Event analysis is an essential and fundamental direction of information extraction, involving various event-centric tasks at different granularity of documents. While large language models (LLMs) have preliminarily achieved promising performance in part of these tasks individually, their capability in event analysis still lacks comprehensive understanding due to restricted document granularity, task designs, and data source of existing benchmarks. To address these limitations, we introduce MiGUE-Bench, a systematic benchmark for assessing the performance of LLMs in multi-granularity event analysis. To support large-scale evaluation, we first develop an LLM-driven self-correcting annotation framework called MiGUE-Pipeline, enabling scalable acquisition of high-quality source data of events with automatic labels. Then, we design four core tasks in our benchmark, i.e., event detection, relation reasoning, structure induction, and future prediction, to probe model competence at different levels, from atomic event details to complex cross-document narratives. Extensive experiments on state-of-the-art LLMs and retrieval-augmented generation (RAG) methods delineate the current capability boundary and identify critical deficiencies, providing insights into the future improvement of LLMs in challenging event analysis tasks.

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.

Session-based recommendation (SBR) predicts the next interaction of anonymous users based on their session data. In practical scenarios, low-exposure tail items constitute the majority of interactions, leading to the biased recommendation whereby a small set of high-exposure head items is preferentially recommended. Existing solutions focus on promoting those tail items but with a sacrifice in recommendation accuracy. We attribute such a tradeoff to session-irrelevant noise within the tail items, which existing long-tail approaches fail to identify and constrain effectively. To resolve this fundamental conflict, we propose Hybrid Intent-based Dual Constraint framework (HID) , a plug-and-play framework that converts the traditional tradeoff between long-tail performance and accuracy into a synergistic relationship by introducing hybrid intent-based dual constraints. HID incorporates two key innovations: (i) Hybrid Intent Learning , which reformulates intent extraction through attribute-aware spectral clustering and discriminates session-irrelevant noise by assigning target and noise intents to each session and (ii) Intent Constraint Loss , which introduces two constraints—diversity and accuracy—to regulate item and session representation learning. These two objectives are unified into a single training loss through rigorous theoretical derivation. To handle ambiguous user intent in the real-world, we also propose a slack version of HID. Extensive experiments show that HID enhances both long-tail performance and accuracy, establishing new state-of-the-art performance in long-tail recommender systems. The implementation code is available at: https://github.com/jarviswww/Code4TradeSynergy .

Large language models (LLMs) have been demonstrated to possess the capabilities to understand fundamental graph properties and address various graph reasoning tasks. Existing methods fine-tune LLMs to understand and execute graph reasoning tasks by specially designed task instructions. However, these Text-Instruction methods generally exhibit poor performance. Inspired by tool learning, researchers propose Tool-Instruction methods to solve various graph problems by special tool calling (e.g., function, API and model), achieving significant improvements in graph reasoning tasks. Nevertheless, current Tool-Instruction approaches focus on the tool information and ignore the graph structure information, which leads to significantly inferior performance on small-scale LLMs (less than 8B). To tackle this issue, we propose GraphTool-Instruction, an innovative Instruction-tuning approach that decomposes the graph reasoning task into three distinct subtasks (i.e., graph extraction, tool name identification and tool parameter extraction), and design specialized instructions for each subtask. Our GraphTool-Instruction can be used as a plug-and-play prompt for different LLMs without fine-tuning. Moreover, building on GraphTool-Instruction, we develop GTools, a dataset that includes twenty graph reasoning tasks, and create a graph reasoning LLM called GraphForge based on Llama3-8B. We conduct extensive experiments on twenty graph reasoning tasks with different graph types (e.g., graph size or graph direction), and we find that GraphTool-Instruction achieves SOTA compared to Text-Instruction and Tool-Instruction methods. Fine-tuned on GTools, GraphForge gets further improvement of over 30% compared to the Tool-Instruction enhanced GPT-3.5-turbo, and it performs comparably to the high-cost GPT-4o. Our codes and data are available at https://github.com/RongzhengWang/GraphTool-Instruction.

