The robustness of recent Large Language Models (LLMs) has become increasingly crucial as their applicability expands across various domains and real-world applications. Retrieval-Augmented Generation (RAG) is a promising solution for addressing the limitations of LLMs, yet existing studies on the robustness of RAG often overlook the interconnected relationships between RAG components or the potential threats prevalent in real-world databases, such as minor textual errors. In this work, we investigate two underexplored aspects when assessing the robustness of RAG: 1) vulnerability to noisy documents through low-level perturbations and 2) a holistic evaluation of RAG robustness. Furthermore, we introduce a novel attack method, the Genetic Attack on RAG (\textit{GARAG}), which targets these aspects. Specifically, GARAG is designed to reveal vulnerabilities within each component and test the overall system functionality against noisy documents. We validate RAG robustness by applying our \textit{GARAG} to standard QA datasets, incorporating diverse retrievers and LLMs. The experimental results show that GARAG consistently achieves high attack success rates. Also, it significantly devastates the performance of each component and their synergy, highlighting the substantial risk that minor textual inaccuracies pose in disrupting RAG systems in the real world.

In this work, the problem of communicating decisions of a classifier over a noisy channel is considered. With machine learning based models being used in variety of time-sensitive applications, transmission of these decisions in a reliable and timely manner is of significant importance. To this end, we study the scenario where a probability vector (representing the decisions of a classifier) at the transmitter, needs to be transmitted over a noisy channel. Assuming that the distortion between the original probability vector and the reconstructed one at the receiver is measured via f-divergence, we study the trade-off between transmission latency and the distortion. We completely analyze this trade-off using uniform, lattice, and sparse lattice-based quantization techniques to encode the probability vector by first characterizing bit budgets for each technique given a requirement on the allowed source distortion. These bounds are then combined with results from finite-blocklength literature to provide a framework for analyzing the effects of both quantization distortion and distortion due to decoding error probability (i.e., channel effects) on the incurred transmission latency. Our results show that there is an interesting interplay between source distortion (i.e., distortion for the probability vector measured via f-divergence) and the subsequent channel encoding/decoding parameters; and indicate that a joint design of these parameters is crucial to navigate the latency-distortion tradeoff. We study the impact of changing different parameters (e.g. number of classes, SNR, source distortion) on the latency-distortion tradeoff and perform experiments on AWGN and fading channels. Our results indicate that sparse lattice-based quantization is the most effective at minimizing latency across various regimes and for sparse, high-dimensional probability vectors (i.e., high number of classes).

Finding controllers that perform well across multiple morphologies is an important milestone for large-scale robotics, in line with recent advances via foundation models in other areas of machine learning. However, the challenges of learning a single controller to control multiple morphologies make the `one robot one task' paradigm dominant in the field. To alleviate these challenges, we present a pipeline that: (1) leverages Quality Diversity algorithms like MAP-Elites to create a dataset of many single-task/single-morphology teacher controllers, then (2) distills those diverse controllers into a single multi-morphology controller that performs well across many different body plans by mimicking the sensory-action patterns of the teacher controllers via supervised learning. The distilled controller scales well with the number of teachers/morphologies and shows emergent properties. It generalizes to unseen morphologies in a zero-shot manner, providing robustness to morphological perturbations and instant damage recovery. Lastly, the distilled controller is also independent of the teacher controllers -- we can distill the teacher's knowledge into any controller model, making our approach synergistic with architectural improvements and existing training algorithms for teacher controllers.

