian efforts, translation into severely low-resource languages often does not require a universal translation engine, but a dedicated text-specific translation engine. For example, healthcare records, hygienic procedures, government communication, emergency procedures and religious texts are all limited texts. While generic translation engines for all languages do not exist, translation of multilingually known limited texts into new, low-resource languages may be possible and reduce human translation effort. We attempt to leverage translation resources from rich-resource languages to efficiently produce best possible translation quality for well known texts, which are available in multiple languages, in a new, low-resource language. To reach this goal, we argue that in translating a closed text into low-resource languages, generalization to out-of-domain texts is not necessary, but generalization to new languages is. Performance gain comes from massive source parallelism by careful choice of close-by language families, style-consistent corpus-level paraphrases within the same language and strategic adaptation of existing large pretrained multilingual models to the domain first and then to the language. Such performance gain makes it possible for machine translation systems to collaborate with human translators to expedite the translation process into new, low-resource languages.

This paper proposes a novel, more computationally efficient method for optimizing robot excitation trajectories for dynamic parameter identification, emphasizing self-collision avoidance. This addresses the system identification challenges for getting high-quality training data associated with co-manipulated robotic arms that can be equipped with a variety of tools, a common scenario in industrial but also clinical and research contexts. Utilizing the Unified Robotics Description Format (URDF) to implement a symbolic Python implementation of the Recursive Newton-Euler Algorithm (RNEA), the approach aids in dynamically estimating parameters such as inertia using regression analyses on data from real robots. The excitation trajectory was evaluated and achieved on par criteria when compared to state-of-the-art reported results which didn't consider self-collision and tool calibrations. Furthermore, physical Human-Robot Interaction (pHRI) admittance control experiments were conducted in a surgical context to evaluate the derived inverse dynamics model showing a 30.1\% workload reduction by the NASA TLX questionnaire.

The pervasive spread of misinformation and disinformation poses a significant threat to society. Professional fact-checkers play a key role in addressing this threat, but the vast scale of the problem forces them to prioritize their limited resources. This prioritization may consider a range of factors, such as varying risks of harm posed to specific groups of people. In this work, we investigate potential implications of using a large language model (LLM) to facilitate such prioritization. Because fact-checking impacts a wide range of diverse segments of society, it is important that diverse views are represented in the claim prioritization process. This paper examines whether a LLM can reflect the views of various groups when assessing the harms of misinformation, focusing on gender as a primary variable. We pose two central questions: (1) To what extent do prompts with explicit gender references reflect gender differences in opinion in the United States on topics of social relevance? and (2) To what extent do gender-neutral prompts align with gendered viewpoints on those topics? To analyze these questions, we present the TopicMisinfo dataset, containing 160 fact-checked claims from diverse topics, supplemented by nearly 1600 human annotations with subjective perceptions and annotator demographics. Analyzing responses to gender-specific and neutral prompts, we find that GPT 3.5-Turbo reflects empirically observed gender differences in opinion but amplifies the extent of these differences. These findings illuminate AI's complex role in moderating online communication, with implications for fact-checkers, algorithm designers, and the use of crowd-workers as annotators. We also release the TopicMisinfo dataset to support continuing research in the community.

In the realm of Earth science, effective cloud property retrieval, encompassing cloud masking, cloud phase classification, and cloud optical thickness (COT) prediction, remains pivotal. Traditional methodologies necessitate distinct models for each sensor instrument due to their unique spectral characteristics. Recent strides in Earth Science research have embraced machine learning and deep learning techniques to extract features from satellite datasets' spectral observations. However, prevailing approaches lack novel architectures accounting for hierarchical relationships among retrieval tasks. Moreover, considering the spectral diversity among existing sensors, the development of models with robust generalization capabilities over different sensor datasets is imperative. Surprisingly, there is a dearth of methodologies addressing the selection of an optimal model for diverse datasets. In response, this paper introduces MT-HCCAR, an end-to-end deep learning model employing multi-task learning to simultaneously tackle cloud masking, cloud phase retrieval (classification tasks), and COT prediction (a regression task). The MT-HCCAR integrates a hierarchical classification network (HC) and a classification-assisted attention-based regression network (CAR), enhancing precision and robustness in cloud labeling and COT prediction. Additionally, a comprehensive model selection method rooted in K-fold cross-validation, one standard error rule, and two introduced performance scores is proposed to select the optimal model over three simulated satellite datasets OCI, VIIRS, and ABI. The experiments comparing MT-HCCAR with baseline methods, the ablation studies, and the model selection affirm the superiority and the generalization capabilities of MT-HCCAR.

By classic results in social choice theory, any reasonable preferential voting method sometimes gives individuals an incentive to report an insincere preference. The extent to which different voting methods are more or less resistant to such strategic manipulation has become a key consideration for comparing voting methods. Here we measure resistance to manipulation by whether neural networks of varying sizes can learn to profitably manipulate a given voting method in expectation, given different types of limited information about how other voters will vote. We trained nearly 40,000 neural networks of 26 sizes to manipulate against 8 different voting methods, under 6 types of limited information, in committee-sized elections with 5-21 voters and 3-6 candidates. We find that some voting methods, such as Borda, are highly manipulable by networks with limited information, while others, such as Instant Runoff, are not, despite being quite profitably manipulated by an ideal manipulator with full information.

Nowadays, real-world applications often face streaming data, which requires the learning system to absorb new knowledge as data evolves. Continual Learning (CL) aims to achieve this goal and meanwhile overcome the catastrophic forgetting of former knowledge when learning new ones. Typical CL methods build the model from scratch to grow with incoming data. However, the advent of the pre-trained model (PTM) era has sparked immense research interest, particularly in leveraging PTMs' robust representational capabilities. This paper presents a comprehensive survey of the latest advancements in PTM-based CL. We categorize existing methodologies into three distinct groups, providing a comparative analysis of their similarities, differences, and respective advantages and disadvantages. Additionally, we offer an empirical study contrasting various state-of-the-art methods to highlight concerns regarding fairness in comparisons. The source code to reproduce these evaluations is available at: https://github.com/sun-hailong/LAMDA-PILOT

Topic models are a popular tool for understanding text collections, but their evaluation has been a point of contention. Automated evaluation metrics such as coherence are often used, however, their validity has been questioned for neural topic models (NTMs) and can overlook the benefits of a model in real world applications. To this end, we conduct the first evaluation of neural, supervised and classical topic models in an interactive task based setting. We combine topic models with a classifier and test their ability to help humans conduct content analysis and document annotation. From simulated, real user and expert pilot studies, the Contextual Neural Topic Model does the best on cluster evaluation metrics and human evaluations; however, LDA is competitive with two other NTMs under our simulated experiment and user study results, contrary to what coherence scores suggest. We show that current automated metrics do not provide a complete picture of topic modeling capabilities, but the right choice of NTMs can be better than classical models on practical tasks.