Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) with external knowledge retrieval, improving factual accuracy and knowledge coverage. However, existing RAG approaches face a fundamental trade-off when handling complex reasoning: while traditional iterative retrieval methods offer flexibility, their local perspective limits their ability to establish global knowledge connections. In contrast, structure-augmented RAG methods capture global relationships but incur significant construction costs. To fill in this gap, we propose MGranRAG, an innovative framework designed to integrate precise local retrieval with structured global reasoning. Our approach circumvents expensive semantic extraction by employing a lightweight contextual hierarchical graph, effectively combining the local adaptability of iterative retrieval with the global consistency of structured knowledge. The framework adopts a novel iterative optimization scheme: at the local level, the LLM identifies multi-granular contextual evidence, such as key sentences and phrases, within retrieved passages to refine retrieval. At the global level, these multi-granularity evidence nodes are then mapped and propagated within the structured hierarchical graph, enabling the diffusion of rich contextual information at different levels to introduce global semantic constraints and reorder retrieval results. This coordination between local and global iterative processes dynamically balances retrieval accuracy and contextual coherence. Experimental results on challenging multi-hop and open-domain question answering datasets show that our proposal achieves new state-of-the-art performance in both retrieval and answer accuracy.

The evolving worldly dynamics necessitate continuous revision and updating of knowledge within Large Language Models (LLMs), driving the development of Knowledge Editing (KE) techniques. Recently, a novel paradigm of Temporal Knowledge Editing (TKE) has been proposed, emphasizing that models deployed in dynamic environments should integrate new information while retaining historical knowledge. However, we observe that current definitions and methods for TKE are insufficient, as they do not effectively capture or adapt to the fine-grained temporal dynamics inherent in real-world knowledge evolution. In this paper, we introduce the notion of multi-granularity TKE, encompassing temporal knowledge across yearly, monthly, and daily granularities, and propose a corresponding dataset, named MTKE. We argue that comprehending and retaining knowledge across different temporal granularities is crucial for LLMs to accurately reflect real-world changes. The key challenge lies in integrating new temporal knowledge at various granularities while also preserving relevant historical knowledge, thus ensuring LLMs maintain a consistent and accurate understanding over time. To achieve this, we propose a Sparse Parameter-Injected Knowledge Editing method, dubbed SPIKE, which anchors both temporal knowledge and subject positions within the model. Experiments demonstrate that our method effectively preserves historical knowledge performance while accurately incorporating dynamic temporal knowledge across multi-granularity temporal scenarios.

Multimedia event extraction aims to jointly extract event structural knowledge from multiple modalities, thus improving the comprehension and utilization of events in the growing multimedia content (e.g., multimedia news). A key challenge in multimedia event extraction is to establish cross-modal correlations during training without multimedia event annotations. Considering the complexity and cost of annotation across modalities, the multimedia event extraction task only provides parallel annotated data for evaluation. Previous works attempt to learn implicit correlations directly from unlabeled image-text pairs, but do not yield substantially better performance for event-centric tasks. To address this problem, we propose a cross-modal multi-task learning framework X-MTL to establish cross-modal correlations at the task level, which can simultaneously address four key tasks of multimedia event extraction: trigger detection, argument extraction, verb classification, and role classification. Specifically, to process inputs from different modalities and tasks, we utilize two separate modality-specific encoders and a modality-shared encoder to learn joint task representations, and introduce textual and visual prompt learning methods to enrich and unify task inputs. To resolve task conflict in cross-modal multi-task learning, we propose a pseudo label based knowledge distillation method, combined with dynamic weight adjustment method, which can effectively lift the performance to surpass the separately-trained models. On the Multimedia Event Extraction benchmark M2E2, experimental results show that X-MTL surpasses the current state-of-the-art (SOTA) methods by 4.1% for multimedia event mention and 8.2% for multimedia argument role.

Script Event Prediction (SEP) aims to forecast the next event in a sequence from a list of candidates. Traditional methods often use pre-trained language models to model event associations but struggle with semantic ambiguity and embedding bias. Semantic ambiguity arises from the multiple meanings of identical words and insufficient consideration of event arguments, while embedding bias results from assigning similar word embeddings to event pairs with similar lexical features, despite their different meanings. To address above issues, we propose a the Semantic and Sentiment Dual-enhanced Generative Model (SSD-GM). SSD-GM leverages two types of script event information to enhance the generative model. Specifically, it employs a GNN-based semantic structure aggregator to integrate the event-centric structure information, thereby mitigating the impact of semantic ambiguity. Furthermore, we find that local sentiment variability effectively reduces biases in event embeddings, while maintaining global sentiment consistency enhances predictive accuracy. As a result, SSD-GM adeptly captures both global and local sentiment of events through its sentiment information awareness mechanism. Extensive experiments on the Multi-Choice Narrative Cloze (MCNC) task demonstrate that our approach achieves better results than other state-of-the-art baselines.

The dependency propagation problem is to determine, given a view defined on data sources and a set of dependencies on the sources, whether another dependency is guaranteed to hold on the view. This paper investigates dependency propagation for recently proposed conditional functional dependencies (CFDs). The need for this study is evident in data integration, exchange and cleaning since dependencies on data sources often only hold conditionally on the view. We investigate dependency propagation for views defined in various fragments of relational algebra, CFDs as view dependencies, and for source dependencies given as either CFDs or traditional functional dependencies (FDs). (a) We establish lower and upper bounds, all matching , ranging from PTIME to undecidable. These not only provide the first results for CFD propagation, but also extend the classical work of FD propagation by giving new complexity bounds in the presence of finite domains. (b) We provide the first algorithm for computing a minimal cover of all CFDs propagated via SPC views; the algorithm has the same complexity as one of the most efficient algorithms for computing a cover of FDs propagated via a projection view, despite the increased expressive power of CFDs and SPC views. (c) We experimentally verify that the algorithm is efficient.