Large Language Models (LLMs) are now widely deployed across modern web services, but their safe and trustworthy use in real-world settings critically depends on accurate alignment with human preferences. Preference alignment is typically achieved using methods such as reinforcement learning or direct preference optimization (DPO), whose effectiveness in practice hinges on the quality of labeled preference data. However, a fundamental practical challenge remains: preference datasets inevitably contain noise. Through a systematic analysis of mainstream preference datasets, we find that roughly 25% of preference pairs show clear inconsistencies between reward-model evaluations and human annotations. Such inconsistent examples do not convey reliable preference signals; training directly on them therefore not only fails to improve alignment but can even degrade model behavior. To address this problem, we propose Noise-Aware Preference Alignment for LLMs via Confidence and Polarity Reweighting (AlignCP), a fully automated, human-free framework for noise-aware preference alignment. AlignCP derives two interpretable metrics from reward-model outputs: Confidence, which measures the reliability of each preference judgment, and Polarity, which evaluates whether the reward-model ranking agrees with the original human label. These metrics are combined to assign a training weight to each sample—amplifying high-confidence, label-consistent pairs while down-weighting or discarding low-confidence, contradictory, or otherwise noisy pairs. Unlike methods that rely on human re-inspection, repeated relabeling, or heavy computational reruns, AlignCP performs automated data-quality control with minimal overhead and no human intervention. Empirical results show that AlignCP substantially outperforms existing data-centric alignment approaches on standard preference benchmarks and remains more robust under noisy supervision.
论文检索
输入标题、作者或关键词，从 17,487 篇学术成果中精准定位
WED-Net: A Weather-Effect Disentanglement Network with Causal Augmentation for Urban Flow Prediction
Urban spatio-temporal prediction under extreme conditions (e.g., heavy rain) is challenging due to event rarity and dynamics. Existing data-driven approaches that incorporate weather as auxiliary input often rely on coarse-grained descriptors and lack dedicated mechanisms to capture fine-grained spatio-temporal effects. Although recent methods adopt causal techniques to improve out-of-distribution generalization, they typically overlook temporal dynamics or depend on fixed confounder stratification. To address these limitations, we propose WED-Net (Weather-Effect Disentanglement Network), a dual-branch Transformer architecture that separates intrinsic and weather-induced traffic patterns via self- and cross-attention, enhanced with memory banks and fused through adaptive gating. To further promote disentanglement, we introduce a discriminator that explicitly distinguishes weather conditions. Additionally, we design a causal data augmentation strategy that perturbs non-causal parts while preserving causal structures, enabling improved generalization under rare scenarios. Experiments on taxi-flow datasets from three cities demonstrate that WED-Net delivers robust performance under extreme weather conditions, highlighting its potential to support safer mobility, disaster preparedness, and urban resilience in real-world settings. The code is publicly available at https://github.com/HQ-LV/WED-Net.
Misinformation on the web increasingly appears in multimodal forms, combining text, images, and OCR-rendered content in ways that amplify harm to public trust and vulnerable communities. While prior fact-checking systems often rely on unimodal signals or shallow fusion strategies, modern misinformation campaigns operate across modalities and require models that can reason over subtle cross-modal inconsistencies in a transparent and responsible manner. We introduce MultiCheck, a lightweight and interpretable framework for multimodal fact verification that jointly analyzes textual, visual, and OCR evidence. At its core, MultiCheck employs a relational fusion module based on element-wise difference and product operations, allowing for explicit cross-modal interaction modeling with minimal computational overhead. A contrastive alignment objective further helps the model distinguish between supporting and refuting evidence while maintaining a small memory and energy footprint, making it suitable for low-resource deployment. Evaluated on the Factify-2 (5-class) and MOCHEG (3-class) benchmarks, MultiCheck achieves substantial performance improvement and remains robust under noisy OCR and missing modality conditions. Overall, MultiCheck is efficient, interpretable, and robust for multimodal verification. Our code is available at the following: https://github.com/Adityakishore09/MultiCheck_WWW-2026 GitHub repository.
