We present S-Path-RAG, a semantic-aware shortest-path Retrieval-Augmented Generation framework designed to improve multi-hop question answering over large knowledge graphs. S-Path-RAG departs from one-shot, text-heavy retrieval by enumerating bounded-length, semantically weighted candidate paths using a hybrid weighted k-shortest, beam, and constrained random-walk strategy, learning a differentiable path scorer together with a contrastive path encoder and lightweight verifier, and injecting a compact soft mixture of selected path latents into a language model via cross-attention. The system runs inside an iterative Neural-Socratic Graph Dialogue loop in which concise diagnostic messages produced by the language model are mapped to targeted graph edits or seed expansions, enabling adaptive retrieval when the model expresses uncertainty. This combination yields a retrieval mechanism that is both token-efficient and topology-aware while preserving interpretable path-level traces for diagnostics and intervention. We validate S-Path-RAG on standard multi-hop KGQA benchmarks and through ablations and diagnostic analyses. The results demonstrate consistent improvements in answer accuracy, evidence coverage, and end-to-end efficiency compared to strong graph- and LLM-based baselines. We further analyze trade-offs between semantic weighting, verifier filtering, and iterative updates, and report practical recommendations for deployment under constrained compute and token budgets.
论文检索
输入标题、作者或关键词，从 100,903 篇学术成果中精准定位
Multi-modal entity alignment (MMEA) aims to identify equivalent entities across heterogeneous multi-modal knowledge graphs (MMKGs), which play a crucial role in organizing and integrating web knowledge from diverse modalities. Although prior studies have made progress by multi-modal features fusion, three inherent limitations remain unresolved. First, instance-level feature fusion is misaligned with the pair-wise task format of MMEA. Second, joint representations often overlook modality-specific characteristics, resulting in insufficient alignment. Third, most existing methods rely solely on global features of modality. This may lead to the misalignment of entities that are similar yet distinct. To address above issues, we propose DMEA, a new decision-fusion-based framework. Specifically, we first design a multi-modal knowledge encoding module to extract both global and local features for different modalities and then introduce a multi-grained alignment module, which consists of two components: intra-modal alignment and cross-modal alignment. The former computes alignment scores between the global and local features of entity pairs within the same modality, while the latter leverages the complementarity across modalities to compute cross-modal alignment scores. Each score is regarded as an independent decision, and the final alignment judgment is made by integrating all decisions. Finally, we incorporate an intra-modal contrastive loss to obtain more discriminative embedding representations. DMEA achieves improvements of 13.2% and 14.8% in hit@1 over the state-of-the-art models on two benchmark datasets, FB15K-DB15K and FB15K-YAGO15K, respectively, validating the superiority of our framework.
Large language models (LLMs) are increasingly adopted as the backbone of recommender systems. However, user–item interactions in real-world scenarios are non-stationary, making preference drift over time inevitable. Existing model update strategies mainly rely on global fine-tuning or pointwise editing, but they face two fundamental challenges: (i) imbalanced update granularity, where global updates perturb behaviors unrelated to the target while pointwise edits fail to capture broader preference shifts; (ii) unstable incremental updates, where repeated edits interfere with prior adaptations, leading to catastrophic forgetting and inconsistent recommendations. To address these issues, we propose Region-Aware Incremental Editing (RAIE), a plug-in framework that freezes the backbone model and performs region-level updates. RAIE first constructs semantically coherent preference regions via spherical k-means in the representation space. It then assigns incoming sequences to regions via confidence-aware gating and performs three localized edit operations-Update, Expand, and Add-to dynamically revise the affected region. Each region is equipped with a dedicated Low-Rank Adaptation (LoRA) module, which is trained only on the region's updated data. During inference, RAIE routes each user sequence to its corresponding region and activates the region-specific adapter for prediction. Experiments on two benchmark datasets under a time-sliced protocol that segments data into Set-up (S), Finetune (F), and Test (T) show that RAIE significantly outperforms state-of-the-art baselines while effectively mitigating forgetting. These results demonstrate that region-aware editing offers an accurate and scalable mechanism for continual adaptation in dynamic recommendation scenarios.
