Africa has a very low doctor-to-patient ratio. At very busy clinics, doctors could see 30+ patients per day -- a heavy patient burden compared with developed countries -- but productivity tools such as clinical automatic speech recognition (ASR) are lacking for these overworked clinicians. However, clinical ASR is mature, even ubiquitous, in developed nations, and clinician-reported performance of commercial clinical ASR systems is generally satisfactory. Furthermore, the recent performance of general domain ASR is approaching human accuracy. However, several gaps exist. Several publications have highlighted racial bias with speech-to-text algorithms and performance on minority accents lags significantly. To our knowledge, there is no publicly available research or benchmark on accented African clinical ASR, and speech data is non-existent for the majority of African accents. We release AfriSpeech, 200hrs of Pan-African English speech, 67,577 clips from 2,463 unique speakers across 120 indigenous accents from 13 countries for clinical and general domain ASR, a benchmark test set, with publicly available pre-trained models with SOTA performance on the AfriSpeech benchmark.

Large Language Models (LLMs) have achieved remarkable success, demonstrating powerful instruction-following capabilities across diverse tasks. Instruction fine-tuning is critical in enabling LLMs to align with user intentions and effectively follow instructions. In this work, we investigate how instruction fine-tuning modifies pre-trained models, focusing on two perspectives: instruction recognition and knowledge evolution. To study the behavior shift of LLMs, we employ a suite of local and global explanation methods, including a gradient-based approach for input-output attribution and techniques for interpreting patterns and concepts in self-attention and feed-forward layers. Our findings reveal three significant impacts of instruction fine-tuning: 1) It empowers LLMs to better recognize the instruction parts from user prompts, thereby facilitating high-quality response generation and addressing the ``lost-in-the-middle'' issue observed in pre-trained models; 2) It aligns the knowledge stored in feed-forward layers with user-oriented tasks, exhibiting minimal shifts across linguistic levels. 3) It facilitates the learning of word-word relations with instruction verbs through the self-attention mechanism, particularly in the lower and middle layers, indicating enhanced recognition of instruction words. These insights contribute to a deeper understanding of the behavior shifts in LLMs after instruction fine-tuning and lay the groundwork for future research aimed at interpreting and optimizing LLMs for various applications. We will release our code and data soon.

Human annotator simulation (HAS) serves as a cost-effective substitute for human evaluation such as data annotation and system assessment. Human perception and behaviour during human evaluation exhibit inherent variability due to diverse cognitive processes and subjective interpretations, which should be taken into account in modelling to better mimic the way people perceive and interact with the world. This paper introduces a novel meta-learning framework that treats HAS as a zeroshot density estimation problem, which incorporates human variability and allows for the efficient generation of human-like annotations for unlabelled test inputs. Under this framework, we propose two new model classes, conditional integer flows and conditional softmax flows, to account for ordinal and categorical annotations, respectively. The proposed method is evaluated on three real-world human evaluation tasks and shows superior capability and efficiency to predict the aggregated behaviours of human annotators, match the distribution of human annotations, and simulate the inter-annotator disagreements. Collecting human annotations or evaluations often requires substantial resources and may expose human annotators to distressing and harmful content in sensitive tasks (e.g., toxic speech detection, suicidal risk prediction, and depression detection). This inspires the exploration of human annotator simulation (HAS) as a scalable and cost-effective alternative, which facilitates large-scale dataset evaluation, benchmarking, and system comparisons. Variability is a unique aspect of real-world human evaluation, since individual variations in cognitive biases, cultural backgrounds, and personal experiences (Hirschberg et al., 2003; Wiebe et al., 2004; Haselton et al., 2015) can lead to variability in human interpretation (Lotfian & Busso, 2019; Mathew et al., 2021; Maniati et al., 2022). HAS aims to incorporate the variability present in human evaluation rather than solely relying on majority opinions, which mitigates potential biases and over-representation in scenarios where dominant opinions could potentially overshadow minority viewpoints (Dixon et al., 2018; Hutchinson et al., 2020), thus promoting fairness and inclusivity. In this work, we investigate HAS for the automatic generation of human-like annotations that take into account the variability in human evaluation.