With the recent advances in machine learning, creating agents that behave realistically in simulated air combat has become a growing field of interest. This survey explores the application of machine learning techniques for modeling air combat behavior, motivated by the potential to enhance simulation-based pilot training. Current simulated entities tend to lack realistic behavior, and traditional behavior modeling is labor-intensive and prone to loss of essential domain knowledge between development steps. Advancements in reinforcement learning and imitation learning algorithms have demonstrated that agents may learn complex behavior from data, which could be faster and more scalable than manual methods. Yet, making adaptive agents capable of performing tactical maneuvers and operating weapons and sensors still poses a significant challenge. The survey examines applications, behavior model types, prevalent machine learning methods, and the technical and human challenges in developing adaptive and realistically behaving agents. Another challenge is the transfer of agents from learning environments to military simulation systems and the consequent demand for standardization. Four primary recommendations are presented regarding increased emphasis on beyond-visual-range scenarios, multi-agent machine learning and cooperation, utilization of hierarchical behavior models, and initiatives for standardization and research collaboration. These recommendations aim to address current issues and guide the development of more comprehensive, adaptable, and realistic machine learning-based behavior models for air combat applications.

This paper investigates what insights about linguistic features and what knowledge about the structure of natural language can be obtained from the encodings in transformer language models.In particular, we explore how BERT encodes the government relation between constituents in a sentence. We use several probing classifiers, and data from two morphologically rich languages. Our experiments show that information about government is encoded across all transformer layers, but predominantly in the early layers of the model. We find that, for both languages, a small number of attention heads encode enough information about the government relations to enable us to train a classifier capable of discovering new, previously unknown types of government, never seen in the training data. Currently, data is lacking for the research community working on grammatical constructions, and government in particular. We release the Government Bank -- a dataset defining the government relations for thousands of lemmas in the languages in our experiments.

Content Warning: This paper contains examples of misgendering and erasure that could be offensive and potentially triggering. Misgendering, the act of incorrectly addressing someone's gender, inflicts serious harm and is pervasive in everyday technologies, yet there is a notable lack of research to combat it. We are the first to address this lack of research into interventions for misgendering by conducting a survey of gender-diverse individuals in the US to understand perspectives about automated interventions for text-based misgendering. Based on survey insights on the prevalence of misgendering, desired solutions, and associated concerns, we introduce a misgendering interventions task and evaluation dataset, MisgenderMender. We define the task with two sub-tasks: (i) detecting misgendering, followed by (ii) correcting misgendering where misgendering is present in domains where editing is appropriate. MisgenderMender comprises 3790 instances of social media content and LLM-generations about non-cisgender public figures, annotated for the presence of misgendering, with additional annotations for correcting misgendering in LLM-generated text. Using this dataset, we set initial benchmarks by evaluating existing NLP systems and highlighting challenges for future models to address. We release the full dataset, code, and demo at https://tamannahossainkay.github.io/misgendermender/.

Socially Assistive Robots are studied in different Child-Robot Interaction settings. However, logistical constraints limit accessibility, particularly affecting timely support for mental wellbeing. In this work, we have investigated whether online interactions with a robot can be used for the assessment of mental wellbeing in children. The children (N=40, 20 girls and 20 boys; 8-13 years) interacted with the Nao robot (30-45 mins) over three sessions, at least a week apart. Audio-visual recordings were collected throughout the sessions that concluded with the children answering user perception questionnaires pertaining to their anxiety towards the robot, and the robot's abilities. We divided the participants into three wellbeing clusters (low, med and high tertiles) using their responses to the Short Moods and Feelings Questionnaire (SMFQ) and further analysed how their wellbeing and their perceptions of the robot changed over the wellbeing tertiles, across sessions and across participants' gender. Our primary findings suggest that (I) online mediated-interactions with robots can be effective in assessing children's mental wellbeing over time, and (II) children's overall perception of the robot either improved or remained consistent across time. Supplementary exploratory analyses have also revealed that gender affected the children's wellbeing assessments as well as their perceptions of the robot.