Conditional Knowledge Graphs (CKGs) extend traditional knowledge graphs by incorporating conditional constraints, enabling a more accurate understanding of complex knowledge with conditional constraints for the semantic web. Conditional information extraction (CIE) aims to extract not only traditional fact triples but also their corresponding conditional qualifiers, forming quintuples that represents these constraints. Existing CIE methods typically treat conditional quintuples as flat structures, overlooking the hierarchical dependencies. Additionally, they often require exploring all possible mention combinations, leading to a large interaction space. These two issues hinder the extraction performance. To this end, we propose a Diffusion Model on Fact-condition Star Graph for CIE (Diff-CIE). We adapt a star graph structure where fact triples serve as central nodes and conditional tuples as leaf nodes, explicitly modeling the hierarchical dependencies. We then leverage the diffusion model to reformulate CIE as a progressive denoising process on these nodes, refining a fixed number of noised nodes into quintuples, thereby reducing the interaction space. Furthermore, to mitigate the inherent optimization instability in traditional diffusion-based information extraction methods, we introduce a deterministic in-order matching strategy to provide an auxiliary constraint. Extensive experiments on three datasets demonstrate that Diff-CIE consistently outperforms state-of-the-art baselines and has higher efficiency, achieving an improvement in F1 metric of over 1.19%, validating the effectiveness of our methods.
Aspect-based sentiment analysis (ABSA) aims to identify the sentiment polarity of the specified aspect in a sentence. Despite achieving the remarkable success, deep models are susceptible to capturing spurious correlations between surface patterns and predicted labels instead of capturing aspect-related causal features, leading to poor robustness. To this end, we propose a new counterfactual-enhanced causal reasoning (CECR) framework to reduce spurious correlations. Specifically, at the data level, the counterfactual data augmentation (CDA) module is exploited to employ a three-stage reasoning paradigm guided by cognitive chain-of-thought (COT) principles to generate high-quality counterfactual data from the training data. At the model level, the multi-level causal attention (MCA) is designed to iteratively extract causal features and remove confounding features. Experimental results on the utilized datasets demonstrate that the CECR achieves outstanding performance on state-of-the-art baselines.
Effective representations of complex web semantic graphs are essential for various web applications, including link prediction, recommendation systems, and social network analysis. However, existing methods assume that multi-interactions (or multi-relationships) between two connected nodes are independent, while these relationships inherently exhibit characteristics of mutual promotion or mutual inhibition. Moreover, these semantic characteristics across different relationships cannot be easily captured by a simple linear combination. To tackle this challenge, we propose an Adaptive Multi-Interaction (AMI) web semantic graph representation method. Specifically, AMI consists of three modules, including a multi-interaction aggregation module, a global pattern aggregation module, and an adaptive relation-specific decoder module. Firstly, we construct a learnable multi-interaction behavior pattern matrix that captures the mutual promotion and mutual inhibition effects between two connected nodes. Secondly, the global pattern aggregation module is designed to efficiently capture global homogeneous interaction patterns through graph convolution networks. Finally, the adaptive relation-specific decoder module employs a hybrid scoring strategy to adaptively decode node embeddings based on their distinct relationships. Extensive experiments on benchmark web datasets for link prediction tasks demonstrate that AMI outperforms state-of-the-art baselines. Our codes are available at https://github.com/AI-stronger123/AMI.
