arXiv subjects

Zheng Chu

Publications and source records attributed to Zheng Chu.

At least 37 records · Page 2Linked to original sources

arXiv2024

Learning to Break: Knowledge-Enhanced Reasoning in Multi-Agent Debate System

Multi-agent debate system (MAD) imitating the process of human discussion in pursuit of truth, aims to align the correct cognition of different agents for the optimal solution. It is challenging to make various agents perform right and highly consistent cognition due to their limited and different knowledge backgrounds (i.e., cognitive islands), which hinders the search for the optimal solution. To address the challenge, we propose a novel \underline{M}ulti-\underline{A}gent \underline{D}ebate with \underline{K}nowledge-\underline{E}nhanced framework (\textbf{MADKE}) to promote the system to find the solution. First, we involve a shared retrieval knowledge pool in the debate process to solve the problem of limited and different knowledge backgrounds. Then, we propose an adaptive knowledge selection method to guarantee the accuracy and personalization of knowledge. This method allows agents to choose whether to use external knowledge in each conversation round according to their own needs. Our experimental results on six datasets show that our method achieves state-of-the-art results compared to existing single-agent and multi-agent methods. Further analysis reveals that the introduction of retrieval knowledge can help the agent to break cognitive islands in the debate process and effectively improve the consistency and correctness of the model. Moreover, MADKE using Qwen1.5-72B-Chat surpasses GPT-4 by +1.26\% on average in six datasets, which validates that our method can help open-source LLMs achieve or even surpass the performance of GPT-4. Our code is available at \url{https://github.com/FutureForMe/MADKE}.

cs.CL↗

arXiv2024

An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented Generation

Retrieval-augmented generation integrates the capabilities of large language models with relevant information retrieved from an extensive corpus, yet encounters challenges when confronted with real-world noisy data. One recent solution is to train a filter module to find relevant content but only achieve suboptimal noise compression. In this paper, we propose to introduce the information bottleneck theory into retrieval-augmented generation. Our approach involves the filtration of noise by simultaneously maximizing the mutual information between compression and ground output, while minimizing the mutual information between compression and retrieved passage. In addition, we derive the formula of information bottleneck to facilitate its application in novel comprehensive evaluations, the selection of supervised fine-tuning data, and the construction of reinforcement learning rewards. Experimental results demonstrate that our approach achieves significant improvements across various question answering datasets, not only in terms of the correctness of answer generation but also in the conciseness with $2.5\%$ compression rate.

cs.CL↗

arXiv2024

TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models

Grasping the concept of time is a fundamental facet of human cognition, indispensable for truly comprehending the intricacies of the world. Previous studies typically focus on specific aspects of time, lacking a comprehensive temporal reasoning benchmark. To address this, we propose TimeBench, a comprehensive hierarchical temporal reasoning benchmark that covers a broad spectrum of temporal reasoning phenomena. TimeBench provides a thorough evaluation for investigating the temporal reasoning capabilities of large language models. We conduct extensive experiments on GPT-4, LLaMA2, and other popular LLMs under various settings. Our experimental results indicate a significant performance gap between the state-of-the-art LLMs and humans, highlighting that there is still a considerable distance to cover in temporal reasoning. Besides, LLMs exhibit capability discrepancies across different reasoning categories. Furthermore, we thoroughly analyze the impact of multiple aspects on temporal reasoning and emphasize the associated challenges. We aspire for TimeBench to serve as a comprehensive benchmark, fostering research in temporal reasoning. Resources are available at: https://github.com/zchuz/TimeBench

cs.CL↗

arXiv2024

BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering

Large language models (LLMs) have demonstrated strong reasoning capabilities. Nevertheless, they still suffer from factual errors when tackling knowledge-intensive tasks. Retrieval-augmented reasoning represents a promising approach. However, significant challenges still persist, including inaccurate and insufficient retrieval for complex questions, as well as difficulty in integrating multi-source knowledge. To address this, we propose Beam Aggregation Reasoning, BeamAggR, a reasoning framework for knowledge-intensive multi-hop QA. BeamAggR explores and prioritizes promising answers at each hop of question. Concretely, we parse the complex questions into trees, which include atom and composite questions, followed by bottom-up reasoning. For atomic questions, the LLM conducts reasoning on multi-source knowledge to get answer candidates. For composite questions, the LLM combines beam candidates, explores multiple reasoning paths through probabilistic aggregation, and prioritizes the most promising trajectory. Extensive experiments on four open-domain multi-hop reasoning datasets show that our method significantly outperforms SOTA methods by 8.5%. Furthermore, our analysis reveals that BeamAggR elicits better knowledge collaboration and answer aggregation.