Graph unlearning has emerged as a critical mechanism for supporting sustainable and privacy-preserving social networks, enabling models to remove the influence of deleted nodes and thereby better safeguard user information. However, we observe that existing graph unlearning techniques insufficiently protect sensitive attributes, often leading to degraded algorithmic fairness compared with traditional graph learning methods. To address this gap, we introduce FairGU, a fairness-aware graph unlearning framework designed to preserve both utility and fairness during the unlearning process. FairGU integrates a dedicated fairness-aware module with effective data protection strategies, ensuring that sensitive attributes are neither inadvertently amplified nor structurally exposed when nodes are removed. Through extensive experiments on multiple real-world datasets, we demonstrate that FairGU consistently outperforms state-of-the-art graph unlearning methods and fairness-enhanced graph learning baselines in terms of both accuracy and fairness metrics. Our findings highlight a previously overlooked risk in current unlearning practices and establish FairGU as a robust and equitable solution for the next generation of socially sustainable networked systems. The codes are available at https://github.com/LuoRenqiang/FairGU.
High-fidelity social simulation is pivotal for addressing complex Web societal challenges, yet it demands agents capable of authentically replicating the dynamic spectrum of human interaction. Current LLM-based multi-agent frameworks, however, predominantly adhere to static interaction topologies, failing to capture the fluid oscillation between cooperative knowledge synthesis and competitive critical reasoning seen in real-world scenarios. This rigidity often leads to unrealistic ''groupthink'' or unproductive deadlocks, undermining the credibility of simulations for decision support. To bridge this gap, we propose BEACOF, a belief-driven adaptive collaboration framework inspired by Perfect Bayesian Equilibrium (PBE). By modeling social interaction as a dynamic game of incomplete information, BEACOF rigorously addresses the circular dependency between collaboration type selection and capability estimation. Agents iteratively refine probabilistic beliefs about peer capabilities and autonomously modulate their collaboration strategy, thereby ensuring sequentially rational decisions under uncertainty. Validated across adversarial (judicial), open-ended (social) and mixed (medical) scenarios, BEACOF prevents coordination failures and fosters robust convergence toward high-quality solutions, demonstrating superior potential for reliable social simulation. Source codes and datasets are publicly released at: https://github.com/WUT-IDEA/BEACOF.
Mind the Ambiguity: Aleatoric Uncertainty Quantification in LLMs for Safe Medical Question Answering
The deployment of Large Language Models in Medical Question Answering is severely hampered by ambiguous user queries, a significant safety risk that demonstrably reduces answer accuracy in high-stakes healthcare settings. In this paper, we formalize this challenge by linking input ambiguity to aleatoric uncertainty (AU), which is the irreducible uncertainty arising from underspecified input. To facilitate research in this direction, we construct CV-MedBench, the first benchmark designed for studying input ambiguity in Medical QA. Using this benchmark, we analyze AU from a representation engineering perspective, revealing that AU is linearly encoded in LLM's internal activation patterns. Leveraging this insight, we introduce a novel AU-guided ''Clarify-Before-Answer'' framework, which incorporates AU-Probe - a lightweight module that detects input ambiguity directly from hidden states. Unlike existing uncertainty estimation methods, AU-Probe requires neither LLM fine-tuning nor multiple forward passes, enabling an efficient mechanism to proactively request user clarification and significantly enhance safety. Extensive experiments across four open LLMs demonstrate the effectiveness of our QA framework, with an average accuracy improvement of 9.48% over baselines. Our framework provides an efficient and robust solution for safe Medical QA, strengthening the reliability of health-related applications. The code is available at https://github.com/yaokunliu/AU-Med.git, and the CV-MedBench dataset is released on Hugging Face at https://huggingface.co/datasets/yaokunl/CV-MedBench.
The escalating energy consumption and carbon footprint of training large-scale Web AI models pose urgent challenges for sustainable development. Dataset Distillation (DD) offers a promising avenue for green AI by compressing large datasets into small synthetic ones for efficient training. However, most existing DD methods overfit to the inductive biases of specific source architectures (e.g., CNNs or ViTs), resulting in poor cross-model generalization. This limitation necessitates redundant re-distillation processes for different architectures, severely undermining the energy-saving potential of DD. To address this, we introduce Adversarial Mutual Information Distillation (AMID), a rigorous framework designed to create highly reusable and robust synthetic datasets. From an information-theoretic perspective, we cast model-agnosticism as minimizing the mutual information (MI) between the synthetic data and the specific identity of the distillation model. We convert this intractable objective into a tractable two-player adversarial game, which unifies knowledge preservation with adversarial unlearning of architectural bias. Extensive experiments on CIFAR-10 and Tiny ImageNet demonstrate that AMID achieves state-of-the-art cross-architecture generalization across diverse CNNs and ViTs. Crucially, our analysis confirms that AMID significantly reduces the computational overhead and CO2 emissions of downstream training while maintaining robust performance, paving the way for energy-efficient, transferable, and sustainable Web AI ecosystems.