Large Language Models (LLMs) have recently emerged as a powerful paradigm for Knowledge Graph Completion (KGC), offering strong reasoning and generalization capabilities beyond traditional embedding-based approaches. However, existing LLM-based methods often struggle to fully exploit structured semantic representations, as the continuous embedding space of pretrained KG models is fundamentally misaligned with the discrete token space of LLMs. This discrepancy hinders effective semantic transfer and limits their performance. To address this challenge, we propose ReaLM, a novel and effective framework that bridges the gap between KG embeddings and LLM tokenization through the mechanism of residual vector quantization. ReaLM discretizes pretrained KG embeddings into compact code sequences and integrates them as learnable tokens within the LLM vocabulary, enabling seamless fusion of symbolic and contextual knowledge. Furthermore, we incorporate ontology-guided class constraints to enforce semantic consistency, refining entity predictions based on class-level compatibility. Extensive experiments on two widely used benchmark datasets demonstrate that ReaLM achieves state-of-the-art performance, confirming its effectiveness in aligning structured knowledge with large-scale language models. The implementation is publicly available at https://github.com/xiumu-gg/ReaLM.
Large Language Models (LLMs) inevitably encounter factual hallucinations and knowledge obsolescence, necessitating lifelong knowledge editing to sustain reliability and factual advancement. While mainstream lifelong editing paradigms aim to alleviate knowledge forgetting through allocating and updating isolated parameter subspaces, they often overlook conflict assessment among distinct editing processes, leading to unjustified subspace allocation and indiscriminate neuron tuning. To address these issues, we propose the Conflict-Assessed Sensitive Editing (CASE) framework, which integrates a Conflict-Assessed Editing Allocation (CAA) module and a Knowledge-sensitive Neuron Tuning (KNT) strategy. The CAA module quantitatively assesses editing conflicts to enable justified subspace allocation, thereby reducing globally significant conflicts and routing errors. The KNT strategy adaptively identifies and tunes knowledge-sensitive neurons through a calibrated sensitivity threshold, effectively eliminating local conflicts and enhancing subspace stability. Extensive experiments on standard lifelong editing benchmarks demonstrate that CASE achieves state-of-the-art performance, improving average editing accuracy by nearly 10% after 1,000 sequential edits. Overall, CASE substantially mitigates editing conflicts and enhances knowledge retention, offering a scalable and conflict-resilient solution for lifelong model editing.
Semantic graphs are fundamental to the Web, enabling applications such as semantic search, recommendation, and knowledge-intensive reasoning. In decentralized Web environments, however, these graphs are distributed across organizations and constrained by strict privacy policies, making centralized training infeasible. Federated learning provides a promising solution, yet its effectiveness is severely limited by the dual incompleteness of real-world semantic graphs: missing node attributes and incomplete relational structures. Such dual missingness, often heterogeneous and unobserved across clients, causes substantial degradation in model performance. We present FedCL, a missingness-aware federated contrastive learning framework for dual-incomplete semantic graphs. FedCL introduces two key components: a topology estimation module, grounded in rate–distortion theory, that privately quantifies structural incompleteness across clients, and a federated reconstruction module that leverages these estimations to generate plausible relations without inferring sensitive attributes. To further improve robustness, FedCL integrates graph contrastive learning across reconstructed subgraphs, ensuring semantic consistency across heterogeneous and incomplete client graphs. Experiments on benchmark citation and Web datasets demonstrate that FedCL consistently outperforms state-of-the-art baselines in accuracy and robustness under heterogeneous missingness, while preserving strong privacy guarantees. These results highlight FedCL as a scalable and trustworthy approach for federated learning on incomplete semantic graphs, advancing privacy-preserving knowledge sharing on the Web.
Existing knowledge graphs (KGs) inevitably contain outdated or erroneous knowledge that needs to be removed from knowledge graph embedding (KGE) models. To address this challenge, knowledge unlearning can be applied to eliminate specific information while preserving the integrity of the remaining knowledge in KGs. Existing unlearning methods can generally be categorized into exact unlearning and approximate unlearning. However, exact unlearning requires high training costs, while approximate unlearning faces two issues when applied to KGs due to the inherent connectivity of triples: (1) It fails to fully remove targeted information, as forgetting triples can still be inferred from remaining ones. (2) It focuses on local data for specific removal, which weakens the remaining knowledge in the forgetting boundary. To address these issues, we propose GraphDPO, a novel approximate unlearning framework based on direct preference optimization (DPO). Firstly, to effectively remove forgetting triples, we reframe unlearning as a preference optimization problem, where the model is trained by DPO to prefer reconstructed alternatives over the original forgetting triples. This formulation penalizes reliance on forgettable knowledge, mitigating incomplete forgetting caused by KG connectivity. Moreover, we introduce an out-boundary sampling strategy to construct preference pairs with minimal semantic overlap, weakening the connection between forgetting and retained knowledge. Secondly, to preserve boundary knowledge, we introduce a boundary recall mechanism that replays and distills relevant information both within and across time steps. We construct eight unlearning datasets across four popular KGs with varying unlearning rates. Experiments show that GraphDPO outperforms state-of-the-art baselines by up to 10.1% in MRR_Avg and 14.0% in MRR_F1. Further analysis confirms that GraphDPO more effectively removes target knowledge while preserving surrounding context.
