arXiv subjects

Bingbing Wang

Publications and source records attributed to Bingbing Wang.

At least 37 records · Page 2Linked to original sources

arXiv2025

Robust Outlier Detection and Low-Latency Concept Drift Adaptation for Data Stream Regression: A Dual-Channel Architecture

Outlier detection and concept drift detection represent two challenges in data analysis. Most studies address these issues separately. However, joint detection mechanisms in regression remain underexplored, where the continuous nature of output spaces makes distinguishing drifts from outliers inherently challenging. To address this, we propose a novel robust regression framework for joint outlier and concept drift detection. Specifically, we introduce a dual-channel decision process that orchestrates prediction residuals into two coupled logic flows: a rapid response channel for filtering point outliers and a deep analysis channel for diagnosing drifts. We further develop the Exponentially Weighted Moving Absolute Deviation with Distinguishable Types (EWMAD-DT) detector to autonomously differentiate between abrupt and incremental drifts via dynamic thresholding. Comprehensive experiments on both synthetic and real-world datasets demonstrate that our unified framework, enhanced by EWMAD-DT, exhibits superior detection performance even when point outliers and concept drifts coexist.

stat.ME↗

arXiv2025

CoreEval: Automatically Building Contamination-Resilient Datasets with Real-World Knowledge toward Reliable LLM Evaluation

Data contamination poses a significant challenge to the fairness of LLM evaluations in natural language processing tasks by inadvertently exposing models to test data during training. Current studies attempt to mitigate this issue by modifying existing datasets or generating new ones from freshly collected information. However, these methods fall short of ensuring contamination-resilient evaluation, as they fail to fully eliminate pre-existing knowledge from models or preserve the semantic complexity of the original datasets. To address these limitations, we propose \textbf{CoreEval}, a \textbf{Co}ntamination-\textbf{re}silient \textbf{Eval}uation strategy for automatically updating data with real-world knowledge. This approach begins by extracting entity relationships from the original data and leveraging the GDELT database to retrieve relevant, up-to-date knowledge. The retrieved knowledge is then recontextualized and integrated with the original data, which is refined and restructured to ensure semantic coherence and enhanced task relevance. Ultimately, a robust data reflection mechanism is employed to iteratively verify and refine labels, ensuring consistency between the updated and original datasets. Extensive experiments on updated datasets validate the robustness of CoreEval, demonstrating its effectiveness in mitigating performance overestimation caused by data contamination.

cs.CL↗

arXiv2025

Comprehensive and Efficient Distillation for Lightweight Sentiment Analysis Models

Recent efforts leverage knowledge distillation techniques to develop lightweight and practical sentiment analysis models. These methods are grounded in human-written instructions and large-scale user texts. Despite the promising results, two key challenges remain: (1) manually written instructions are limited in diversity and quantity, making them insufficient to ensure comprehensive coverage of distilled knowledge; (2) large-scale user texts incur high computational cost, hindering the practicality of these methods. To this end, we introduce CompEffDist, a comprehensive and efficient distillation framework for sentiment analysis. Our framework consists of two key modules: attribute-based automatic instruction construction and difficulty-based data filtering, which correspondingly tackle the aforementioned challenges. Applying our method across multiple model series (Llama-3, Qwen-3, and Gemma-3), we enable 3B student models to match the performance of 20x larger teacher models on most tasks. In addition, our approach greatly outperforms baseline methods in data efficiency, attaining the same performance level with only 10% of the data.

cs.CL↗

arXiv2025

Transfer Learning in Regression with Influential Points

Regression prediction plays a crucial role in practical applications and strongly relies on data annotation. However, due to prohibitive annotation costs or domain-specific constraints, labeled data in the target domain is often scarce, making transfer learning a critical solution by leveraging knowledge from resource-rich source domains. In the practical target scenario, although transfer learning has been widely applied, influential points can significantly distort parameter estimation for the target domain model. This issue is further compounded when influential points are also present in source domains, leading to aggravated performance degradation and posing critical robustness challenges for existing transfer learning frameworks. In this study, we innovatively introduce a transfer learning collaborative optimization (Trans-CO) framework for influential point detection and regression model fitting. Extensive simulation experiments demonstrate that the proposed Trans-CO algorithm outperforms competing methods in terms of model fitting performance and influential point identification accuracy. Furthermore, it achieves superior predictive accuracy on real-world datasets, providing a novel solution for transfer learning in regression with influential points

stat.ME↗

arXiv2025

Relaxation and Its Effects on Electronic Structure in Twisted Systems: An Analytical Perspective

