The capacity of large language models (LLMs) to generate honest, harmless, and helpful responses heavily relies on the quality of user prompts. However, these prompts often tend to be brief and vague, thereby significantly limiting the full potential of LLMs. Moreover, harmful prompts can be meticulously crafted and manipulated by adversaries to jailbreak LLMs, inducing them to produce potentially toxic content. To enhance the capabilities of LLMs while maintaining strong robustness against harmful jailbreak inputs, this study proposes a transferable and pluggable framework that refines user prompts before they are input into LLMs. This strategy improves the quality of the queries, empowering LLMs to generate more truthful, benign and useful responses. Specifically, a lightweight query refinement model is introduced and trained using a specially designed reinforcement learning approach that incorporates multiple objectives to enhance particular capabilities of LLMs. Extensive experiments demonstrate that the refinement model not only improves the quality of responses but also strengthens their robustness against jailbreak attacks. Code is available at: https://github.com/Huangzisu/query-refinement .

Reinforcement learning (RL) -- finding the optimal behaviour (also referred to as policy) maximizing the collected long-term cumulative reward -- is among the most influential approaches in machine learning with a large number of successful applications. In several decision problems, however, one faces the possibility of policy switching -- changing from the current policy to a new one -- which incurs a non-negligible cost (examples include the shifting of the currently applied educational technology, modernization of a computing cluster, and the introduction of a new webpage design), and in the decision one is limited to using historical data without the availability for further online interaction. Despite the inevitable importance of this offline learning scenario, to our best knowledge, very little effort has been made to tackle the key problem of balancing between the gain and the cost of switching in a flexible and principled way. Leveraging ideas from the area of optimal transport, we initialize the systematic study of policy switching in offline RL. We establish fundamental properties and design a Net Actor-Critic algorithm for the proposed novel switching formulation. Numerical experiments demonstrate the efficiency of our approach on multiple benchmarks of the Gymnasium.

The demand for efficient and accurate assessment methods has intensified as education systems transition to digital platforms. Providing feedback is essential in educational settings and goes beyond simply conveying marks as it justifies the assigned marks. In this context, we present a significant advancement in automated grading by introducing Engineering Short Answer Feedback (EngSAF) -- a dataset of 5.8k student answers accompanied by reference answers and questions for the Automatic Short Answer Grading (ASAG) task. The EngSAF dataset is meticulously curated to cover a diverse range of subjects, questions, and answer patterns from multiple engineering domains. We leverage state-of-the-art large language models' (LLMs) generative capabilities with our Label-Aware Synthetic Feedback Generation (LASFG) strategy to include feedback in our dataset. This paper underscores the importance of enhanced feedback in practical educational settings, outlines dataset annotation and feedback generation processes, conducts a thorough EngSAF analysis, and provides different LLMs-based zero-shot and finetuned baselines for future comparison. Additionally, we demonstrate the efficiency and effectiveness of the ASAG system through its deployment in a real-world end-semester exam at the Indian Institute of Technology Bombay (IITB), showcasing its practical viability and potential for broader implementation in educational institutions.

Complex adaptive agents consistently achieve their goals by solving problems that seem to require an understanding of causal information, information pertaining to the causal relationships that exist among elements of combined agent-environment systems. Causal cognition studies and describes the main characteristics of causal learning and reasoning in human and non-human animals, offering a conceptual framework to discuss cognitive performances based on the level of apparent causal understanding of a task. Despite the use of formal intervention-based models of causality, including causal Bayesian networks, psychological and behavioural research on causal cognition does not yet offer a computational account that operationalises how agents acquire a causal understanding of the world. Machine and reinforcement learning research on causality, especially involving disentanglement as a candidate process to build causal representations, represent on the one hand a concrete attempt at designing causal artificial agents that can shed light on the inner workings of natural causal cognition. In this work, we connect these two areas of research to build a unifying framework for causal cognition that will offer a computational perspective on studies of animal cognition, and provide insights in the development of new algorithms for causal reinforcement learning in AI.