The ability of Large Language Models (LLMs) to perform reasoning tasks such as deduction has been widely investigated in recent years. Yet, their capacity to generate proofs—faithful, human-readable explanations of why conclusions follow—remains largely underexplored. In this work, we study proof generation in the context of OWL ontologies, which are widely adopted for representing and reasoning over complex knowledge, by developing an automated dataset construction and evaluation framework. Our evaluation encompassing three sequential tasks for complete proving: Extraction, Simplification, and Explanation, as well as an additional task of assessing Logic Completeness of the premise. Through extensive experiments on widely used reasoning LLMs, we achieve important findings including: (1) Some models achieve overall strong results but remain limited on complex cases; (2) Logical complexity, rather than representation format (formal logic language versus natural language), is the dominant factor shaping LLM performance; and (3) Noise and incompleteness in input data substantially diminish LLMs' performance. Together, these results underscore both the promise of LLMs for explanation with rigorous logics and the gap of supporting resilient reasoning under complex or imperfect conditions. Code and data are available at https://github.com/HuiYang1997/LLMOwlR.
Continual knowledge graph embedding (CKGE) aims to incrementally learn embeddings of entities and relations in a knowledge graph (KG) that evolves over time with a sequence of newly arriving triples. This capability is essential for dynamic applications such as retrieval-augmented generation (RAG), but remains challenging due to the structural diversity and non-uniform growth of evolving KGs. Existing CKGE approaches reveal limitations in both leveraging rich structural information and achieving update efficiency, as they often rely on simplistic metrics (e.g., degree) and a vanilla TransE loss that is not adaptive to structural dynamics. In this work, we propose STARK (Structure-aware and Adaptive Representation learning for CKGE), a fast yet effective CKGE framework that enhances structure awareness and supports adaptive optimization. To this end, we propose two major techniques, namely structural novelty prioritization (SNP) and adaptive TransE loss (ATL). Through SNP, STARK allocates higher representational capacity to topologically more important entities, while ATL adaptively keeps embeddings close to the true target of each head-relation pair (h, r, ?), dynamically scaling the boundary according to the cardinality of candidate tails. Extensive experiments on multiple CKGE benchmarks demonstrate that STARK achieves both higher accuracy and better efficiency in the time-performance tradeoff compared to existing state-of-the-art methods. Moreover, embedding visualizations and quantitative analysis confirm that STARK produces more coherent clusters of entities sharing the same (h, r, ?), reflecting improved structural consistency.
Accurate travel time estimation (TTE) plays a crucial role in intelligent transportation systems. However, it remains challenging due to heterogeneous data sources and complex traffic dynamics. Moreover, traditional approaches typically convert trajectory data into fixed-length representations. This overlooks the inherent variability of real-world motion patterns, often resulting in information loss and redundancy. To address these challenges, this paper introduces the Multimodal Dynamic Trajectory Integration (MDTI) framework--a novel multimodal trajectory representation learning approach that integrates GPS sequences, grid trajectories, and road network constraints to enhance the performance of TTE. MDTI employs modality-specific encoders and a multimodal fusion module to capture complementary spatial, temporal, and topological semantics, while a dynamic trajectory modeling mechanism adaptively regulates information density for trajectories of varying lengths. Two self-supervised pretraining objectives, named contrastive alignment and masked language modeling, further strengthen multimodal consistency and contextual understanding. Extensive experiments on three real-world datasets demonstrate that MDTI consistently outperforms state-of-the-art baselines, confirming its robustness and strong generalization abilities. The code is publicly available at: https://github.com/City-Computing/MDTI.