GPT-3), have been developed to understand language through the analysis of extensive text data, allowing them to identify patterns and connections between words. While LLMs have demonstrated impressive performance across various text-related tasks, they encounter challenges in tasks associated with reasoning. To address this challenge, Chain of Thought (CoT) prompting method has been proposed as a means to enhance LLMs' proficiency in complex reasoning tasks like solving math word problems and answering questions based on logical argumentative reasoning. The primary aim of this research is to assess how well four language models can grade reflective essays of third-year medical students. The assessment will specifically target the evaluation of critical thinking skills using CoT prompting. The research will provide the following contributions; to introduce and educate on the process of instructing models to evaluate reflective essays from a dataset they have not been previously trained on; to illustrate the use of CoT prompting as an instructional approach for training large models to carry out particular tasks. Our results suggest that among all the models, Llama-7b performs the least effectively, displaying the highest mean squared error. Conversely, ChatGPT emerges as the superior model, boasting a higher Cohen kappa score value of 0.53. Lastly, it's important to note that the selected models do prioritise user privacy by allowing users to delete their own conducted conversations.

Recent developments in large language models (LLMs) have been impressive. However, these models sometimes show inconsistencies and problematic behavior, such as hallucinating facts, generating flawed code, or creating offensive and toxic content. Unlike these models, humans typically utilize external tools to cross-check and refine their initial content, like using a search engine for fact-checking, or a code interpreter for debugging. Inspired by this observation, we introduce a framework called CRITIC that allows LLMs, which are essentially "black boxes" to validate and progressively amend their own outputs in a manner similar to human interaction with tools. More specifically, starting with an initial output, CRITIC interacts with appropriate tools to evaluate certain aspects of the text, and then revises the output based on the feedback obtained during this validation process. Comprehensive evaluations involving free-form question answering, mathematical program synthesis, and toxicity reduction demonstrate that CRITIC consistently enhances the performance of LLMs. Meanwhile, our research highlights the crucial importance of external feedback in promoting the ongoing self-improvement of LLMs.

Behavioral health interventions, delivered through digital platforms, have the potential to significantly improve health outcomes, through education, motivation, reminders, and outreach. We study the problem of optimizing personalized interventions for patients to maximize a long-term outcome, where interventions are costly and capacity-constrained. We assume there exists a dataset collected from an initial pilot study that we can leverage. We present a new approach for this problem that we dub DecompPI, which approximates one step of policy iteration. Implementing DecompPI simply consists of a prediction task using the dataset, alleviating the need for online experimentation. DecompPI is a generic model-free algorithm that can be used irrespective of the underlying patient behavior model. We derive theoretical guarantees on a simple, special case of the model that is representative of our problem setting. We establish an approximation ratio for DecompPI with respect to the improvement beyond a null policy that does not allocate interventions. Specifically, when the initial policy used to collect the data is randomized, the approximation ratio of the improvement approaches 1/2 as the intervention capacity of the initial policy decreases. We show that this guarantee is robust to estimation errors. We conduct a rigorous empirical case study using real-world data from a mobile health platform for improving treatment adherence for tuberculosis. Using a validated simulation model, we demonstrate that DecompPI can provide the same efficacy as the status quo approach with approximately half the capacity of interventions. DecompPI is simple and easy to implement for organizations aiming to improve long-term behavior through targeted interventions, and this paper demonstrates its strong performance both theoretically and empirically.