In response to the needs of 6G global communications, satellite communication networks have emerged as a key solution. However, the large-scale development of satellite communication networks is constrained by the complex system models, whose modeling is challenging for massive users. Moreover, transmission interference between satellites and users seriously affects communication performance. To solve these problems, this paper develops generative artificial intelligence (AI) agents for model formulation and then applies a mixture of experts (MoE) approach to design transmission strategies. Specifically, we leverage large language models (LLMs) to build an interactive modeling paradigm and utilize retrieval-augmented generation (RAG) to extract satellite expert knowledge that supports mathematical modeling. Afterward, by integrating the expertise of multiple specialized components, we propose an MoE-proximal policy optimization (PPO) approach to solve the formulated problem. Each expert can optimize the optimization variables at which it excels through specialized training through its own network and then aggregates them through the gating network to perform joint optimization. The simulation results validate the accuracy and effectiveness of employing a generative agent for problem formulation. Furthermore, the superiority of the proposed MoE-ppo approach over other benchmarks is confirmed in solving the formulated problem. The adaptability of MoE-PPO to various customized modeling problems has also been demonstrated.

Given the extensive and growing capabilities offered by deep learning (DL), more researchers are turning to DL to address complex challenges in next-generation (xG) communications. However, despite its progress, DL also reveals several limitations that are becoming increasingly evident. One significant issue is its lack of interpretability, which is especially critical for safety-sensitive applications. Another significant consideration is that DL may not comply with the constraints set by physics laws or given security standards, which are essential for reliable DL. Additionally, DL models often struggle outside their training data distributions, which is known as poor generalization. Moreover, there is a scarcity of theoretical guidance on designing DL algorithms. These challenges have prompted the emergence of a burgeoning field known as science-informed DL (ScIDL). ScIDL aims to integrate existing scientific knowledge with DL techniques to develop more powerful algorithms. The core objective of this article is to provide a brief tutorial on ScIDL that illustrates its building blocks and distinguishes it from conventional DL. Furthermore, we discuss both recent applications of ScIDL and potential future research directions in the field of wireless communications.

Large language models (LLMs) have become the foundation of many applications, leveraging their extensive capabilities in processing and understanding natural language. While many open-source LLMs have been released with technical reports, the lack of training details hinders further research and development. This paper presents the development of YuLan, a series of open-source LLMs with $12$ billion parameters. The base model of YuLan is pre-trained on approximately $1.7$T tokens derived from a diverse corpus, including massive English, Chinese, and multilingual texts. We design a three-stage pre-training method to enhance YuLan's overall capabilities. Subsequent phases of training incorporate instruction-tuning and human alignment, employing a substantial volume of high-quality synthesized data. To facilitate the learning of complex and long-tail knowledge, we devise a curriculum-learning framework throughout across these stages, which helps LLMs learn knowledge in an easy-to-hard manner. YuLan's training is finished on Jan, 2024 and has achieved performance on par with state-of-the-art LLMs across various English and Chinese benchmarks. This paper outlines a comprehensive technical roadmap for developing LLMs from scratch. Our model and codes are available at https://github.com/RUC-GSAI/YuLan-Chat.

This study investigates the impact of model size on Online Continual Learning performance, with a focus on catastrophic forgetting. Employing ResNet architectures of varying sizes, the research examines how network depth and width affect model performance in class-incremental learning using the SplitCIFAR-10 dataset. Key findings reveal that larger models do not guarantee better Continual Learning performance; in fact, they often struggle more in adapting to new tasks, particularly in online settings. These results challenge the notion that larger models inherently mitigate catastrophic forgetting, highlighting the nuanced relationship between model size and Continual Learning efficacy. This study contributes to a deeper understanding of model scalability and its practical implications in Continual Learning scenarios.

The recent surge in generative AI technologies, such as large language models and diffusion models, has boosted the development of AI applications in various domains, including science, finance, and education. Concurrently, adaptive learning, a concept that has gained substantial interest in the educational sphere, has proven its efficacy in enhancing students' learning efficiency. In this position paper, we aim to shed light on the intersectional studies of these two methods, which combine generative AI with adaptive learning concepts. By presenting discussions about the benefits, challenges, and potentials in this field, we argue that this union will contribute significantly to the development of the next-stage learning format in education.

Using the full potential of LLMs in higher education is hindered by challenges with access to LLMs. The two main access modes currently discussed are paying for a cloud-based LLM or providing a locally maintained open LLM. In this paper, we describe the current state of establishing an open LLM infrastructure at FernUniversit\"at in Hagen under the project name FLEXI (FernUni LLM Experimental Infrastructure). FLEXI enables experimentation within teaching and research with the goal of generating strongly needed evidence in favor (or against) the use of locally maintained open LLMs in higher education. The paper will provide some practical guidance for everyone trying to decide whether to run their own LLM server.