Lattice relaxation profoundly reshapes electronic structures in twisted materials. Prevailing treatments, however, typically rely on large-scale density functional theory (DFT), which is computationally costly and mechanistically opaque. Here, we develop a unified analytical framework to overcome these limitations. From continuum elastic theory, we derive closed-form solutions for both in-plane and out-of-plane relaxation fields. We further introduce an analytical phase factor expansion theory that maps relaxation into the electronic Hamiltonian. By applying this framework, the relaxation-mediated single-particle and many-body topological phase transitions in twisted MoTe$_{2}$ is accurately captured, and the evolution of flat bands in magic-angle graphene is quantitatively reproduced. Our work transforms the research of moiré relaxation from black-box numerical fitting to an analytical paradigm, offering fundamental insights, exceptional efficiency, and general applicability to a wide range of twisted materials.

cond-mat.mtrl-sci↗

arXiv2025

GOSU: Retrieval-Augmented Generation with Global-Level Optimized Semantic Unit-Centric Framework

Building upon the standard graph-based Retrieval-Augmented Generation (RAG), the introduction of heterogeneous graphs and hypergraphs aims to enrich retrieval and generation by leveraging the relationships between multiple entities through the concept of semantic units (SUs). But this also raises a key issue: The extraction of high-level SUs limited to local text chunks is prone to ambiguity, complex coupling, and increased retrieval overhead due to the lack of global knowledge or the neglect of fine-grained relationships. To address these issues, we propose GOSU, a semantic unit-centric RAG framework that efficiently performs global disambiguation and utilizes SUs to capture interconnections between different nodes across the global context. In the graph construction phase, GOSU performs global merging on the pre-extracted SUs from local text chunks and guides entity and relationship extraction, reducing the difficulty of coreference resolution while uncovering global semantic objects across text chunks. In the retrieval and generation phase, we introduce hierarchical keyword extraction and semantic unit completion. The former uncovers the fine-grained binary relationships overlooked by the latter, while the latter compensates for the coarse-grained n-ary relationships missing from the former. Evaluation across multiple tasks demonstrates that GOSU outperforms the baseline RAG methods in terms of generation quality.

cs.CL↗

arXiv2025

MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents

Modern task-oriented dialogue (TOD) systems increasingly rely on large language model (LLM) agents, leveraging Retrieval-Augmented Generation (RAG) and long-context capabilities for long-term memory utilization. However, these methods are primarily based on semantic similarity, overlooking task intent and reducing task coherence in multi-session dialogues. To address this challenge, we introduce MemGuide, a two-stage framework for intent-driven memory selection. (1) Intent-Aligned Retrieval matches the current dialogue context with stored intent descriptions in the memory bank, retrieving QA-formatted memory units that share the same goal. (2) Missing-Slot Guided Filtering employs a chain-of-thought slot reasoner to enumerate unfilled slots, then uses a fine-tuned LLaMA-8B filter to re-rank the retrieved units by marginal slot-completion gain. The resulting memory units inform a proactive strategy that minimizes conversational turns by directly addressing information gaps. Based on this framework, we introduce the MS-TOD, the first multi-session TOD benchmark comprising 132 diverse personas, 956 task goals, and annotated intent-aligned memory targets, supporting efficient multi-session task completion. Evaluations on MS-TOD show that MemGuide raises the task success rate by 11% (88% -> 99%) and reduces dialogue length by 2.84 turns in multi-session settings, while maintaining parity with single-session benchmarks.

cs.CL↗

arXiv2025

Reply with Sticker: New Dataset and Model for Sticker Retrieval

Using stickers in online chatting is very prevalent on social media platforms, where the stickers used in the conversation can express someone's intention/emotion/attitude in a vivid, tactful, and intuitive way. Existing sticker retrieval research typically retrieves stickers based on context and the current utterance delivered by the user. That is, the stickers serve as a supplement to the current utterance. However, in the real-world scenario, using stickers to express what we want to say rather than as a supplement to our words only is also important. Therefore, in this paper, we create a new dataset for sticker retrieval in conversation, called \textbf{StickerInt}, where stickers are used to reply to previous conversations or supplement our words. Based on the created dataset, we present a simple yet effective framework for sticker retrieval in conversation based on the learning of intention and the cross-modal relationships between conversation context and stickers, coined as \textbf{Int-RA}. Specifically, we first devise a knowledge-enhanced intention predictor to introduce the intention information into the conversation representations. Subsequently, a relation-aware sticker selector is devised to retrieve the response sticker via cross-modal relationships. Extensive experiments on two datasets show that the proposed model achieves state-of-the-art performance and generalization capability in sticker retrieval. The dataset and source code of this work are released at https://github.com/HITSZ-HLT/Int-RA.

cs.MM↗

arXiv2025

One dimensional analytical solutions of the transport equations for incompressible magnetohydrodynamic (MHD) turbulence

