相关论文: From Mimicking to Integrating: Knowledge Integrati…

Machine unlearning (MU) seeks to remove knowledge of specific data samples from trained models without the necessity for complete retraining, a task made challenging by the dual objectives of effective erasure of data and maintaining the…

For named entity recognition (NER) in zero-resource languages, utilizing knowledge distillation methods to transfer language-independent knowledge from the rich-resource source languages to zero-resource languages is an effective means.…

Recent advances in product bundling have leveraged multimodal information through sophisticated encoders, but remain constrained by limited semantic understanding and a narrow scope of knowledge. Therefore, some attempts employ In-context…

Although large language models (LLMs) have demonstrated remarkable capabilities in recent years, the potential of information theory (IT) to enhance LLM development remains underexplored. This paper introduces the information theoretic…

The development of machine learning models has led to an abundance of datasets containing quantum mechanical (QM) calculations for molecular and material systems. However, traditional training methods for machine learning models are unable…

As multimedia content expands, the demand for unified multimodal retrieval (UMR) in real-world applications increases. Recent work leverages multimodal large language models (MLLMs) to tackle this task. However, their large parameter size…

In this study, we reveal an in-context learning (ICL) capability of multilingual large language models (LLMs): by translating the input to several languages, we provide Parallel Input in Multiple Languages (PiM) to LLMs, which significantly…

Integrating domain knowledge into deep neural networks is a promising way to improve generalization. Existing methods either encode prior knowledge in the loss function or apply post-processing modules, but both depend on identifying useful…

Humans learn language via multi-modal knowledge. However, due to the text-only pre-training scheme, most existing pre-trained language models (PLMs) are hindered from the multi-modal information. To inject visual knowledge into PLMs,…

Software reuse has long been recognized as a critical and widely studied topic in software engineering, offering substantial benefits in reducing development costs, improving software quality, and enhancing operational efficiency. This…

Model merging combines the parameters of multiple neural networks into a single model without additional training. As fine-tuned large language models (LLMs) proliferate, merging offers a computationally efficient alternative to ensembles…

To steer pretrained language models for downstream tasks, today's post-training paradigm relies on humans to specify desired behaviors. However, for models with superhuman capabilities, it is difficult or impossible to get high-quality…

Recent advancements in visiolinguistic (VL) learning have allowed the development of multiple models and techniques that offer several impressive implementations, able to currently resolve a variety of tasks that require the collaboration…

Integrating structured knowledge from Knowledge Graphs (KGs) into Large Language Models (LLMs) enhances factual grounding and reasoning capabilities. This survey paper systematically examines the synergy between KGs and LLMs, categorizing…

Knowledge plays a critical role in artificial intelligence. Recently, the extensive success of pre-trained language models (PLMs) has raised significant attention about how knowledge can be acquired, maintained, updated and used by language…

Machine Unlearning (MU) technology facilitates the removal of the influence of specific data instances from trained models on request. Despite rapid advancements in MU technology, its vulnerabilities are still underexplored, posing…

Multi-modal Large Language Models (MLLMs) have shown remarkable capabilities in various multi-modal tasks. Nevertheless, their performance in fine-grained image understanding tasks is still limited. To address this issue, this paper…

Multimodal foundation models have demonstrated impressive generalization capabilities, yet efficiently adapting them to new tasks in a few-shot setting remains a critical challenge. In this work, we investigate the few-shot adaptation of…

Information retrieval aims to find information that meets users' needs from the corpus. Different needs correspond to different IR tasks such as document retrieval, open-domain question answering, retrieval-based dialogue, etc., while they…

Cognitive Diagnosis Models (CDMs) are designed to assess students' cognitive states by analyzing their performance across a series of exercises. However, existing CDMs often struggle with diagnosing infrequent students and exercises due to…