相关论文: Beyond Memorization: A Rigorous Evaluation Framewo…

As real-world knowledge continues to evolve, the parametric knowledge acquired by multimodal models during pretraining becomes increasingly difficult to remain consistent with real-world knowledge. Existing research on multimodal knowledge…

Knowledge embeddings (KE) represent a knowledge graph (KG) by embedding entities and relations into continuous vector spaces. Existing methods are mainly structure-based or description-based. Structure-based methods learn representations…

Knowledge editing methods (KEs) are a cost-effective way to update the factual content of large language models (LLMs), but they pose a dual-use risk. While KEs are beneficial for updating outdated or incorrect information, they can be…

Large language models (LLMs) have demonstrated promising performance on medical benchmarks; however, their ability to perform medical calculations, a crucial aspect of clinical decision-making, remains underexplored and poorly evaluated.…

Drug repurposing is often framed as a candidate identification task, but existing approaches provide limited guidance for distinguishing biologically plausible candidates from historically well-connected ones. Here we introduce DrugKLM, a…

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…

Large language models (LLMs) acquire knowledge during pre-training, but over time, this knowledge may become incorrect or outdated, necessitating updates after training. Knowledge editing techniques address this issue without the need for…

Constructing domain-specific knowledge graphs from unstructured text remains challenging due to heterogeneous entity mentions, long-tail relation distributions, and the absence of standardized schemas. We present LEC-KG, a bidirectional…

Large language models (LLMs) excel at factual recall yet still propagate stale or incorrect knowledge. In-context knowledge editing offers a gradient-free remedy suitable for black-box APIs, but current editors rely on static demonstration…

Machine learning in healthcare requires effective representation of structured medical codes, but current methods face a trade off: knowledge graph based approaches capture formal relationships but miss real world patterns, while data…

Large language models (LLMs), as a novel information technology, are seeing increasing adoption in the Architecture, Engineering, and Construction (AEC) field. They have shown their potential to streamline processes throughout the building…

Adversarial attacks on knowledge graph embeddings (KGE) aim to disrupt the model's ability of link prediction by removing or inserting triples. A recent black-box method has attempted to incorporate textual and structural information to…

The popularity of large-scale pre-training has promoted the development of medical foundation models. However, some studies have shown that although foundation models exhibit strong general feature extraction capabilities, their performance…

With the emerging branch of incorporating factual knowledge into pre-trained language models such as BERT, most existing models consider shallow, static, and separately pre-trained entity embeddings, which limits the performance gains of…

In response to the pressing need for advanced clinical problem-solving tools in healthcare, we introduce BooksMed, a novel framework based on a Large Language Model (LLM). BooksMed uniquely emulates human cognitive processes to deliver…

Interpretation is critical for disease diagnosis, but existing models struggle to balance predictive accuracy with human-understandable rationales. While large language models (LLMs) offer strong reasoning abilities, their clinical use is…

Knowledge editing allows for efficient adaptation of large language models (LLMs) to new information or corrections without requiring full retraining. However, prior methods typically focus on either single-language editing or basic…

Large language models (LLMs) have garnered significant attention for their superior performance in many knowledge-driven applications on the world wide web.These models are designed to train hundreds of millions or more parameters on large…

Knowledge editing and machine unlearning are two popular approaches for large language models (LLMs) to stay up-to-date. However, the knowledge updating mechanism of LLMs remains largely unexplored due to insufficient, isolated, and…

Deep neural networks are becoming increasingly pervasive in academia and industry, matching and surpassing human performance on a wide variety of fields and related tasks. However, just as humans, even the largest artificial neural networks…