相关论文: WAVE++: Capturing Within-Task Variance for Continu…

In this paper, we propose an effective yet efficient model PAIE for both sentence-level and document-level Event Argument Extraction (EAE), which also generalizes well when there is a lack of training data. On the one hand, PAIE utilizes…

Joint entity and relation extraction is the fundamental task of information extraction, consisting of two subtasks: named entity recognition and relation extraction. However, most existing joint extraction methods suffer from issues of…

Missing modality issues are common in real-world applications, arising from factors such as equipment failures and privacy concerns. When fine-tuning pre-trained models on downstream datasets with missing modalities, performance can degrade…

Prompt Learning has recently gained great popularity in bridging the gap between pretraining tasks and various downstream tasks. It freezes Pretrained Language Models (PLMs) and only tunes a few task-related parameters (prompts) for…

Contrastive representation learning has emerged as a promising technique for continual learning as it can learn representations that are robust to catastrophic forgetting and generalize well to unseen future tasks. Previous work in…

Current state-of-the-art large language models are effective in generating high-quality text and encapsulating a broad spectrum of world knowledge. These models, however, often hallucinate and lack locally relevant factual data.…

Humans learn adaptively and efficiently throughout their lives. However, incrementally learning tasks causes artificial neural networks to overwrite relevant information learned about older tasks, resulting in 'Catastrophic Forgetting'.…

Mixture-of-Experts models have become a dominant architecture for scaling Large Language Models by activating only a sparse subset of experts per token. However, latency-critical MoE inference faces a fundamental tension: while expert…

Prompt learning has become a prevalent strategy for adapting vision-language foundation models (VLMs) such as CLIP to downstream tasks. With the emergence of large language models (LLMs), recent studies have explored the potential of using…

Relation extraction (RE) is a core task in natural language processing. Traditional approaches typically frame RE as a supervised learning problem, directly mapping context to labels-an approach that often suffers from poor out-of-domain…

Sequential recommendation aims to provide users with personalized suggestions based on their historical interactions. When training sequential models, padding is a widely adopted technique for two main reasons: 1) The vast majority of…

Recent advances in text-to-image diffusion models have achieved impressive image generation capabilities. However, it remains challenging to control the generation process with desired properties (e.g., aesthetic quality, user intention),…

Domain-specific intelligence demands specialized knowledge and sophisticated reasoning for problem-solving, posing significant challenges for large language models (LLMs) that struggle with knowledge hallucination and inadequate reasoning…

Event relation extraction (ERE) is a critical and fundamental challenge for natural language processing. Existing work mainly focuses on directly modeling the entire document, which cannot effectively handle long-range dependencies and…

Multivariate time series forecasting often struggles to capture long-range dependencies due to fixed lookback windows. Retrieval-augmented forecasting addresses this by retrieving historical segments from memory, but existing approaches…

Document-level Relation Extraction (DocRE) aims to identify relationships between entity pairs within a document. However, most existing methods assume a uniform label distribution, resulting in suboptimal performance on real-world,…

Model merging aims to integrate task-specific abilities from individually fine-tuned models into a single model without extra training. In recent model merging methods, task vector has become a fundamental building block, as it can…

Continual learning refers to the ability to acquire and transfer knowledge without catastrophically forgetting what was previously learned. In this work, we consider \emph{few-shot} continual learning in classification tasks, and we propose…

Events describe the state changes of entities. In a document, multiple events are connected by various relations (e.g., Coreference, Temporal, Causal, and Subevent). Therefore, obtaining the connections between events through Event-Event…

We study leveraging adaptive retrieval to ensure sufficient "bridge" documents are retrieved for reasoning-intensive retrieval. Bridge documents are those that contribute to the reasoning process yet are not directly relevant to the initial…