The current Large Language Models (LLMs) face significant challenges in improving their performance on low-resource languages and urgently need data-efficient methods without costly fine-tuning.From the perspective of language-bridge, we propose a simple yet effective method, namely BridgeX-ICL, to improve the zero-shot Cross-lingual In-Context Learning (X-ICL) for low-resource languages.Unlike existing works focusing on language-specific neurons, BridgeX-ICL explores whether sharing neurons can improve cross-lingual performance in LLMs.We construct neuron probe data from the groundtruth MUSE bilingual dictionaries, and define a subset of language overlap neurons accordingly to ensure full activation of these anchored neurons.Subsequently, we propose an HSIC-based metric to quantify LLMs' internal linguistic spectrum based on overlapping neurons, guiding optimal bridge selection.The experiments conducted on 4 crosslingual tasks and 15 language pairs from 7 diverse families, covering both high-low and moderate-low pairs, validate the effectiveness of BridgeX-ICL and offer empirical insights into the underlying multilingual mechanisms of LLMs.

Abstract Based on the foundation of Large Language Models (LLMs), Multilingual LLMs (MLLMs) have been developed to address the challenges faced in multilingual natural language processing, hoping to achieve knowledge transfer from high-resource languages to low-resource languages. However, significant limitations and challenges still exist, such as language imbalance, multilingual alignment, and inherent bias. In this paper, we aim to provide a comprehensive analysis of MLLMs, delving deeply into discussions surrounding these critical issues. First of all, we start by presenting an overview of MLLMs, covering their evolutions, key techniques, and multilingual capacities. Secondly, we explore the multilingual training corpora of MLLMs and the multilingual datasets oriented for downstream tasks that are crucial to enhance the cross-lingual capability of MLLMs. Thirdly, we survey the state-of-the-art studies of multilingual representations and investigate whether the current MLLMs can learn a universal language representation. Fourthly, we discuss bias on MLLMs, including its categories, evaluation metrics, and debiasing techniques. Finally, we discuss existing challenges and point out promising research directions of MLLMs.

Unsupervised bilingual lexicon induction (BLI) task aims to find word translations between languages and has achieved great success in similar language pairs.However, related works mostly rely on a single linear mapping for language alignment and fail on distant or lowresource language pairs, achieving less than half the performance observed in similar language pairs.In this paper, we introduce DM-BLI, a Dynamic Multiple subspaces alignment framework for unsupervised BLI.DM-BLI improves language alignment by utilizing multiple subspace alignments instead of a single mapping.We begin via unsupervised clustering to discover subspaces in source embedding space.Then we identify corresponding subspaces in the target space using a rough global alignment.DM-BLI further employs intra-cluster and inter-cluster contrastive learning to refine precise alignment for each subspace pair.Experiments conducted on standard BLI datasets for 12 language pairs (6 richresource and 6 low-resource) demonstrate substantial gains achieved by our framework.We release our code at https://github.com/huling- 2/DM-BLI.git.

Abstract Cross-lingual sentiment analysis (CLSA) leverages one or several source languages to help the low-resource languages to perform sentiment analysis. Therefore, the problem of lack of annotated corpora in many non-English languages can be alleviated. Along with the development of economic globalization, CLSA has attracted much attention in the field of sentiment analysis and the last decade has seen a surge of researches in this area. Numerous methods, datasets and evaluation metrics have been proposed in the literature, raising the need for a comprehensive and updated survey. This paper fills the gap by reviewing the state-of-the-art CLSA approaches from 2004 to the present. This paper teases out the research context of cross-lingual sentiment analysis and elaborates the following methods in detail: (1) The early main methods of CLSA, including those based on Machine Translation and its improved variants, parallel corpora or bilingual sentiment lexicon; (2) CLSA based on cross-lingual word embedding; (3) CLSA based on multi-BERT and other pre-trained models. We further analyze their main ideas, methodologies, shortcomings, etc., and attempt to reach a conclusion on the coverage of languages, datasets and their performance. Finally, we look into the future development of CLSA and the challenges facing the research area.

Information Centric Networking (ICN) leverages built-in caching capacity, termed as in-network caching, to support fast and efficient content distribution. The profits of ICN brought by its widespread in-network caching infrastructures has been well explored, but how to incentivize network players to deploy the socially optimal number of caches was largely ignored. Network players might not want to deploy or contribute their cache resources, if they do not have clear economic incentives, as cache deployment implies an extra capital expenditure. In this paper, we focus on the economic incentive interactions in caching deployment and usage between several types of network players in ICN. In particular, a Stackerlberg game model is used to capture the interactions between content provider (CP) and Internet service providers (ISPs). By using backward induction, it is proven that an equilibrium of the proposed model exists, under which both ISPs and CP can achieve their maximum utility. Numerical results show the effectiveness of the proposed model and the findings can provide important insights for network players to design efficient content sharing and caching schemes.

