Lens: Rethinking Multilingual Enhancement for Large Language Models

Despite the growing global demand for large language models (LLMs) that serve users from diverse linguistic backgrounds, most cutting-edge LLMs remain predominantly English-centric. This creates a performance gap across languages, restricting access to advanced AI services for non-English speakers. Current methods to enhance multilingual capabilities largely rely on data-driven post-training techniques, such as multilingual instruction tuning or continual pre-training. However, these approaches encounter significant challenges, including the scarcity of high-quality multilingual datasets and the limited enhancement of multilingual capabilities. They often suffer from off-target issues and catastrophic forgetting of central language abilities. To this end, we propose Lens, a novel approach to enhance multilingual capabilities of LLMs by leveraging their internal language representation spaces. Specially, Lens operates by manipulating the hidden representations within the language-agnostic and language-specific subspaces from top layers of LLMs. Using the central language as a pivot, the target language is drawn closer to it within the language-agnostic subspace, allowing it to inherit well-established semantic representations. Meanwhile, in the language-specific subspace, the representations of the target and central languages are pushed apart, enabling the target language to express itself distinctly. Extensive experiments on one English-centric and two multilingual LLMs demonstrate that Lens effectively improves multilingual performance without sacrificing the original central language capabilities of the backbone model, achieving superior results with much fewer computational resources compared to existing post-training approaches.

Towards Comprehensive and Efficient Post Safety Alignment of Large Language Models via Safety Patching

Safety alignment of large language models (LLMs) has been gaining increasing attention. However, current safety-aligned LLMs suffer from the fragile and imbalanced safety mechanisms, which can still be induced to generate unsafe responses, exhibit over-safety by rejecting safe user inputs, and fail to preserve general utility after safety alignment. To this end, we propose a novel post safety alignment (PSA) method to address these inherent and emerging safety challenges, including safety enhancement, over-safety mitigation, and utility preservation. In specific, we introduce \textsc{SafePatching}, a novel framework for comprehensive and efficient PSA, where two distinct safety patches are developed on the harmful data to enhance safety and mitigate over-safety concerns, and then seamlessly integrated into the target LLM backbone without compromising its utility. Extensive experiments show that \textsc{SafePatching} achieves a more comprehensive and efficient PSA than baseline methods. It even enhances the utility of the backbone, further optimizing the balance between being helpful and harmless in current aligned LLMs. Also, \textsc{SafePatching} demonstrates its superiority in continual PSA scenarios.

Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence

Emotional Intelligence (EI), consisting of emotion perception, emotion cognition and emotion expression, plays the critical roles in improving user interaction experience for the current large language model (LLM) based conversational general AI assistants. Previous works mainly focus on raising the emotion perception ability of them via naive fine-tuning on EI-related classification or regression tasks. However, this leads to the incomplete enhancement of EI and catastrophic forgetting of the general intelligence (GI). To this end, we first introduce \textsc{EiBench}, a large-scale collection of EI-related tasks in the text-to-text formation with task instructions that covers all three aspects of EI, which lays a solid foundation for the comprehensive EI enhancement of LLMs. Then a novel \underline{\textbf{Mo}}dular \underline{\textbf{E}}motional \underline{\textbf{I}}ntelligence enhancement method (\textbf{MoEI}), consisting of Modular Parameter Expansion and intra-inter modulation, is proposed to comprehensively enhance the EI of LLMs without compromise their GI. Extensive experiments on two representative LLM-based assistants, Flan-T5 and LLaMA-2-Chat, demonstrate the effectiveness of MoEI to improving EI while maintain GI.

DAPT: A Dual Attention Framework for Parameter-Efficient Continual Learning of Large Language Models

The continual learning (CL) ability is vital for deploying large language models (LLMs) in the dynamic world. Based on parameter-efficient tuning (PET), existing methods devise the learning module and the selection module to handle the challenges of catastrophic forgetting (CF) and knowledge transfer (KT) in CL. The learning module allocates separate PET blocks for each continually emerged task and the selection module function to choose the correct one for the input at testing time. However, there are limitations in their deigns of both modules and they ignore the potential of aligning the two module to address CF and KT simultaneously. To this end, we propose a novel Dual Attention Framework , to align the PET learning and selection via the Dual Attentive Learning\&Selection module. Extensive Experiments on two CL benchmarks demonstrate the superiority of DAPT to resist CF and facilitate KT at the same time. Moreover, DAPT exhibits the superiority when we scale it to different model sizes (from 770M to 11B) and unseen tasks.