The rapid proliferation of emotion-aware web services has necessitated the analysis of multimodal user interactions. However, this introduces new vulnerabilities where adversaries exploit emotional signals to circumvent fraud detection systems. Despite its improved utility, the robustness of multimodal fraud detection against emotion-driven adversarial manipulation remains significantly underexplored. Existing paradigms often treat emotional cues as static features, overlooking the adversary's capability to strategically modulate multimodal signals (e.g., facial micro-expressions, vocal intonation, and textual styles) to mimic genuine behavior. Furthermore, prevalent evaluations are typically confined to unimodal perturbations and fail to account for context-consistent, cross-modal attacks, thereby compromising system reliability in real-world deployments. To bridge this gap, we propose Context-Emotion Adversarial Training (CEAT), a robust framework designed to fortify multimodal fraud detection against emotion-based attacks. CEAT leverages a Transformer-based architecture to synergistically model emotional features (e.g., visual dynamics and acoustic prosody) alongside semantic context derived from text, yielding a unified representation. Crucially, CEAT introduces a context-aware perturbation mechanism that injects noise into the emotional latent space during training. This process preserves semantic consistency while encouraging the learning of emotion-invariant and discriminative representations. Additionally, a contrastive learning objective is integrated to maximize the distributional divergence between genuine and adversarial samples within the latent manifold. Extensive experiments on multimodal benchmarks demonstrate that CEAT significantly outperforms state-of-the-art baselines, exhibiting superior robustness under simulated emotion-driven attack scenarios.
Large language models (LLMs) are increasingly deployed in domains where errors carry high social, scientific, or safety costs. Yet standard confidence estimators, such as token likelihood, semantic similarity and multi-sample consistency, remain brittle under distribution shift, domain-specialised text, and compute limits. In this work, we present Structural Confidence, a single-pass, model-agnostic framework that enhances output correctness prediction based on multi-scale structural signals derived from a model's final-layer hidden-state trajectory. By combining spectral, local-variation, and global shape descriptors, our method captures internal stability patterns that are missed by probabilities and sentence embeddings. We conduct extensive, cross-domain evaluation across four heterogeneous benchmarks—FEVER (fact verification), SciFact (scientific claims), WikiBio-hallucination (biographical consistency), and TruthfulQA (truthfulness-oriented QA). Our Structural Confidence framework demonstrates strong performance compared with established baselines in terms of AUROC and AUPR. More importantly, unlike sampling-based consistency methods which require multiple stochastic generations and an auxiliary model, our approach uses a single deterministic forward pass, offering a practical basis for efficient, robust post-hoc confidence estimation in socially impactful, resource-constrained LLM applications.
Accurate forecasting of Avian Influenza Virus (AIV) outbreaks within wild bird populations necessitates models that account for complex, multi-scale transmission patterns driven by diverse factors. While conventional spatiotemporal epidemic models are robust for human-centric diseases, they rely on spatial homophily and diffusive transmission between geographic regions. This simplification is incomplete for AIV as it neglects valuable genomic information critical for capturing dynamics like high-frequency reassortment and lineage turnover at the case level (e.g., genetic descent across regions), which are essential for understanding AIV spread. To address these limitations, we systematically formulate the AIV forecasting problem and propose BLUE (bi-layer genomic-aware heterogeneous graph fusion pipeline). This pipeline integrates genetic, spatial, and ecological data to achieve highly accurate outbreak forecasting. It 1) defines a multi-layered graph structure incorporating information from diverse sources and multiple layers (case and location), 2) applies cross-relation smoothing to smooth information flow across edge types, 3) performs graph fusion that preserves critical structural patterns backed by theoretical spectral guarantees, and 4) forecasts future outbreaks using an autoregressive graph sequence model to capture transmission dynamics. To support research, we release the Avian-US dataset, which provides comprehensive genetic, spatial, and ecological data on US avian influenza outbreaks. BLUE demonstrates superior performance over existing baselines, highlighting the efficacy of integrating multi-layer information for infectious disease forecasting. The code is available at: https://github.com/cruiseresearchgroup/BLUE.
