23 accepted papers
Large Vision-Language Models (LVLMs) have achieved impressive performance across multimodal understanding and reasoning tasks, yet their internal safety mechanisms remain opaque and poorly controlled. In this work, we present a comprehensive framework for diagnosing and repairing unsafe channels wit
Despite the strong performance of Large Language Models (LLMs) on complex instruction-following tasks, precise control of output length remains a persistent challenge. Existing methods primarily attempt to enforce length constraints by externally imposing length signals or optimization objectives, w…
Graph Neural Networks (GNNs) are widely used in high-stakes decision-making, where explanation robustness is crucial. Yet, even minor structural perturbations can drastically change explanations without changing predictions. Existing methods primarily characterize structural perturbations by their e
Multi-domain graph pre-training integrates knowledge from diverse domains to enhance performance in the target domains, which is crucial for building graph foundation models. Despite initial success, existing solutions often fall short of answering a fundamental question: how is knowledge integrated…
Fine-tuning Large Language Models (LLMs) enables data holders to construct proprietary, task-specific models by leveraging external high-performance computing infrastructure. However, existing paradigms typically address data privacy and model intellectual property (IP) in isolation, failing to simu…
Steering Vector (SV) is a powerful technique for controlling Large Language Models (LLMs) by manipulating their activations without altering model weights. However, when constructed from sensitive data, SV poses significant privacy risks, as it may leak private information. Existing differential pri
Data heterogeneity poses a critical challenge in federated learning, driving the development of personalized client models. However, when each client’s local data is limited and nonindependent and identically distributed (non-IID), previous efforts fail to implement collaborative strategies based on…
Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks yet still are vulnerable to external threats, particularly LLM Denial-of-Service (LLM-DoS) attacks. Specifically, LLM-DoS attacks aim to exhaust computational resources and block services. However, existing st…
Large language models (LLMs) have shown strong potential in complex reasoning tasks. However, as task complexity increases, their performance often degrades, resulting in hallucinations, errors, and logical inconsistencies. To enhance reasoning capabilities, Monte Carlo Tree Search (MCTS) has been i
As LLM-based agents become increasingly prevalent, triggers implanted in user queries or environment feedback can activate hidden backdoors, raising critical concerns about safety vulnerabilities in agents.However, traditional backdoor attacks are often detectable by safety audits that analyze the r
Graph Neural Networks (GNNs) have demonstrated superior performance in a variety of graph mining and learning tasks. However, when node representations involve sensitive personal information or variables related to individuals, learning from graph data can raise significant privacy concerns. Althoug…
Large Language Models (LLMs) have revolutionized language processing and understanding, yet their performance is hampered by inaccuracies and outdated information. Model editing techniques offer a solution but face two key challenges: **(I)** Most methods inject knowledge by constructing rigid loss,
While large language models (LLMs) can solve PhD-level reasoning problems over long context inputs, they still struggle with a seemingly simpler task: *following explicit length instructions*—e.g., *write a 10,000-word novel*. Additionally, models often generate far too short outputs, terminate prem…
Large Language Models (LLMs), due to substantial computational requirements, are vulnerable to resource consumption attacks, which can severely degrade server performance or even cause crashes, as demonstrated by denial-of-service (DoS) attacks designed for LLMs. However, existing works lack mitigat
Ensuring that large language models (LLMs) remain both helpful and harmless poses a significant challenge: fine-tuning on repetitive safety datasets—where unsafe prompts are paired with standard refusal templates—often leads to \emph{false refusals}, in which benign queries are declined. We first qu…
Mixture-of-Experts (MoE) shines brightly in large language models (LLMs) and demonstrates outstanding performance in plentiful natural language processing tasks. However, existing methods transforming LLMs from dense to MoE face significant data requirements and typically rely on large-scale post-tr…
Large language models are susceptible to jailbreak attacks, which can result in the generation of harmful content. While prior defenses mitigate these risks by perturbing or inspecting inputs, they ignore competing objectives, the underlying cause of alignment failures. In this paper, we propose Ali…
Large language models (LLMs) have been proven capable of memorizing their training data, which can be extracted through specifically designed prompts. As the scale of datasets continues to grow, privacy risks arising from memorization have attracted increasing attention. Quantifying language model m…
Graph representation learning received increasing attentions in recent years. Most of the existing methods ignore the complexity of the graph structures and restrict graphs in a single constant-curvature representation space, which is only suitable to particular kinds of graph structure indeed. Addi…
Learning representations for graphs plays a critical role in a wide spectrum of downstream applications. In this paper, we summarize the limitations of the prior works in three folds: representation space, modeling dynamics and modeling uncertainty. To bridge this gap, we propose to learn dynamic gr…
Event detection (ED) aims at identifying event instances of specified types in given texts, which has been formalized as a sequence labeling task. As far as we know, existing neural-based ED models make decisions relying entirely on the contextual semantic features of each word in the inputted text,…
Recently, aligning users among different social networks has received significant attention. However, most of the existing studies do not consider users’ behavior information during the aligning procedure and thus still suffer from the poor learning performance. In fact, we observe that social netwo…
Multi-modality fusion technologies have greatly improved the performance of neural network-based Video Description/Caption, Visual Question Answering (VQA) and Audio Visual Scene-aware Dialog (AVSD) over the recent years. Most previous approaches only explore the last layers of multiple layer featur…