Wireless Powered Short Packet Communications with Multiple WPT Sources

We study a multi-source wireless power transfer (WPT) enabled network supporting multi-sensor transmissions. Activated by energy harvesting (EH) from multiple WPT sources, sensors transmit short packets to a destination with finite blocklength (FBL) codes. This work for the first time characterizes the FBL reliability for such multi-source WPT enabled network and provides reliability-oriented resource allocation designs, while a practical nonlinear EH model is considered. For scenario with a fixed frame structure, we maximize the FBL reliability via optimally allocating the transmit power among multi-source. In particular, we first investigate the relationship between the FBL reliability and multiple WPT source power, based on which a power allocation problem is formulated. To solve the formulated non-convex problem, we introduce auxiliary variables and apply successive convex approximation (SCA) technique to the non-convex component. Consequently, a sub-optimal solution can be obtained. Moreover, we extend our design into a dynamic frame structure scenario, i.e., the blocklength allocated for WPT phase and short-packet transmission phase are adjustable, which introduces more flexibility and new challenges to the system design. We provide a joint power and blocklength allocation design to minimize the system overall error probability under the total power and blocklength constraints. To address the high-dimensional optimization problem, auxiliary variables introduction, multiple variable substitutions and SCA technique utilization are exploited to reformulate and efficiently solve the problem. Finally, through numerical results, we validate our analytical model and evaluate the system performance, where a set of guidelines for practical system design are concluded.

Deep Reinforcement Learning based Joint Active and Passive Beamforming Design for RIS-Assisted MISO Systems

Owing to the unique advantages of low cost and controllability, reconfigurable intelligent surface (RIS) is a promising candidate to address the blockage issue in millimeter wave (mmWave) communication systems, consequently has captured widespread attention in recent years. However, the joint active beamforming and passive beamforming design is an arduous task due to the high computational complexity and the dynamic changes of wireless environment. In this paper, we consider a RIS-assisted multi-user multiple-input single-output (MU-MISO) mmWave system and aim to develop a deep reinforcement learning (DRL) based algorithm to jointly design active hybrid beamformer at the base station (BS) side and passive beamformer at the RIS side. By employing an advanced soft actor-critic (SAC) algorithm, we propose a maximum entropy based DRL algorithm, which can explore more stochastic policies than deterministic policy, to design active analog precoder and passive beamformer simultaneously. Then, the digital precoder is determined by minimum mean square error (MMSE) method. The experimental results demonstrate that our proposed SAC algorithm can achieve better performance compared with conventional optimization algorithm and DRL algorithm.

DRL-based Joint Beamforming and BS-RIS-UE Association Design for RIS-Assisted mmWave Networks

Reconfigurable intelligent surface (RIS) is considered as an extraordinarily promising technology to solve the blockage problem of millimeter wave (mmWave) communications owing to its capable of establishing a reconfigurable wireless propagation. In this paper, we focus on a RIS-assisted mmWave communication network consisting of multiple base stations (BSs) serving a set of user equipments (UEs). Considering the BS-RIS-UE association problem which determines that the RIS should assist which BS and UEs, we joint optimize BS-RIS-UE association and passive beamforming at RIS to maximize the sum-rate of the system. To solve this intractable non-convex problem, we propose a soft actor-critic (SAC) deep reinforcement learning (DRL)-based joint beamforming and BS-RIS-UE association design algorithm, which can learn the best policy by interacting with the environment using less prior information and avoid falling into the local optimal solution by incorporating with the maximization of policy information entropy. The simulation results demonstrate that the proposed SAC-DRL algorithm can achieve significant performance gains compared with benchmark schemes.