Large language models (LLMs) have shown great progress in responding to user questions, allowing for a multitude of diverse applications. Yet, the quality of LLM outputs heavily depends on the prompt design, where a good prompt might enable the LLM to answer a very challenging question correctly. Therefore, recent works have developed many strategies for improving the prompt, including both manual crafting and in-domain optimization. However, their efficacy in unrestricted scenarios remains questionable, as the former depends on human design for specific questions and the latter usually generalizes poorly to unseen scenarios. To address these problems, we give LLMs the freedom to design the best prompts according to themselves. Specifically, we include a hierarchy of LLMs, first constructing a prompt with precise instructions and accurate wording in a hierarchical manner, and then using this prompt to generate the final answer to the user query. We term this pipeline Hierarchical Multi-Agent Workflow, or HMAW. In contrast with prior works, HMAW imposes no human restriction and requires no training, and is completely task-agnostic while capable of adjusting to the nuances of the underlying task. Through both quantitative and qualitative experiments across multiple benchmarks, we verify that despite its simplicity, the proposed approach can create detailed and suitable prompts, further boosting the performance of current LLMs.

Large language models (LLMs) exhibit enhanced reasoning at larger scales, driving efforts to distill these capabilities into smaller models via teacher-student learning. Previous works simply fine-tune student models on teachers' generated Chain-of-Thoughts (CoTs) data. Although these methods enhance in-domain (IND) reasoning performance, they struggle to generalize to out-of-domain (OOD) tasks. We believe that the widespread spurious correlations between questions and answers may lead the model to preset a specific answer which restricts the diversity and generalizability of its reasoning process. In this paper, we propose Cascading Decomposed CoTs Distillation (CasCoD) to address these issues by decomposing the traditional single-step learning process into two cascaded learning steps. Specifically, by restructuring the training objectives -- removing the answer from outputs and concatenating the question with the rationale as input -- CasCoD's two-step learning process ensures that students focus on learning rationales without interference from the preset answers, thus improving reasoning generalizability. Extensive experiments demonstrate the effectiveness of CasCoD on both IND and OOD benchmark reasoning datasets. Code can be found at https://github.com/C-W-D/CasCoD.

The rapid advancement of artificial intelligence (AI) has brought significant challenges to the education and workforce skills required to take advantage of AI for human-AI collaboration in the workplace. As AI continues to reshape industries and job markets, the need to define how AI literacy can be considered in lifelong learning has become increasingly critical (Cetindamar et al., 2022; Laupichler et al., 2022; Romero et al., 2023). Like any new technology, AI is the subject of both hopes and fears, and what it entails today presents major challenges (Cugurullo \& Acheampong, 2023; Villani et al., 2018). It also raises profound questions about our own humanity. Will the machine surpass the intelligence of the humans who designed it? What will be the relationship between so-called AI and our human intelligences? How could human-AI collaboration be regulated in a way that serves the Sustainable Development Goals (SDGs)? This paper provides a review of the challenges of lifelong learning in the era of AI from a computational thinking, critical thinking, and creative competencies perspective, highlighting the implications for management and leadership in organizations.

In this work, we investigate whether small language models can determine high-quality subsets of large-scale text datasets that improve the performance of larger language models. While existing work has shown that pruning based on the perplexity of a larger model can yield high-quality data, we investigate whether smaller models can be used for perplexity-based pruning and how pruning is affected by the domain composition of the data being pruned. We demonstrate that for multiple dataset compositions, perplexity-based pruning of pretraining data can \emph{significantly} improve downstream task performance: pruning based on perplexities computed with a 125 million parameter model improves the average performance on downstream tasks of a 3 billion parameter model by up to 2.04 and achieves up to a $1.45\times$ reduction in pretraining steps to reach commensurate baseline performance. Furthermore, we demonstrate that such perplexity-based data pruning also yields downstream performance gains in the over-trained and data-constrained regimes.

As a form of artificial intelligence (AI) technology based on interactive learning, deep reinforcement learning (DRL) has been widely applied across various fields and has achieved remarkable accomplishments. However, DRL faces certain limitations, including low sample efficiency and poor generalization. Therefore, we present how to leverage generative AI (GAI) to address these issues above and enhance the performance of DRL algorithms in this paper. We first introduce several classic GAI and DRL algorithms and demonstrate the applications of GAI-enhanced DRL algorithms. Then, we discuss how to use GAI to improve DRL algorithms from the data and policy perspectives. Subsequently, we introduce a framework that demonstrates an actual and novel integration of GAI with DRL, i.e., GAI-enhanced DRL. Additionally, we provide a case study of the framework on UAV-assisted integrated near-field/far-field communication to validate the performance of the proposed framework. Moreover, we present several future directions. Finally, the related code is available at: https://xiewenwen22.github.io/GAI-enhanced-DRL.