cs.CL↗

arXiv2024

GUIDE: A Guideline-Guided Dataset for Instructional Video Comprehension

There are substantial instructional videos on the Internet, which provide us tutorials for completing various tasks. Existing instructional video datasets only focus on specific steps at the video level, lacking experiential guidelines at the task level, which can lead to beginners struggling to learn new tasks due to the lack of relevant experience. Moreover, the specific steps without guidelines are trivial and unsystematic, making it difficult to provide a clear tutorial. To address these problems, we present the GUIDE (Guideline-Guided) dataset, which contains 3.5K videos of 560 instructional tasks in 8 domains related to our daily life. Specifically, we annotate each instructional task with a guideline, representing a common pattern shared by all task-related videos. On this basis, we annotate systematic specific steps, including their associated guideline steps, specific step descriptions and timestamps. Our proposed benchmark consists of three sub-tasks to evaluate comprehension ability of models: (1) Step Captioning: models have to generate captions for specific steps from videos. (2) Guideline Summarization: models have to mine the common pattern in task-related videos and summarize a guideline from them. (3) Guideline-Guided Captioning: models have to generate captions for specific steps under the guide of guideline. We evaluate plenty of foundation models with GUIDE and perform in-depth analysis. Given the diversity and practicality of GUIDE, we believe that it can be used as a better benchmark for instructional video comprehension.

cs.CV↗

arXiv2024

Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future

Reasoning, a fundamental cognitive process integral to human intelligence, has garnered substantial interest within artificial intelligence. Notably, recent studies have revealed that chain-of-thought prompting significantly enhances LLM's reasoning capabilities, which attracts widespread attention from both academics and industry. In this paper, we systematically investigate relevant research, summarizing advanced methods through a meticulous taxonomy that offers novel perspectives. Moreover, we delve into the current frontiers and delineate the challenges and future directions, thereby shedding light on future research. Furthermore, we engage in a discussion about open questions. We hope this paper serves as an introduction for beginners and fosters future research. Resources have been made publicly available at https://github.com/zchuz/CoT-Reasoning-Survey

cs.CL↗

arXiv2024

Intelligent Reflecting Surface Assisted Integrated Sensing and Communications for mmWave Channels

This paper proposes an intelligent reflecting surface (IRS) assisted integrated sensing and communication (ISAC) system operating at the millimeter-wave (mmWave) band. Specifically, the ISAC system combines communication and radar operations and performs, detecting and communicating simultaneously with multiple targets and users. The IRS dynamically controls the amplitude or phase of the radio signal via reflecting elements to reconfigure the radio propagation environment and enhance the transmission rate of the ISAC system. By jointly designing the radar signal covariance (RSC) matrix, the beamforming vector of the communication system, and the IRS phase shift, the ISAC system transmission rate can be improved while matching the desired waveform for radar. The problem is non-convex due to multivariate coupling, and thus we decompose it into two separate subproblems. First, a closed-form solution of the RSC matrix is derived from the desired radar waveform. Next, the quadratic transformation (QT) technique is applied to the subproblem, and then alternating optimization (AO) is employed to determine the communication beamforming vector and the IRS phase shift. For computing the IRS phase shift, we adopt both the majorization minimization (MM) and the manifold optimization (MO). Also, we derive a closed-form solution for the formulated problem, effectively decreasing computational complexity. Furthermore, a trade-off factor is introduced to balance the performance of communication and sensing. Finally, the simulations verify the effectiveness of the algorithm and demonstrate that the IRS can improve the performance of the ISAC system.

eess.SP↗

arXiv2023

Intelligent Reflective Surface Assisted Integrated Sensing and Wireless Power Transfer

