Recently, innovative model aggregation methods based on knowledge distillation (KD) have been proposed for federated learning (FL). These methods not only improved the robustness of model aggregation over heterogeneous learning environment, but also allowed training heterogeneous models on client devices. However, the scalability of existing methods is not satisfactory, because the training cost on the server increases with the number of clients, which limits their application in large scale systems. Furthermore, the ensemble of existing methods is built from a set of client models initialized from the same checkpoint, causing low diversity. In this paper, we propose a scalable and diversity-enhanced federated distillation scheme, FedSDD, which decouples the training complexity from the number of clients to enhance the scalability, and builds the ensemble from a set of aggregated models with enhanced diversity. In particular, the teacher model in FedSDD is an ensemble built by a small group of aggregated (global) models, instead of all client models, such that the computation cost will not scale with the number of clients. Furthermore, to enhance diversity, FedSDD only performs KD to enhance one of the global models, i.e., the \textit{main global model}, which improves the performance of both the ensemble and the main global model. While partitioning client model into more groups allow building an ensemble with more aggregated models, the convergence of individual aggregated models will be slow down. We introduce the temporal ensembling which leverage the issues, and provide significant improvement with the heterogeneous settings. Experiment results show that FedSDD outperforms other FL methods, including FedAvg and FedDF, on the benchmark datasets.

Semi-supervised learning holds great promise for many real-world applications, due to its ability to leverage both unlabeled and expensive labeled data. However, most semi-supervised learning algorithms still heavily rely on the limited labeled data to infer and utilize the hidden information from unlabeled data. We note that any semi-supervised learning task under the self-training paradigm also hides an auxiliary task of discriminating label observability. Jointly solving these two tasks allows full utilization of information from both labeled and unlabeled data, thus alleviating the problem of over-reliance on labeled data. This naturally leads to a new generic and efficient learning framework without the reliance on any domain-specific information, which we call FlexSSL. The key idea of FlexSSL is to construct a semi-cooperative "game", which forges cooperation between a main self-interested semi-supervised learning task and a companion task that infers label observability to facilitate main task training. We show with theoretical derivation of its connection to loss re-weighting on noisy labels. Through evaluations on a diverse range of tasks, we demonstrate that FlexSSL can consistently enhance the performance of semi-supervised learning algorithms.

We study interactive imitation learning, where a learner interactively queries a demonstrating expert for action annotations, aiming to learn a policy that has performance competitive with the expert, using as few annotations as possible. We give an algorithmic framework named Ensemble-based Interactive Imitation Learning (EIIL) that achieves this goal. Theoretically, we prove that an oracle-efficient version of EIIL achieves sharp regret guarantee, given access to samples from some ``explorative'' distribution over states. Empirically, EIIL notably surpasses online and offline imitation learning benchmarks in continuous control tasks. Our work opens up systematic investigations on the benefit of using model ensembles for interactive imitation learning.

This study evaluates the performance of large language models, specifically GPT-3.5 and BARD (supported by Gemini Pro model), in undergraduate admissions exams proposed by the National Polytechnic Institute in Mexico. The exams cover Engineering/Mathematical and Physical Sciences, Biological and Medical Sciences, and Social and Administrative Sciences. Both models demonstrated proficiency, exceeding the minimum acceptance scores for respective academic programs to up to 75% for some academic programs. GPT-3.5 outperformed BARD in Mathematics and Physics, while BARD performed better in History and questions related to factual information. Overall, GPT-3.5 marginally surpassed BARD with scores of 60.94% and 60.42%, respectively.

The aim of the work presented in this paper is to develop and evaluate an integrated system that provides automated lecture style evaluation, allowing teachers to get instant feedback related to the goodness of their lecturing style. The proposed system aims to promote improvement of lecture quality, that could upgrade the overall student learning experience. The proposed application utilizes specific measurable biometric characteristics, such as facial expressions, body activity, speech rate and intonation, hand movement, and facial pose, extracted from a video showing the lecturer from the audience point of view. Measurable biometric features extracted during a lecture are combined to provide teachers with a score reflecting lecture style quality both at frame rate and by providing lecture quality metrics for the whole lecture. The acceptance of the proposed lecture style evaluation system was evaluated by chief education officers, teachers and students regarding the functionality, usefulness of the application, and possible improvements. The results indicate that participants found the application novel and useful in providing automated feedback regarding lecture quality. Furthermore, the performance evaluation of the proposed system was compared with the performance of humans in the task of lecture style evaluation. Results indicate that the proposed system not only achieves similar performance to human observers, but in some cases, it outperforms them.