Continual learning of partially similar tasks poses a challenge for artificial neural networks, as task similarity presents both an opportunity for knowledge transfer and a risk of interference and catastrophic forgetting. However, it remains unclear how task similarity in input features and readout patterns influences knowledge transfer and forgetting, as well as how they interact with common algorithms for continual learning. Here, we develop a linear teacher-student model with latent structure and show analytically that high input feature similarity coupled with low readout similarity is catastrophic for both knowledge transfer and retention. Conversely, the opposite scenario is relatively benign. Our analysis further reveals that task-dependent activity gating improves knowledge retention at the expense of transfer, while task-dependent plasticity gating does not affect either retention or transfer performance at the over-parameterized limit. In contrast, weight regularization based on the Fisher information metric significantly improves retention, regardless of task similarity, without compromising transfer performance. Nevertheless, its diagonal approximation and regularization in the Euclidean space are much less robust against task similarity. We demonstrate consistent results in a permuted MNIST task with latent variables. Overall, this work provides insights into when continual learning is difficult and how to mitigate it.

Deep Reinforcement Learning is widely used for aligning Large Language Models (LLM) with human preference. However, the conventional reward modelling is predominantly dependent on human annotations provided by a select cohort of individuals. Such dependence may unintentionally result in skewed models that reflect the inclinations of these annotators, thereby failing to adequately represent the wider population's expectations. We propose the Distributional Preference Reward Model (DPRM), a simple yet effective framework to align large language models with diverse human preferences. To this end, we characterize multiple preferences by a categorical distribution and introduce a Bayesian updater to accommodate shifted or new preferences. On top of that, we design an optimal-transportation-based loss to calibrate DPRM to align with the preference distribution. Finally, the expected reward is utilized to fine-tune an LLM policy to generate responses favoured by the population. Our experiments show that DPRM significantly enhances the alignment of LLMs with population preference, yielding more accurate, unbiased, and contextually appropriate responses.

Machine learning is increasingly used to predict lifestyle-related disease onset using health and medical data. However, the prediction effectiveness is hindered by dataset shift, which involves discrepancies in data distribution between the training and testing datasets, misclassifying out-of-distribution (OOD) data. To diminish dataset shift effects, this paper proposes the out-of-distribution reject option for prediction (ODROP), which integrates OOD detection models to preclude OOD data from the prediction phase. We investigated the efficacy of five OOD detection methods (variational autoencoder, neural network ensemble std, neural network ensemble epistemic, neural network energy, and neural network gaussian mixture based energy measurement) across two datasets, the Hirosaki and Wakayama health checkup data, in the context of three disease onset prediction tasks: diabetes, dyslipidemia, and hypertension. To evaluate the ODROP method, we trained disease onset prediction models and OOD detection models on Hirosaki data and used AUROC-rejection curve plots from Wakayama data. The variational autoencoder method showed superior stability and magnitude of improvement in Area Under the Receiver Operating Curve (AUROC) in five cases: AUROC in the Wakayama data was improved from 0.80 to 0.90 at a 31.1% rejection rate for diabetes onset and from 0.70 to 0.76 at a 34% rejection rate for dyslipidemia. We categorized dataset shifts into two types using SHAP clustering - those that considerably affect predictions and those that do not. We expect that this classification will help standardize measuring instruments. This study is the first to apply OOD detection to actual health and medical data, demonstrating its potential to substantially improve the accuracy and reliability of disease prediction models amidst dataset shift.

Large language models (LLMs) have shown great promise at generating robot programs from natural language given domain-specific robot application programming interfaces (APIs). However, the performance gap between proprietary LLMs and smaller open-weight LLMs remains wide. This raises a question: Can we fine-tune smaller open-weight LLMs for generating domain-specific robot programs to close the performance gap with proprietary LLMs? While Self-Instruct is a promising solution by generating a diverse set of training data, it cannot verify the correctness of these programs. In contrast, a robot simulator with a well-defined world can identify execution errors but limits the diversity of programs that it can verify. In this work, we introduce Robo-Instruct, which brings the best of both worlds -- it promotes the diversity of Self-Instruct while providing the correctness of simulator-based checking. Robo-Instruct introduces RoboSim to synthesize a consistent world state on the fly by inferring properties relevant to the program being checked, and simulating actions accordingly. Furthermore, the instructions and programs generated by Self-Instruct may be subtly inconsistent -- such as the program missing a step implied by the instruction. Robo-Instruct further addresses this with InstAlign, an instruction-program alignment procedure that revises the task instruction to reflect the actual results of the generated program. Given a few seed task descriptions and the robot APIs, Robo-Instruct is capable of generating a training dataset using only a small open-weight model. This dataset can then be used to fine-tune small open-weight language models, enabling them to match or even exceed the performance of several proprietary LLMs, such as GPT-3.5-Turbo and Gemini-Pro.

This paper analyzes Large Language Models (LLMs) with regard to their programming exercise generation capabilities. Through a survey study, we defined the state of the art, extracted their strengths and weaknesses and finally proposed an evaluation matrix, helping researchers and educators to decide which LLM is the best fitting for the programming exercise generation use case. We also found that multiple LLMs are capable of producing useful programming exercises. Nevertheless, there exist challenges like the ease with which LLMs might solve exercises generated by LLMs. This paper contributes to the ongoing discourse on the integration of LLMs in education.