We derive one dimensional (1D) analytical solutions for the transport equations of incompressible magnetohydrodynamic (MHD) turbulence developed by Zank et al. [2012], Adhikari et al. [2023], including the Elsässer energies and the correlation lengths. The solutions are suitable for an arbitrary given background convection speed and Alfvén speed profiles but require near equipartition of turbulent kinetic energy and magnetic field energy. These analytical solutions provide a simple tool to investigate the evolution of turbulence and resulting energetic particle diffusion coefficients in various space and astrophysical environments that possess simple geometry.

astro-ph.HE↗

arXiv2024

Exploring Context Window of Large Language Models via Decomposed Positional Vectors

Transformer-based large language models (LLMs) typically have a limited context window, resulting in significant performance degradation when processing text beyond the length of the context window. Extensive studies have been proposed to extend the context window and achieve length extrapolation of LLMs, but there is still a lack of in-depth interpretation of these approaches. In this study, we explore the positional information within and beyond the context window for deciphering the underlying mechanism of LLMs. By using a mean-based decomposition method, we disentangle positional vectors from hidden states of LLMs and analyze their formation and effect on attention. Furthermore, when texts exceed the context window, we analyze the change of positional vectors in two settings, i.e., direct extrapolation and context window extension. Based on our findings, we design two training-free context window extension methods, positional vector replacement and attention window extension. Experimental results show that our methods can effectively extend the context window length.

cs.CL↗

arXiv2024

Half-KFN: An Enhanced Detection Method for Subtle Covariate Drift

Detecting covariate drift is a common task of significant practical value in supervised learning. Once covariate drift occurs, the models may no longer be applicable, hence numerous studies have been devoted to the advancement of detection methods. However, current research methods are not particularly effective in handling subtle covariate drift when dealing with small proportions of drift samples. In this paper, inspired by the $k$-nearest neighbor (KNN) approach, a novel method called Half $k$-farthest neighbor (Half-KFN) is proposed in response to specific scenarios. Compared to traditional ones, Half-KFN exhibits higher power due to the inherent capability of the farthest neighbors which could better characterize the nature of drift. Furthermore, with larger sample sizes, the employment of the bootstrap for hypothesis testing is recommended. It is leveraged to calculate $p$-values dramatically faster than permutation tests, with speed undergoing an exponential growth as sample size increases. Numerical experiments on simulated and real data are conducted to evaluate our proposed method, and the results demonstrate that it consistently displays superior sensitivity and rapidity in covariate drift detection across various cases.

stat.ME↗

arXiv2024

Towards Real-World Stickers Use: A New Dataset for Multi-Tag Sticker Recognition

In real-world conversations, the diversity and ambiguity of stickers often lead to varied interpretations based on the context, necessitating the requirement for comprehensively understanding stickers and supporting multi-tagging. To address this challenge, we introduce StickerTAG, the first multi-tag sticker dataset comprising a collected tag set with 461 tags and 13,571 sticker-tag pairs, designed to provide a deeper understanding of stickers. Recognizing multiple tags for stickers becomes particularly challenging due to sticker tags usually are fine-grained attribute aware. Hence, we propose an Attentive Attribute-oriented Prompt Learning method, ie, Att$^2$PL, to capture informative features of stickers in a fine-grained manner to better differentiate tags. Specifically, we first apply an Attribute-oriented Description Generation (ADG) module to obtain the description for stickers from four attributes. Then, a Local Re-attention (LoR) module is designed to perceive the importance of local information. Finally, we use prompt learning to guide the recognition process and adopt confidence penalty optimization to penalize the confident output distribution. Extensive experiments show that our method achieves encouraging results for all commonly used metrics.

cs.MM↗

arXiv2024

MFA-Net: Multi-Scale feature fusion attention network for liver tumor segmentation

Segmentation of organs of interest in medical CT images is beneficial for diagnosis of diseases. Though recent methods based on Fully Convolutional Neural Networks (F-CNNs) have shown success in many segmentation tasks, fusing features from images with different scales is still a challenge: (1) Due to the lack of spatial awareness, F-CNNs share the same weights at different spatial locations. (2) F-CNNs can only obtain surrounding information through local receptive fields. To address the above challenge, we propose a new segmentation framework based on attention mechanisms, named MFA-Net (Multi-Scale Feature Fusion Attention Network). The proposed framework can learn more meaningful feature maps among multiple scales and result in more accurate automatic segmentation. We compare our proposed MFA-Net with SOTA methods on two 2D liver CT datasets. The experimental results show that our MFA-Net produces more precise segmentation on images with different scales.

cs.AI↗

arXiv2024

Imagining density distribution of molecular orbitals in IR+XUV co-rotating circular laser fields by frequency-domain theory

