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.
论文检索
输入标题、作者或关键词，从 954 篇学术成果中精准定位
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.
Equipping large language models (LLMs) with external tools has emerged as a promising paradigm for addressing real-world tasks. Nonetheless, with the web-based tool ecosystems rapidly expanding, it is impractical to include all tools within the limited input length of LLMs. To alleviate these issues, researchers have explored incorporating a tool retrieval module to select the most relevant tools or represent tools as unique tokens within LLM parameters. However, most state-of-the-art methods are under transductive settings, assuming all tools have been observed during training. Such a setting deviates from reality as tools on the web are constantly updated and new tools are frequently added to the online ecosystem. When dealing with these unseen tools, which refer to tools not encountered during the training phase, these methods are limited by two key issues, including the large distribution shift and the sensitivity of semantic-only retrieval. To this end, inspired by human cognitive processes of mastering unseen tools through discovering and applying the logical information from prior experience, we introduce a novel Logic-Guided Semantic Bridging framework for inductive tool retrieval, namely, LoSemB, which aims to mine and transfer latent logical information for inductive tool retrieval without costly retraining. Specifically, LoSemB contains a logic-based embedding alignment module to mitigate distribution shifts and a relational augmented retrieval mechanism to overcome the limitations of semantic-only similarity methods. Extensive experiments demonstrate that LoSemB achieves advanced performance in both the inductive and transductive settings.
LLM-based empathetic dialogue systems enhance agents' emotional support capabilities. Previous approaches primarily relied on Chain-of-Thought (CoT) prompting to extract key dialogue cues and further strengthened the agent's sensitivity to these signals through supervised fine-tuning. However, such methods overly depend on the information extraction capability of LLMs, leading to unstable reasoning and limited interpretability. To simultaneously improve an agent's ability to proactively explore solutions through rational reasoning while attending to users' sensitive emotions via empathetic understanding, we propose Neuro-Sym Supporter, a hybrid decision-making emotional support agent that integrates symbolic reasoning with deep learning. This model combines rational inference with emotional empathy, enabling the agent to generate supportive responses that balance logic and emotion. Specifically, we introduce Sym-Mind, a differentiable logic-based reasoning framework for emotional support strategy selection, which unifies interpretability with stable performance. Experimental results on public datasets demonstrate that our approach consistently outperforms multiple competitive baselines in both automatic and human evaluations, validating its effectiveness.
Large language models (LLMs) show promising performance on small-scale graph reasoning tasks but fail when handling real-world graphs with complex queries. This phenomenon arises from LLMs' working memory constraints, which result in their inability to retain long-range graph topology over extended contexts while sustaining coherent multi-step reasoning. However, real-world graphs are often structurally complex, such as Web, Transportation, Social, and Citation networks. To address these limitations, we propose GraphCogent, a collaborative agent framework inspired by human Working Memory Model that decomposes graph reasoning into specialized cognitive processes: sense, buffer, and execute. The framework consists of three modules: Sensory Module standardizes diverse graph text representations via subgraph sampling, Buffer Module integrates and indexes graph data across multiple formats, and Execution Module combines tool calling and tool creation for efficient reasoning. We also introduce Graph4real, a comprehensive benchmark that contains four domains of real-world graphs (Web, Transportation, Social, and Citation) to evaluate LLMs' graph reasoning capabilities. Our Graph4real covers 21 different graph reasoning tasks, categorized into three types (Structural Querying, Algorithmic Reasoning, and Predictive Modeling tasks), with graph scales up to 10 times larger than existing benchmarks. Experiments show that Llama3.1-8B based GraphCogent achieves a 50% improvement over massive-scale LLMs like DeepSeek-R1 (671B). Compared to state-of-the-art code-based baseline, our framework outperforms by 20% in accuracy while reducing token usage by 80% for in-toolset tasks and 30% for out-toolset tasks.