Content-Centric Networking (CCN) proposals rethink the communication model around named data. In-network caching is a fundamental feature to distinguish the CCN from the current host-centric IP network. Caching scheme by hash-routing is a prominent solution as it enables a joint consideration of content placement and request-to-cache routing through a hash function, and therefore, makes the cached contents visible in the domain and meanwhile, eliminates the content redundancy. In this paper, we present here a collaborative caching scheme in a CCN AS domain, which can fully exploit in-network caching by network clustering and hash-routing. Specifically, a heuristic algorithm is proposed to dynamically adjust caching capacity of each cluster based on its egress traffic while controlling the total path stretch incurred. The proposed scheme can improve the caching utility and reduce caching redundancy. Extensive experiments have been performed to evaluate the proposed scheme. Simulation results show that the proposed is effective and outperforms the existing caching mechanisms in CCN.

To reduce data access latency, network traffic volume and server load, in-network caching was proposed and has become an intrinsic component of the content-centric network (CCN) architecture. The content-oriented characteristics of in-network caching, such as arbitrary topology, volatile content locations and line speed requirements, make routers content-aware and supportive of fast content distribution. Meanwhile, they also raise new challenges in content placement and request routing, namely, how to optimally make content storage decisions and provision individual router's bandwidth to serve user requests, so as to minimize the bandwidth cost under storage and link capacity limit. To address this problem, we build a distributed in-network caching model to formulate the content placement and request routing in CCN, aiming at minimizing the bandwidth cost with strict storage and bandwidth constraints. Based on the proposed model, we design a scalable, adaptive and low-complexity in-network caching scheme for content placement and request routing and analyze the performance gains via simulations on a real ISP network topology and traffic traces. The experimental results show the proposed model and scheme are superior. Compared with the existing works, we also observe significant performance enhancements in terms of hit ratio of requests, reduction of server load, and bandwidth cost.

Content Centric Networking (CCN) is an emerging next-generation network infrastructure around content dissemination and retrieval, shifting from physical locations to named data. The built-in caching capacity of CCN, termed as in-network caching, promises to enable fast and effective content distribution at a global scale. Because of the in-network caching, the caching strategy of content location potentially affects how to make content searching decisions, while content searching in return decides in which routers content are stored. The relationship between content caching location and content searching has not been fully exploited in CCN or further used for the whole network performance improvement. This paper exploits the content caching location and content searching mechanism of CCN, and proposes a Popularity-driven content Caching Location and Searching scheme (P-CLS) in CCN. P-CLS leverages content access popularity to realize diverse content distribution and reduce content caching redundancy, which also overcomes the oscillation and frequent replacement phenomenon in the existing content caching and searching (CLS) scheme. Extensive simulations via hierarchical and arbitrary caching topologies show that the proposed scheme outperforms the existing caching algorithms.

To reduce network access latency, network traffic volume, and server load, caching capacity was proposed as a component of eNodeBs in the radio access network (RAN). These eNodeB caches require less transport energy but bring additional caching energy through providing each eNodeB with caching capacity. It is thus challenging for eNodeBs to make content placement and request routing decisions so as to minimize the total energy consumption, especially when considering different caching hardware technologies, arrival rate of requests and content popularity. To address this problem, we first build an energy model to formulate the problem of minimizing energy consumption at eNodeB caches. Then a Lagrangian relaxation technique is adopted to find a near-optimal solution to the proposed model. Based on the proposed model and the obtained solution, we design a practical scheme for coordinating the content placement and request routing, and thus ensure the minimum-energy eNodeB caches. Compared with the existing works, our proposal significantly reduces the energy consumption by approximately 28% while keeps a good network performance. Our results also indicate that caching hardware technologies and content popularity greatly affect the content placement, therefore are crucial to the energy efficiency of eNodeB caches.

Information-Centric Networking (ICN) enables caching of addressable content chunks in every cache-equipped router. So it is crucial to make the cached content to be visible locally, in order to satisfy the subsequent request. We achieve this goal in this paper with a novel caching scheme, which combines the content placement with dynamic request routing by selectively creating trails along the content delivery path. In addition, in-network caching requires search or replacement of cached chunks at line-speed, which resorts to the low complexity collaborative caching scheme and limits the cache size at each network level. Coordinate with the feasible cache size allocation, the proposed scheme automatically distributes the content to the proper cache location according to its popularity. Therefore, the proposed self assembly caching scheme could reduce caching redundancy and in turn, make more efficient utilization of available cache resources. The simulation results show that the proposed scheme outperforms existing algorithms.

Content Centric Networking (CCN) is a new emerging network architecture, shifting from an end-to-end connection to a content-centric communication model. A number of content-oriented characteristics, such as name-based routing, arbitrary topology and ubiquitous caching make caching in CCN different from the previous works. In this paper, we focus on the collaborative caching in CCN and propose a dominating-set-based collaborative caching mechanism, which jointly considers the content placement and request routing in a tightly-couple manner. Extensive experiments have been performed to evaluate the proposed scheme. Simulation results show that the proposed CollaCache proposal outperforms the existing caching and routing mechanisms in CCN.