Wireless sensing and wireless energy are enablers to pave the way for smart transportation and a greener future. In this paper, an intelligent reflecting surface (IRS) assisted integrated sensing and wireless power transfer (ISWPT) system is investigated, where the transmitter in transportation infrastructure networks sends signals to sense multiple targets and simultaneously to multiple energy harvesting devices (EHDs) to power them. In light of the performance tradeoff between energy harvesting and sensing, we propose to jointly optimize the system performance via optimizing the beamforming and IRS phase shift. However, the coupling of optimization variables makes the formulated problem non-convex. Thus, an alternative optimization approach is introduced and based on which two algorithms are proposed to solve the problem. Specifically, the first one involves a semi-definite program technique, while the second one features a low-complexity optimization algorithm based on successive convex approximation and majorization minimization. Our simulation results validate the proposed algorithms and demonstrate the advantages of using IRS to assist wireless power transfer in ISWPT systems.

eess.SP↗

arXiv2023

MTGER: Multi-view Temporal Graph Enhanced Temporal Reasoning over Time-Involved Document

The facts and time in the document are intricately intertwined, making temporal reasoning over documents challenging. Previous work models time implicitly, making it difficult to handle such complex relationships. To address this issue, we propose MTGER, a novel Multi-view Temporal Graph Enhanced Temporal Reasoning framework for temporal reasoning over time-involved documents. Concretely, MTGER explicitly models the temporal relationships among facts by multi-view temporal graphs. On the one hand, the heterogeneous temporal graphs explicitly model the temporal and discourse relationships among facts; on the other hand, the multi-view mechanism captures both time-focused and fact-focused information, allowing the two views to complement each other through adaptive fusion. To further improve the implicit reasoning capability of the model, we design a self-supervised time-comparing objective. Extensive experimental results demonstrate the effectiveness of our method on the TimeQA and SituatedQA datasets. Furthermore, MTGER gives more consistent answers under question perturbations.

cs.CL↗

arXiv2023

Resource Allocation for RIS-Empowered Wireless Communications: Low-Complexity and Robust Designs

This article delves into advancements in resource allocation techniques tailored for systems utilizing reconfigurable intelligent surfaces (RIS), with a primary focus on achieving low-complexity and resilient solutions. The investigation of low-complexity approaches for RIS holds significant relevance, primarily owing to the intricate characteristics inherent in RIS-based systems and the need of deploying large-scale RIS arrays. Concurrently, the exploration of robust solutions aims to address the issue of hardware impairments occurring at both the transceivers and RIS components in practical RIS-assisted systems. In the realm of both low-complexity and robust resource allocation, this article not only elucidates the fundamental techniques underpinning these methodologies but also offers comprehensive numerical results for illustrative purposes. The necessity of adopting resource allocation strategies that are both low in complexity and resilient is thoroughly established. Ultimately, this article provides prospective research avenues in the domain of low-complexity and robust resource allocation techniques tailored for RIS-assisted systems.

cs.IT↗

arXiv2023

STAR-RIS-Assisted-Full-Duplex Jamming Design for Secure Wireless Communications System

Physical layer security (PLS) technologies are expected to play an important role in the next-generation wireless networks, by providing secure communication to protect critical and sensitive information from illegitimate devices. In this paper, we propose a novel secure communication scheme where the legitimate receiver use full-duplex (FD) technology to transmit jamming signals with the assistance of simultaneous transmitting and reflecting reconfigurable intelligent surface (STARRIS) which can operate under the energy splitting (ES) model and the mode switching (MS) model, to interfere with the undesired reception by the eavesdropper. We aim to maximize the secrecy capacity by jointly optimizing the FD beamforming vectors, amplitudes and phase shift coefficients for the ESRIS, and mode selection and phase shift coefficients for the MS-RIS. With above optimization, the proposed scheme can concentrate the jamming signals on the eavesdropper while simultaneously eliminating the self-interference (SI) in the desired receiver. To tackle the coupling effect of multiple variables, we propose an alternating optimization algorithm to solve the problem iteratively. Furthermore, we handle the non-convexity of the problem by the the successive convex approximation (SCA) scheme for the beamforming optimizations, amplitudes and phase shifts optimizations for the ES-RIS, as well as the phase shifts optimizations for the MS-RIS. In addition, we adopt a semi-definite relaxation (SDR) and Gaussian randomization process to overcome the difficulty introduced by the binary nature of mode optimization of the MS-RIS. Simulation results validate the performance of our proposed schemes as well as the efficacy of adapting both two types of STAR-RISs in enhancing secure communications when compared to the traditional selfinterference cancellation technology.