Recently, hypergraph knowledge distillation has been proposed to alleviate the high computational cost of Hypergraph Neural Networks (HGNNs) when modeling high-order relationships in Web-related graph tasks. Its effectiveness primarily depends on the quality of knowledge transferred from the teacher and the representation capability of the student. However, existing methods remain limited on both sides. On the teacher side, most methods typically rely on a single HGNN teacher, which provides limited structural and semantic knowledge, thereby constraining the upper bound of the student's performance. The potential of exploiting multiple teachers in HGNNs remains largely underexplored. On the student side, existing methods ignore the student's capability to capture high-order semantic and structural information beyond simply imitating teacher outputs, leading to limited representation learning. To address these limitations, we propose MARCH, a framework for Multi-TeAcheR Contrastive Hypergraph Distillation, which advances semantic modeling and distillation for Web-scale structured data. Specifically, MARCH proposes a multi-teacher distillation strategy that adaptively transfers complementary knowledge from multiple teachers at both node and hyperedge levels, empowering the student model to learn richer and more discriminative representations and even outperform its teachers. Extensive experiments on six benchmark datasets demonstrate the superior performance of MARCH.
Real-world data streams exhibit inherent non-stationarity characterized by concept drift, posing significant challenges for adaptive learning systems. While existing methods address isolated distribution shifts, they overlook the critical co-evolution of label spaces and distributions under limited supervision and persistent uncertainty. To address this, we formalize Generalized Incremental Learning under Concept Drift (GILCD), characterizing the joint evolution of distributions and label spaces in open-environment streaming contexts, and propose a novel framework called Calibrated Source-Free Adaptation (CSFA). First, CSFA introduces a training-free prototype calibration mechanism that dynamically fuses emerging prototypes with base representations, enabling stable new-class identification without optimization overhead. Second, we design a novel source-free adaptation algorithm, i.e., Reliable Surrogate Gap Sharpness-aware (RSGS) minimization. It integrates sharpness-aware perturbation loss optimization with surrogate gap minimization, while employing entropy-based uncertainty filtering to discard unreliable samples. This mechanism ensures robust distribution alignment and mitigates generalization degradation caused by uncertainties. Thus, CSFA establishes a unified framework for stable adaptation to evolving semantics and distributions in open-world streaming scenarios. Extensive experiments validate the superior performance and effectiveness of CSFA compared to SOTA approaches.
Visual instruction tuning is a key training stage of large multimodal models. However, when learning multiple visual tasks simultaneously, this approach often results in suboptimal and imbalanced overall performance due to latent knowledge conflicts across tasks. To mitigate this issue, we propose a novel Adaptive Task Balancing approach tailored for visual instruction tuning (VisATB). Specifically, we measure two critical dimensions for visual task balancing based on validation performance: (1) Inter-Task Contribution, the mechanism where learning one task enhances the performance on others owing to shared knowledge across tasks, and (2) Intra-Task Difficulty, which denotes the inherent learning difficulty of a single task. Furthermore, we propose prioritizing three categories of tasks with greater weight: those that offer substantial contributions to others, those that receive minimal contributions from others, and those that present high learning difficulties. Among these three task weighting strategies, the first and third focus on improving overall performance, and the second targets the mitigation of performance imbalance. Extensive experiments on three benchmarks demonstrate that our VisATB approach consistently achieves superior and more balanced overall performance in visual instruction tuning. The data, code, and models are available at https://github.com/YanqiDai/VisATB.