Deep neural networks have become the method of choice for solving many classification tasks, largely because they can fit very complex functions defined over raw data. The downside of such powerful learners is the danger of overfit. In this paper, we introduce a novel ensemble classifier for deep networks that effectively overcomes overfitting by combining models generated at specific intermediate epochs during training. Our method allows for the incorporation of useful knowledge obtained by the models during the overfitting phase without deterioration of the general performance, which is usually missed when early stopping is used. To motivate this approach, we begin with the theoretical analysis of a regression model, whose prediction -- that the variance among classifiers increases when overfit occurs -- is demonstrated empirically in deep networks in common use. Guided by these results, we construct a new ensemble-based prediction method, where the prediction is determined by the class that attains the most consensual prediction throughout the training epochs. Using multiple image and text classification datasets, we show that when regular ensembles suffer from overfit, our method eliminates the harmful reduction in generalization due to overfit, and often even surpasses the performance obtained by early stopping. Our method is easy to implement and can be integrated with any training scheme and architecture, without additional prior knowledge beyond the training set. It is thus a practical and useful tool to overcome overfit. Code is available at https://github.com/uristern123/United-We-Stand-Using-Epoch-wise-Agreement-of-Ensembles-to-Combat-Overfit.

A growing area of research investigates augmenting language models with tools (e.g., search engines, calculators) to overcome their shortcomings (e.g., missing or incorrect knowledge, incorrect logical inferences). Various few-shot tool-usage strategies have been proposed. However, there is no systematic and fair comparison across different strategies, or between these strategies and strong baselines that do not leverage tools. We conduct an extensive empirical analysis, finding that (1) across various datasets, example difficulty levels, and models, strong no-tool baselines are competitive to tool-assisted strategies, implying that effectively using tools with in-context demonstrations is a difficult unsolved problem; (2) for knowledge-retrieval tasks, strategies that *refine* incorrect outputs with tools outperform strategies that retrieve relevant information *ahead of* or *during generation*; (3) tool-assisted strategies are expensive in the number of tokens they require to work -- incurring additional costs by orders of magnitude -- which does not translate into significant improvement in performance. Overall, our findings suggest that few-shot tool integration is still an open challenge, emphasizing the need for comprehensive evaluations of future strategies to accurately assess their *benefits* and *costs*.

Every major technical invention resurfaces the dual-use dilemma -- the new technology has the potential to be used for good as well as for harm. Generative AI (GenAI) techniques, such as large language models (LLMs) and diffusion models, have shown remarkable capabilities (e.g., in-context learning, code-completion, and text-to-image generation and editing). However, GenAI can be used just as well by attackers to generate new attacks and increase the velocity and efficacy of existing attacks. This paper reports the findings of a workshop held at Google (co-organized by Stanford University and the University of Wisconsin-Madison) on the dual-use dilemma posed by GenAI. This paper is not meant to be comprehensive, but is rather an attempt to synthesize some of the interesting findings from the workshop. We discuss short-term and long-term goals for the community on this topic. We hope this paper provides both a launching point for a discussion on this important topic as well as interesting problems that the research community can work to address.

In recent years, personality has been regarded as a valuable personal factor being incorporated into numerous tasks such as sentiment analysis and product recommendation. This has led to widespread attention to text-based personality recognition task, which aims to identify an individual's personality based on given text. Considering that ChatGPT has recently exhibited remarkable abilities on various natural language processing tasks, we provide a preliminary evaluation of ChatGPT on text-based personality recognition task for generating effective personality data. Concretely, we employ a variety of prompting strategies to explore ChatGPT's ability in recognizing personality from given text, especially the level-oriented prompting strategy we designed for guiding ChatGPT in analyzing given text at a specified level. The experimental results on two representative real-world datasets reveal that ChatGPT with zero-shot chain-of-thought prompting exhibits impressive personality recognition ability and is capable to provide natural language explanations through text-based logical reasoning. Furthermore, by employing the level-oriented prompting strategy to optimize zero-shot chain-of-thought prompting, the performance gap between ChatGPT and corresponding state-of-the-art model has been narrowed even more. However, we observe that ChatGPT shows unfairness towards certain sensitive demographic attributes such as gender and age. Additionally, we discover that eliciting the personality recognition ability of ChatGPT helps improve its performance on personality-related downstream tasks such as sentiment classification and stress prediction.

Large language models (LLMs) are gaining increasing popularity in both academia and industry, owing to their unprecedented performance in various applications. As LLMs continue to play a vital role in both research and daily use, their evaluation becomes increasingly critical, not only at the task level, but also at the society level for better understanding of their potential risks. Over the past years, significant efforts have been made to examine LLMs from various perspectives. This paper presents a comprehensive review of these evaluation methods for LLMs, focusing on three key dimensions: what to evaluate, where to evaluate, and how to evaluate. Firstly, we provide an overview from the perspective of evaluation tasks, encompassing general natural language processing tasks, reasoning, medical usage, ethics, educations, natural and social sciences, agent applications, and other areas. Secondly, we answer the `where' and `how' questions by diving into the evaluation methods and benchmarks, which serve as crucial components in assessing performance of LLMs. Then, we summarize the success and failure cases of LLMs in different tasks. Finally, we shed light on several future challenges that lie ahead in LLMs evaluation. Our aim is to offer invaluable insights to researchers in the realm of LLMs evaluation, thereby aiding the development of more proficient LLMs. Our key point is that evaluation should be treated as an essential discipline to better assist the development of LLMs. We consistently maintain the related open-source materials at: https://github.com/MLGroupJLU/LLM-eval-survey.