cs.IT↗

arXiv2023

Resource Management for IRS-assisted WP-MEC Networks with Practical Phase Shift Model

Wireless powered mobile edge computing (WP-MEC) has been recognized as a promising solution to enhance the computational capability and sustainable energy supply for low-power wireless devices (WDs). However, when the communication links between the hybrid access point (HAP) and WDs are hostile, the energy transfer efficiency and task offloading rate are compromised. To tackle this problem, we propose to employ multiple intelligent reflecting surfaces (IRSs) to WP-MEC networks. Based on the practical IRS phase shift model, we formulate a total computation rate maximization problem by jointly optimizing downlink/uplink IRSs passive beamforming, downlink energy beamforming and uplink multi-user detection (MUD) vector at HAPs, task offloading power and local computing frequency of WDs, and the time slot allocation. Specifically, we first derive the optimal time allocation for downlink wireless energy transmission (WET) to IRSs and the corresponding energy beamforming. Next, with fixed time allocation for the downlink WET to WDs, the original optimization problem can be divided into two independent subproblems. For the WD charging subproblem, the optimal IRSs passive beamforming is derived by utilizing the successive convex approximation (SCA) method and the penalty-based optimization technique, and for the offloading computing subproblem, we propose a joint optimization framework based on the fractional programming (FP) method. Finally, simulation results validate that our proposed optimization method based on the practical phase shift model can achieve a higher total computation rate compared to the baseline schemes.

cs.IT↗

arXiv2023

Exploring & Exploiting High-Order Graph Structure for Sparse Knowledge Graph Completion

Sparse knowledge graph (KG) scenarios pose a challenge for previous Knowledge Graph Completion (KGC) methods, that is, the completion performance decreases rapidly with the increase of graph sparsity. This problem is also exacerbated because of the widespread existence of sparse KGs in practical applications. To alleviate this challenge, we present a novel framework, LR-GCN, that is able to automatically capture valuable long-range dependency among entities to supplement insufficient structure features and distill logical reasoning knowledge for sparse KGC. The proposed approach comprises two main components: a GNN-based predictor and a reasoning path distiller. The reasoning path distiller explores high-order graph structures such as reasoning paths and encodes them as rich-semantic edges, explicitly compositing long-range dependencies into the predictor. This step also plays an essential role in densifying KGs, effectively alleviating the sparse issue. Furthermore, the path distiller further distills logical reasoning knowledge from these mined reasoning paths into the predictor. These two components are jointly optimized using a well-designed variational EM algorithm. Extensive experiments and analyses on four sparse benchmarks demonstrate the effectiveness of our proposed method.

cs.AI↗

arXiv2023

Sum Secrecy Rate Maximization for IRS-aided Multi-Cluster MIMO-NOMA Terahertz Systems

Intelligent reflecting surface (IRS) is a promising technique to extend the network coverage and improve spectral efficiency. This paper investigates an IRS-assisted terahertz (THz) multiple-input multiple-output (MIMO)-nonorthogonal multiple access (NOMA) system based on hybrid precoding with the presence of eavesdropper. Two types of sparse RF chain antenna structures are adopted, i.e., sub-connected structure and fully connected structure. First, cluster heads are selected for each beam, and analog precoding based on discrete phase is designed. Then, users are clustered based on channel correlation, and NOMA technology is employed to serve the users. In addition, a low-complexity forced-zero method is utilized to design digital precoding in order to eliminate inter-cluster interference. On this basis, we propose a secure transmission scheme to maximize the sum secrecy rate by jointly optimizing the power allocation and phase shifts of IRS subject to the total transmit power budget, minimal achievable rate requirement of each user, and IRS reflection coefficients. Due to multiple coupled variables, the formulated problem leads to a non-convex issue. We apply the Taylor series expansion and semidefinite programming to convert the original non-convex problem into a convex one. Then, an alternating optimization algorithm is developed to obtain a feasible solution of the original problem. Simulation results verify the convergence of the proposed algorithm, and deploying IRS can bring significant beamforming gains to suppress the eavesdropping.