It remains a significant challenge to train generally capable agents with reinforcement learning (RL). A promising avenue for improving the robustness of RL agents is through the use of curricula. One such class of methods frames environment design as a game between a student and a teacher, using regret-based objectives to produce environment instantiations (or levels) at the frontier of the student agent's capabilities. These methods benefit from their generality, with theoretical guarantees at equilibrium, yet they often struggle to find effective levels in challenging design spaces. By contrast, evolutionary approaches seek to incrementally alter environment complexity, resulting in potentially open-ended learning, but often rely on domain-specific heuristics and vast amounts of computational resources. In this paper we propose to harness the power of evolution in a principled, regret-based curriculum. Our approach, which we call Adversarially Compounding Complexity by Editing Levels (ACCEL), seeks to constantly produce levels at the frontier of an agent's capabilities, resulting in curricula that start simple but become increasingly complex. ACCEL maintains the theoretical benefits of prior regret-based methods, while providing significant empirical gains in a diverse set of environments. An interactive version of the paper is available at accelagent.github.io.

Federated learning (FL) is a popular paradigm for private and collaborative model training on the edge. In centralized FL, the parameters of a global architecture (such as a deep neural network) are maintained and distributed by a central server/controller to clients who transmit model updates (gradients) back to the server based on local optimization. While many efforts have focused on reducing the communication complexity of gradient transmission, the vast majority of compression-based algorithms assume that each participating client is able to download and train the current and full set of parameters, which may not be a practical assumption depending on the resource constraints of smaller clients such as mobile devices. In this work, we propose a simple yet effective novel algorithm, Comfetch, which allows clients to train large networks using reduced representations of the global architecture via the count sketch, which reduces local computational and memory costs along with bi-directional communication complexity. We provide a nonconvex convergence guarantee and experimentally demonstrate that it is possible to learn large models, such as a deep convolutional network, through federated training on their sketched counterparts. The resulting global models exhibit competitive test accuracy over CIFAR10/100 classification when compared against un-compressed model training.

Anomaly detection is a critical task that involves the identification of data points that deviate from a predefined pattern, useful for fraud detection and related activities. Various techniques are employed for anomaly detection, but recent research indicates that deep learning methods, with their ability to discern intricate data patterns, are well-suited for this task. This study explores the use of Generative Adversarial Networks (GANs) for anomaly detection in power generation plants. The dataset used in this investigation comprises fuel consumption records obtained from power generation plants operated by a telecommunications company. The data was initially collected in response to observed irregularities in the fuel consumption patterns of the generating sets situated at the company's base stations. The dataset was divided into anomalous and normal data points based on specific variables, with 64.88% classified as normal and 35.12% as anomalous. An analysis of feature importance, employing the random forest classifier, revealed that Running Time Per Day exhibited the highest relative importance. A GANs model was trained and fine-tuned both with and without data augmentation, with the goal of increasing the dataset size to enhance performance. The generator model consisted of five dense layers using the tanh activation function, while the discriminator comprised six dense layers, each integrated with a dropout layer to prevent overfitting. Following data augmentation, the model achieved an accuracy rate of 98.99%, compared to 66.45% before augmentation. This demonstrates that the model nearly perfectly classified data points into normal and anomalous categories, with the augmented data significantly enhancing the GANs' performance in anomaly detection. Consequently, this study recommends the use of GANs, particularly when using large datasets, for effective anomaly detection.

Previous statistical approaches to hierarchical clustering for social network analysis all construct an "ultrametric" hierarchy. While the assumption of ultrametricity has been discussed and studied in the phylogenetics literature, it has not yet been acknowledged in the social network literature. We show that "non-ultrametric structure" in the network introduces significant instabilities in the existing top-down recovery algorithms. To address this issue, we introduce an instability diagnostic plot and use it to examine a collection of empirical networks. These networks appear to violate the "ultrametric" assumption. We propose a deceptively simple and yet general class of probabilistic models called $\mathbb{T}$-Stochastic Graphs which impose no topological restrictions on the latent hierarchy. To illustrate this model, we propose six alternative forms of hierarchical network models and then show that all six are equivalent to the $\mathbb{T}$-Stochastic Graph model. These alternative models motivate a novel approach to hierarchical clustering that combines spectral techniques with the well-known Neighbor-Joining algorithm from phylogenetic reconstruction. We prove this spectral approach is statistically consistent.