We have investigated the angle-resolved ATI spectrum of oriented molecules in the IR+XUV co-rotating circular laser fields. According to the different roles of IR and XUV laser in the ionization process, we purposefully adjust the photon energy of XUV and the intensity of IR laser to make the ionization spectrum of the molecule distributed in a suitable momentum region. Moreover, under the same laser conditions, the background fringes in the ionization spectrum of the molecule can be removed by using the ionization spectrum of the atom with the same ionization energy as the molecule, so that the molecular orbital density distribution in the suitable momentum region can be obtained. That is, for any unknown molecule, as long as the ionization energy of the molecule can be measured, the density distribution of the molecular orbital can be imaged in a definite momentum region by adjusting the laser field conditions, which may shed light on the experimental detection of molecular orbitals.

physics.atom-ph↗

arXiv2023

SDIF-DA: A Shallow-to-Deep Interaction Framework with Data Augmentation for Multi-modal Intent Detection

Multi-modal intent detection aims to utilize various modalities to understand the user's intentions, which is essential for the deployment of dialogue systems in real-world scenarios. The two core challenges for multi-modal intent detection are (1) how to effectively align and fuse different features of modalities and (2) the limited labeled multi-modal intent training data. In this work, we introduce a shallow-to-deep interaction framework with data augmentation (SDIF-DA) to address the above challenges. Firstly, SDIF-DA leverages a shallow-to-deep interaction module to progressively and effectively align and fuse features across text, video, and audio modalities. Secondly, we propose a ChatGPT-based data augmentation approach to automatically augment sufficient training data. Experimental results demonstrate that SDIF-DA can effectively align and fuse multi-modal features by achieving state-of-the-art performance. In addition, extensive analyses show that the introduced data augmentation approach can successfully distill knowledge from the large language model.

cs.CL↗

arXiv2023

Particle Radiation Environment in the Heliosphere: Status, limitations and recommendations

Space weather is a multidisciplinary research area connecting scientists from across heliophysics domains seeking a coherent understanding of our space environment that can also serve modern life and society's needs. COSPAR's ISWAT (International Space Weather Action Teams) 'clusters' focus attention on different areas of space weather study while ensuring the coupled system is broadly addressed via regular communications and interactions. The ISWAT cluster "H3: Radiation Environment in the Heliosphere" (https://www.iswat-cospar.org/h3) has been working to provide a scientific platform to understand, characterize and predict the energetic particle radiation in the heliosphere with the practical goal of mitigating radiation risks associated with areospace activities, satellite industry and human space explorations. In particular, present approaches help us understand the physical phenomena at large, optimizing the output of multi-viewpoint observations and pushing current models to their limits. In this paper, we review the scientific aspects of the radiation environment in the heliosphere covering four different radiation types: Solar Energetic Particles (SEPs), Ground Level Enhancement (GLE, a type of SEP events with energies high enough to trigger the enhancement of ground-level detectors), Galactic Cosmic Rays (GCRs) and Anomalous Cosmic Rays (ACRs). We focus on related advances in the research community in the past 10-20 years and what we still lack in terms of understanding and predictive capabilities. Finally we also consider some recommendations related to the improvement of both observational and modeling capabilities in the field of space radiation environment.

physics.space-ph↗

arXiv2023

Improving Few-shot and Zero-shot Entity Linking with Coarse-to-Fine Lexicon-based Retriever

Few-shot and zero-shot entity linking focus on the tail and emerging entities, which are more challenging but closer to real-world scenarios. The mainstream method is the ''retrieve and rerank'' two-stage framework. In this paper, we propose a coarse-to-fine lexicon-based retriever to retrieve entity candidates in an effective manner, which operates in two layers. The first layer retrieves coarse-grained candidates by leveraging entity names, while the second layer narrows down the search to fine-grained candidates within the coarse-grained ones. In addition, this second layer utilizes entity descriptions to effectively disambiguate tail or new entities that share names with existing popular entities. Experimental results indicate that our approach can obtain superior performance without requiring extensive finetuning in the retrieval stage. Notably, our approach ranks the 1st in NLPCC 2023 Shared Task 6 on Chinese Few-shot and Zero-shot Entity Linking.

cs.CL↗

arXiv2022

Resolved frustrated tunneling ionization in asymmetrical fast oscillation of above-threshold ionization spectrum

Tunneling ionization is one of the fundamental electron dynamics, which has wide applications in ultrafast physics. When frustrated tunneling ionization (FTI) is considered, the tunneling rate is not equivalent to ionization rate. However, it is hard to resolve the effects of FTI and direct tunneling ionization (DTI) in ionization spectrum experimentally. Here we report the first observation of the asymmetrical fast oscillation in above-threshold ionization (ATI) spectrum of Argon as function of carrier-envelope phase (CEP), to the best of our knowledge. Simulation results identify that in the experimental ATI spectrum, the π/5 oscillation originates from the quantum interference of electrons in FTI, while DTI is responsible for the asymmetry. Our results provide clear evidence to resolve the effects of direct tunneling and FTI in a new physical regime.

physics.optics↗