Recently, prompt tuning has garnered considerable attention due to its success across various Vision-Language (VL) tasks. However, unimodal prompts, coupled prompts, and joint prompts in these models often lead to suboptimal performance due to differences in information density and complexity between modalities. Particularly, in scenarios with missing modalities, these prompt-based approaches tend to exacerbate 'Channel Bias'-a phonomenon where models overly rely on specific feature (such as unmissing-modal feature) channels from the base tasks, thereby undermining the model's ability to capture crucial shared knowledge applicable to new tasks and affecting its generalizability. To address this challenge, we propose RobustPT, a dynamic disentanglement prompt tuning model designed to enhance the robustness of VL models under modality missing conditions. RobustPT utilizes a multi-channel prompting mechanism to dynamically disentangle and align prompts. Specifically, RobustPT is divided into single-channel tuning and alignment-channel tuning, where prompts for each modality run independently in sequence to delve deeply into their intrinsic characteristics, followed by an integration through a non-strong coupling strategy to effectively balance information contributions and enhance overall performance. Extensive experiments demonstrate that our RobustPT achieve significant improvements over the current state-of-the-art across all benchmark datasets. Our codes are available at https://github.com/Trae1ounG/RobustPT.

Abstract Session-based recommendation (SBR) focuses on predicting the next potential item for anonymous users based on short-click sessions. However, these interaction sessions often contain noise items, which arise from misclicks or shifts in user interests. Existing denoising methods typically presume a strong exclusionary relationship between noise items and the recommendation target, assuming that reducing noise can enhance recommendation accuracy. In contrast, our observations reveal a nuanced phenomenon: as the length of the interaction session shortens, the effect of noise removal on recommendation performance gradually transitions from positive to negative. This finding suggests that in short sessions with insufficient contextual information, relying solely on the exclusion of noise items within the session may fail to improve and could even hinder-the recommendation performance. Such complexities have been largely overlooked in prior research. To bridge this gap, we propose two solutions: (i) expanding the view of denoising from a single session to multiple sessions (i.e., from local to global), and (ii) introducing relevant contextual information into each session by employing enhancement strategies. Therefore, we design the Hybrid Prototype-based In-and-Out Flow Network (HyPro), which employs both denoising and enhancing processes for each session based on our proposed hybrid prototypes. Specifically, for each item, HyPro first learns the hybrid prototype by aggregating information from the item’s semantic and topological neighbors across all sessions. Then, based on the hybrid prototypes, HyPro employs an in-and-out flow network comprising two components: (i) the out-flow channel, which targets the removal of irrelevant information at both the data and feature levels, and (ii) the in-flow channel, which integrates global information for each session at the item and session levels. Extensive experiments conducted on three real-world datasets demonstrate that HyPro outperforms the state-of-the-art baselines. The implementation code is available at: https://github.com/jarviswww/Code4HyPro .

In recent years, thanks to the vigorous development of deep learning, single image super-resolution has advanced greatly. Most super-resolution (SR) methods use convolution layers to construct the network, which achieves superior results over the traditional methods based on manual features. However, most methods based on convolutional neural networks (CNN) blindly deepen the depth of the network leading to a large number of model parameters, which inevitably brings huge computing overhead and memory consumption, and greatly limits the application in resource-limited devices. In order to alleviate this problem, a knowledge distillation framework based on contrastive learning is proposed to compress and accelerate the SR model with enormous parameters. The student network is directly constructed by reducing the number of layers of the teacher network. In particular, the proposed method distills the statistical information of the intermediate feature maps from the teacher network to train the lightweight student network. In addition, through explicit knowledge transfer, a novel contrastive loss is introduced to improve the reconstruction performance of the student network. Experiments show that the proposed contrastive distillation framework can effectively compress the model scale with an acceptable loss of performance.