Tables serve as a core format for representing structured data on the web, as their two-dimensional layouts effectively encode complex inter-entity relationships. However, real-world web tables often feature heterogeneous structures and rich semantics. Accurately interpreting such tables requires not only spatial layout perception but also multi-step reasoning across rows and columns, posing substantial challenges to web intelligence systems. Multimodal large language models (MLLMs) show promise in table question answering (TableQA) by leveraging visual layouts. However, their performance on complex web tables remains uneven, as existing benchmarks often blur the impact of individual difficulty factors, hindering precise capability analysis. To advance TableQA beyond superficial task difficulty and toward interpretable capability modeling, we introduce MMTableBench, a multi-level benchmark that systematically evaluates MLLMs along two fine-grained dimensions: layout complexity and reasoning complexity. By organizing table-question pairs along these axes, MMTableBench facilitates a detailed evaluation of model performance under varying structural and reasoning challenges, while revealing the respective strengths and limitations of multimodal inputs. Our comprehensive analysis shows that state-of-the-art MLLMs continue to exhibit notable limitations when confronted with complex layouts and deep reasoning tasks, underscoring persistent gaps despite the structural advantages offered by visual inputs. MMTableBench thus provides not only a rigorous evaluation framework but also a diagnostic tool for analyzing and interpreting model behaviors, enabling more transparent and explainable progress in multimodal TableQA development.
Retrieval-augmented generation (RAG) has proven effective at mitigating limitations of large language models (LLMs), including outdated knowledge, semantic gaps, and hallucinations. However, existing RAG techniques are primarily optimised for factual question answering—where answers can be directly retrieved—rather than for predictive tasks that require inferring unknown outcomes, such as user preferences in recommendations. To address this gap, we propose PRAG, a RAG framework tailored for predictive settings. PRAG computes the semantic similarity between a user's historical interactions and target information, and adaptively integrates this similarity as prompt weights, thereby enhancing the LLM's ability to model personalised, semantics-informed preferences. PRAG integrates seamlessly into LLM-based applications; instantiated in recommender systems, it explicitly captures user-specific preference signals via semantic similarity modelling. Experiments using two LLM backbones and four real-world datasets show that PRAG significantly improves predictive recommendation performance.
Knowledge Graph Retrieval-Augmented Generation (KG-RAG) extends the RAG paradigm by incorporating structured knowledge from knowledge graphs, enabling Large Language Models (LLMs) to perform more precise and explainable reasoning. While KG-RAG improves factual accuracy in complex tasks, existing KG-RAG models are often severely overconfident, producing high-confidence predictions even when retrieved sub-graphs are incomplete or unreliable, which raises concerns for deployment in high-stakes domains. To address this issue, we propose Ca2KG, a Causality-aware Calibration framework for KG-RAG. Ca2KG integrates counterfactual prompting, which exposes retrieval-dependent uncertainties in knowledge quality and reasoning reliability, with a panel-based re-scoring mechanism that stabilises predictions across interventions. Extensive experiments on two complex QA datasets demonstrate that Ca2KG consistently improves calibration while maintaining or even enhancing predictive accuracy. The source code can be found at~ https://aisuko.github.io/ca2kg/.
Large Language Models (LLMs) power numerous AI applications, yet updating their knowledge remains costly. Model editing provides a lightweight alternative through targeted parameter modifications, with meta-learning-based model editing (MLME) demonstrating strong effectiveness and efficiency. However, we find that MLME struggles in low-data regimes and incurs high training costs due to the use of KL divergence. To address these issues, we propose Efficient Multi-Step Edit (EMSEdit), which leverages multi-step backpropagation (MSBP) to effectively capture gradient-activation mapping patterns within editing samples, performs multi-step edits per sample to enhance editing performance under limited data, and introduces norm-based regularization to preserve unedited knowledge while improving training efficiency. Experiments on two datasets and three LLMs show that EMSEdit consistently outperforms state-of-the-art methods in both sequential and batch editing. Moreover, MSBP can be seamlessly integrated into existing approaches to yield additional performance gains. Further experiments on a multi-hop reasoning editing task demonstrate EMSEdit's robustness in handling complex edits, while ablation studies validate the contribution of each design component. Our code is available at https://github.com/xpq-tech/emsedit.