Dual History Enhancement with Hybrid Hypergraph-Graph Networks for Temporal Knowledge Graph Reasoning
PDF ↗Temporal Knowledge Graph (TKG) reasoning seeks to predict future events by analyzing historical data, where the effective leverage of both local and global historical facts proves crucial. Existing approaches employ graph neural networks (GNNs) and recurrent neural networks (RNNs) for local evolution patterns, complemented by statistical methods to enhance attention to global facts, demonstrating efficient predictive capabilities. However, traditional GNNs, constrained by their low-order neighborhood aggregation design, inherently fail to model potential high-order dependencies among facts. Furthermore, existing global history modeling approaches may introduce irrelevant historical information that interferes with prediction tasks. To address these limitations, we propose a Dual History-aware HyperGraph Network for TKG reasoning, namely DHHGN. Specifically, for local history modeling, we design a hybrid hypergraph-graph joint recurrent convolution module that simultaneously captures low-order neighborhood information and high-order interaction patterns among entities, employing a gating mechanism to adaptively blend their contributions. For global history modeling, we propose a dual history enhancement module that amplifies attention on pivotal historical facts while ensuring holistic integration of all historical contexts. Extensive experiments on four public benchmarks validate that DualHist-HGN consistently outperforms existing state-of-the-art methods across TKG reasoning tasks.
With the rapid growth of multi-modal content on the Web, robust vision-language models are essential for semantic understanding and classification of web images under diverse and dynamic contexts, supporting Web applications such as multimedia search and recommendation. Prompt learning has proven effective for enhancing vision-language models in semantic image classification tasks. However, previous methods often suffer from poor generalization: the learned prompts tend to overfit the base classes seen during training, leading to poor performance on unseen classes and under distribution shifts. This issue is especially challenging in Web-scale data, where new classes emerge and distributions shift dynamically. To address these limitations, we propose PLIKD, a novel prompt learning method that integrates instance-aware knowledge distillation for robust Web-scale semantic image classification. Specifically, PLIKD introduces an instance-aware knowledge extraction module, which leverages multi-modal large language models through a step-by-step strategy to extract external knowledge for each image instance. To incorporate this extracted knowledge, PLIKD further introduces an instance-aware knowledge distillation module, which consists of two key steps: (1) a dual-teacher strategy for robust and informative knowledge distillation, and (2) fine-grained cross-modal alignment via Smooth and Sparse Optimal Transport. Extensive experiments demonstrate that PLIKD significantly improves generalization to both seen and unseen classes, and remains robust under distribution shifts, outperforming existing state-of-the-art methods on Web-scale semantic image classification.
The multimodal Chinese idiom reading comprehension task aims to select the most appropriate idiom from a candidate list via the given text and image. This poses a significant challenge for the model to comprehend each Chinese idiom accurately. Existing multimodal Chinese idiom reading comprehension methods primarily focus on aligning contextual text and images, while overlooking two key attributes of Chinese idioms.(1) There is a discrepancy between the literal and metaphorical meanings of Chinese idioms. (2) The same Chinese idiom has different meanings in different scenarios, which requires targeted understanding by experts who specialize in different fields. To address the above challenges, we rethink the solution to the multimodal idiom reading comprehension task from a metaphorical perspective and propose a framework named MePe. Firstly, we propose a literal metaphorical semantic graph that systematically transforms the implicit discrepancy between the literal and metaphorical meanings of Chinese idioms into structured explicit relationships, thereby making metaphorical meanings more understandable. Then, we propose a mixture of idiom experts consisting of a literal idiom expert and a metaphorical idiom expert. Through division of labor and collaboration among these experts, we achieve an understanding of the dual meanings of Chinese idioms across different scenarios. Finally, we employ the maximum mean discrepancy to adjust the variance between the literal and metaphorical semantic features of Chinese idioms. By mapping these features onto a shared reproducing kernel Hilbert space, the model can better distinguish between the two based on contextual clues. Extensive experiments demonstrate that MePe achieves state-of-the-art performance on the MChIRC dataset.