cs.IT↗

arXiv2022

A Framework for Simulating Real-world Stream Data of the Internet of Things

With the rapid growth in the number of devices of the Internet of Things (IoT), the volume and types of stream data are rapidly increasing in the real world. Unfortunately, the stream data has the characteristics of infinite and periodic volatility in the real world, which cause problems with the inefficient stream processing tasks. In this study, we report our recent efforts on this issue, with a focus on simulating stream data. Firstly, we explore the characteristics of the real-world stream data of the IoT, which helps us to understand the stream data in the real world. Secondly, the pipeline of simulating stream data is proposed, which can accurately and efficiently simulate the characteristics of the stream data to improve efficiency for specific tasks. Finally, we design and implement a novel framework that can simulate various stream data for related stream processing tasks. To verify the validity of the proposed framework, we apply this framework to stream processing task running in the stream processing system. The experimental results reveal that the related stream processing task is accelerated by at least 24 times using our proposed simulation framework with the premise of ensuring volatility and trends of stream data.

cs.PF↗

arXiv2022

The Far-/Near-Field Beam Squint and Solutions for THz Intelligent Reflecting Surface Communications

Terahertz (THz) and intelligent reflecting surface (IRS) have been regarded as two promising technologies to improve the capacity and coverage for future 6G networks. Generally, IRS is usually equipped with large-scale elements when implemented at THz frequency. In this case, the near-field model and beam squint should be considered. Therefore, in this paper, we investigate the far-field and near-field beam squint problems in THz IRS communications for the first time. The far-field and near-field channel models are constructed based on the different electromagnetic radiation characteristics. Next, we first analyze the far-field beam squint and its effect for the beam gain based on the cascaded base station (BS)-IRS-user channel model, and then the near-field case is studied. To overcome the far-field and near-field beam squint effects, we propose to apply delay adjustable metasurface (DAM) to IRS, and develop a scheme of optimizing the reflecting phase shifts and time delays of IRS elements, which effectively eliminates the beam gain loss caused by beam squint. Finally, simulations are conducted to demonstrate the effectiveness of our proposed schemes in combating the near and far field beam squint.

cs.IT↗

arXiv2022

HIT at SemEval-2022 Task 2: Pre-trained Language Model for Idioms Detection

The same multi-word expressions may have different meanings in different sentences. They can be mainly divided into two categories, which are literal meaning and idiomatic meaning. Non-contextual-based methods perform poorly on this problem, and we need contextual embedding to understand the idiomatic meaning of multi-word expressions correctly. We use a pre-trained language model, which can provide a context-aware sentence embedding, to detect whether multi-word expression in the sentence is idiomatic usage.

cs.CL↗

arXiv2022

Machine Learning-based Beamforming Design for Millimeter Wave IRS Communications with Discrete Phase Shifters

In this paper, we investigate an intelligent reflecting surface (IRS)-assisted millimeter-wave multiple-input single-output downlink wireless communication system. By jointly calculating the active beamforming at the base station and the passive beamforming at the IRS, we aim to minimize the transmit power under the constraint of each user' signal-to-interference-plus-noise ratio. To solve this problem, we propose a low-complexity machine learning-based cross-entropy (CE) algorithm to alternately optimize the active beamforming and the passive beamforming. Specifically, in the alternative iteration process, the zero-forcing (ZF) method and CE algorithm are applied to acquire the active beamforming and the passive beamforming, respectively. The CE algorithm starts with random sampling, by the idea of distribution focusing, namely shifting the distribution towards a desired one by minimizing CE, and a near optimal reflection coefficients with adequately high probability can be obtained. In addition, we extend the original one-bit phase shift at the IRS to the common case with high-resolution phase shift to enhance the effectiveness of the algorithms. Simulation results verify that the proposed algorithm can obtain a near optimal solution with lower computational complexity.

cs.IT↗