Accurate semantic segmentation is crucial for rapid risk and severity assessment following flash flood disasters. However, in drone networks deployed for disaster recovery, bandwidth constraints mean the backhaul transmission of massive imagery required for centralized processing is highly prone to causing network congestion. Federated Learning, a decentralized collaborative paradigm that permits drones to process data locally, offers an ideal pathway to address this challenge. Nonetheless, existing FL methods are plagued by the dilemma of excessive communication overhead and insufficient segmentation performance. Therefore, this paper proposes a Communication-Efficient Federated Distillation (CEFD) framework. The core of this framework lies in the design of a lightweight, multi-level knowledge representation. It discards the transmission of bulky parameters, opting instead for the efficient exchange of high-level semantic logits and key intermediate features that have undergone feature-space dimensionality reduction. On the server side, adaptive weighted aggregation is then utilized to construct a robust global knowledge model. Experimental results show that CEFD achieved high segmentation performance on the LSD dataset, attaining an mIoU of 0.6226, a Mean Recall of 0.6532, an Accuracy of 0.9794, and an MAE of 0.0400, while reducing communication overhead by approximately 99.5%. This enables scalable collaborative intelligence for resource-constrained edge devices, a key capability for the future web systems.
Deep learning has made remarkable progress in medical image analysis, yet its black-box nature still limits interpretability and clinician trust. Concept-based modeling offers a promising direction for explainable AI by integrating human-understandable concepts. However, existing approaches typically rely on global concept annotations and infer diagnosis based solely on the presence or absence of individual concepts. This oversimplified paradigm ignores the rich relationships among concepts and their causal influence on disease outcomes. To overcome these limitations, we propose the Concept Relationship Embedding Model (CREM) for interpretable medical diagnosis. CREM mirrors coarse-to-fine clinical reasoning by first extracting fine-grained subregional concepts, then explicitly encoding their relationships as a concept interaction graph, and finally performing causal inference between concepts and diagnoses to enable reliable and transparent diagnostic predictions. We evaluate CREM on four public medical imaging benchmarks, where it achieves state-of-the-art performance on both concept recognition and disease classification tasks, while exhibiting improved robustness, label efficiency, and interpretability. Furthermore, we deploy CREM as an interactive web-based demo that allows clinicians to visualize concept activations, trace diagnostic reasoning paths, and iteratively refine concept cues, facilitating effective human-in-the-loop decision-making.
Dengue, a mosquito-borne disease, continues to pose a persistent public health challenge in urban areas, particularly in tropical regions such as Singapore. Effective and affordable control requires anticipating where transmission risks are likely to emerge so that interventions can be deployed proactively rather than reactively. This study introduces a novel framework that uncovers and exploits latent transmission links between urban regions, mined directly from publicly available dengue case data. Instead of treating cases as isolated reports, we model how hotspot formation in one area is influenced by epidemic dynamics in neighboring regions. While mosquito movement is highly localized, long-distance transmission is often driven by human mobility, and in our case study, the learned network aligns closely with commuting flows, providing an interpretable explanation for citywide spread. These hidden links are optimized through gradient descent and used not only to forecast hotspot status but also to verify the consistency of spreading patterns, by examining the stability of the inferred network across consecutive weeks. Case studies on Singapore during 2013–2018 and 2020 show that four weeks of hotspot history are sufficient to achieve an average F-score of 0.79. Even under the COVID-19 ''circuit breaker,'' when mobility patterns were severely disrupted, the model remained robust with an F-score of 0.83. Importantly, the learned transmission links align with commuting flows, highlighting the interpretable interplay between hidden epidemic spread and human mobility. By shifting from simply reporting dengue cases to mining and validating hidden spreading dynamics, this work transforms open web-based case data into a predictive and explanatory resource. The proposed framework advances epidemic modeling while providing a scalable, low-cost tool for public health planning, early intervention, and urban resilience.
As Large Language Models (LLMs) increasingly shape online content, how to remove targeted information from well-trained LLMs (also known as LLM unlearning) has become increasingly critical for web governance. A key challenge in LLM unlearning lies in the sample-wise imbalance within the forget set: different samples exhibit widely varying unlearning difficulty, leading to asynchronous forgetting speeds where some knowledge remains insufficiently erased while others become over-forgotten. To address this challenge, we propose BalDRO, a novel and efficient framework for balanced LLM unlearning. BalDRO formulates unlearning as a min–sup process, where the inner process identifies a worst-case data distribution that adaptively emphasizes hard-to-unlearn samples, while the outer process updates model parameters based on the worst-case data distribution. We instantiate this formulation through two efficient variants: BalDRO-G, a discrete GroupDRO-based approximation that focuses on high-loss subsets, and BalDRO-DV, a continuous Donsker–Varadhan dual method that enables smooth, adaptive weighting within standard LLM training pipelines. Extensive experiments on the TOFU and MUSE benchmarks demonstrate the effectiveness of our proposed BalDRO, yielding significant improvements in both forgetting quality and model utility over existing methods. For reproducibility, we have released the code for BalDRO. https://github.com/nxZhai/BalDRO.