Automotive insurers increasingly have access to telematic information via black-box recorders installed in the insured vehicle, and wish to identify undesirable behaviour which may signify increased risk or uninsured activities. However, identification of such behaviour with machine learning is non-trivial, and results are far from perfect, requiring human investigation to verify suspected cases. An appropriately formed priority score, generated by automated analysis of GPS data, allows underwriters to make more efficient use of their time, improving detection of the behaviour under investigation. An example of such behaviour is the use of a privately insured vehicle for commercial purposes, such as delivering meals and parcels. We first make use of trip GPS and accelerometer data, augmented by geospatial information, to train an imperfect classifier for delivery driving on a per-trip basis. We make use of a mixture of Beta-Binomial distributions to model the propensity of a policyholder to undertake trips which result in a positive classification as being drawn from either a rare high-scoring or common low-scoring group, and learn the parameters of this model using MCMC. This model provides us with a posterior probability that any policyholder will be a regular generator of automated alerts given any number of trips and alerts. This posterior probability is converted to a priority score, which was used to select the most valuable candidates for manual investigation. Testing over a 1-year period ranked policyholders by likelihood of commercial driving activity on a weekly basis. The top 0.9% have been reviewed at least once by the underwriters at the time of writing, and of those 99.4% have been confirmed as correctly identified, showing the approach has achieved a significant improvement in efficiency of human resource allocation compared to manual searching.

We have developed the world's first canopy height map of the distribution area of world-level giant trees. This mapping is crucial for discovering more individual and community world-level giant trees, and for analyzing and quantifying the effectiveness of biodiversity conservation measures in the Yarlung Tsangpo Grand Canyon (YTGC) National Nature Reserve. We proposed a method to map the canopy height of the primeval forest within the world-level giant tree distribution area by using a spaceborne LiDAR fusion satellite imagery (Global Ecosystem Dynamics Investigation (GEDI), ICESat-2, and Sentinel-2) driven deep learning modeling. And we customized a pyramid receptive fields depth separable CNN (PRFXception). PRFXception, a CNN architecture specifically customized for mapping primeval forest canopy height to infer the canopy height at the footprint level of GEDI and ICESat-2 from Sentinel-2 optical imagery with a 10-meter spatial resolution. We conducted a field survey of 227 permanent plots using a stratified sampling method and measured several giant trees using UAV-LS. The predicted canopy height was compared with ICESat-2 and GEDI validation data (RMSE =7.56 m, MAE=6.07 m, ME=-0.98 m, R^2=0.58 m), UAV-LS point clouds (RMSE =5.75 m, MAE =3.72 m, ME = 0.82 m, R^2= 0.65 m), and ground survey data (RMSE = 6.75 m, MAE = 5.56 m, ME= 2.14 m, R^2=0.60 m). We mapped the potential distribution map of world-level giant trees and discovered two previously undetected giant tree communities with an 89% probability of having trees 80-100 m tall, potentially taller than Asia's tallest tree. This paper provides scientific evidence confirming southeastern Tibet--northwestern Yunnan as the fourth global distribution center of world-level giant trees initiatives and promoting the inclusion of the YTGC giant tree distribution area within the scope of China's national park conservation.

Printed mathematical expression recognition (MER) models are usually trained and tested using LaTeX-generated mathematical expressions (MEs) as input and the LaTeX source code as ground truth. As the same ME can be generated by various different LaTeX source codes, this leads to unwanted variations in the ground truth data that bias test performance results and hinder efficient learning. In addition, the use of only one font to generate the MEs heavily limits the generalization of the reported results to realistic scenarios. We propose a data-centric approach to overcome this problem, and present convincing experimental results: Our main contribution is an enhanced LaTeX normalization to map any LaTeX ME to a canonical form. Based on this process, we developed an improved version of the benchmark dataset im2latex-100k, featuring 30 fonts instead of one. Second, we introduce the real-world dataset realFormula, with MEs extracted from papers. Third, we developed a MER model, MathNet, based on a convolutional vision transformer, with superior results on all four test sets (im2latex-100k, im2latexv2, realFormula, and InftyMDB-1), outperforming the previous state of the art by up to 88.3%.