Table retrieval is the task of retrieving the most relevant tables from large-scale corpora given natural language queries. However, structural and semantic discrepancies between unstructured text and structured tables make embedding alignment particularly challenging. Recent methods such as QGpT attempt to enrich table semantics by generating synthetic queries, yet they still rely on coarse partial-table sampling and simple fusion strategies, which limit semantic diversity and hinder effective query–table alignment. We propose STAR (Semantic Table Representation), a lightweight framework that improves semantic table representation through semantic clustering and weighted fusion. STAR first applies header-aware K-means clustering to group semantically similar rows and selects representative centroid instances to construct a diverse partial table. It then generates cluster-specific synthetic queries to comprehensively cover the table's semantic space. Finally, STAR employs weighted fusion strategies to integrate table and query embeddings, enabling fine-grained semantic alignment. This design enables STAR to capture complementary information from structured and textual sources, improving the expressiveness of table representations. Experiments on five benchmarks show that STAR achieves consistently higher Recall than QGpT on all datasets, demonstrating the effectiveness of semantic clustering and weighted fusion for robust table representation. Our code is available at https://github.com/adsl135789/STAR.
Foundation models for tabular data, such as the Tabular Prior-data Fitted Network (TabPFN), are pre-trained on a massive number of synthetic datasets generated by structural causal models (SCM). They leverage in-context learning to offer high predictive accuracy in real-world tasks. However, the fairness properties of these foundational models, which incorporate ideas from causal reasoning during pre-training, remain underexplored. In this work, we conduct a comprehensive empirical evaluation of TabPFN and its fine-tuned variants, assessing predictive performance, fairness, and robustness across varying dataset sizes and distributional shifts. Our results reveal that while TabPFN achieves stronger predictive accuracy compared to baselines and exhibits robustness to spurious correlations, improvements in fairness are moderate and inconsistent, particularly under missing-not-at-random (MNAR) covariate shifts. These findings suggest that the causal pre-training in TabPFN is helpful but insufficient for algorithmic fairness, highlighting implications for deploying TabPFN (and similar) models in practice and the need for further fairness interventions.
Tabular data drive most real-world machine learning applications, yet building general-purpose models for them remains difficult. Mixed numeric and categorical fields, weak feature structure, and limited labeled data make scaling and generalization challenging. To this end, we introduce Orion-Bix, a tabular foundation model that combines biaxial attention with meta-learned in-context reasoning for few-shot tabular learning. Its encoder alternates standard, grouped, hierarchical, and relational attention, fusing their outputs through multi-CLS summarization to capture both local and global dependencies efficiently. A label-aware in-context learning (ICL) head adapts on the fly and scales to large label spaces via hierarchical decision routing. Delivered as a scikit-learn–compatible foundation model, it outperforms gradient-boosting baselines and remains competitive with state-of-the-art tabular foundation models on public benchmarks, showing that biaxial attention with episodic meta-training enables robust, few-shot-ready tabular learning.
Trusted multi-view classification (TMC) aims to improve prediction reliability by integrating evidence from multiple views. Existing TMC methods extract evidence from single view and use a regularization term to shape the evidence distribution. However, existing methods typically enforce a uniform regularization objective across all views, overlooking critical view-specific biases: intra-view class ambiguity caused by confusable features and inter-view quality disparities reflected in evidence uncertainty. To address these issues, we propose an adaptive regularization strategy that enhances robustness on two levels. At the intra-view level, it quantifies feature ambiguity to apply targeted relaxation to confusable classes, preventing over-penalization of inherent uncertainty. At the inter-view level, it evaluates relative view quality to impose stronger constraints on unreliable views and suppress noise from low-quality ones. Extensive experiments across multiple benchmarks demonstrate the superiority and reliability of the proposed method.
Emotion detection is a central problem in NLP, with recent progress driven by transformer-based models trained on established datasets. However, little is known about the linguistic regularities that characterize how emotions are expressed across different corpora and labels. This study examines whether linguistic features can serve as reliable interpretable signals for emotion recognition in text. We extract emotion-specific linguistic signatures from 13 English datasets and evaluate how incorporating these features into transformer models impacts performance. Our RoBERTa-based models enriched with high level linguistic features achieve consistent performance gains of up to +2.4 macro F1 on the GoEmotions benchmark, showing that explicit lexical cues can complement neural representations and improve robustness in predicting emotion categories.