相关论文: In-context Contrastive Learning for Event Causalit…

Detecting Alzheimer's Disease (AD) from narrative transcripts remains a challenging task for large language models (LLMs), particularly under out-of-distribution (OOD) and data-scarce conditions. While in-context learning (ICL) provides a…

Recent advancements in language models have demonstrated remarkable in-context learning abilities, prompting the exploration of in-context reinforcement learning (ICRL) to extend the promise to decision domains. Due to involving more…

In-context learning (ICL) adapts LLMs by providing demonstrations without fine-tuning the model parameters; however, it does not differentiate between demonstrations and quadratically increases the complexity of Transformer LLMs, exhausting…

In-context learning (ICL) allows large language models (LLMs) to solve novel tasks without weight updates. Despite its empirical success, the mechanism behind ICL remains poorly understood, limiting our ability to interpret, improve, and…

High-quality phrase representations are essential to finding topics and related terms in documents (a.k.a. topic mining). Existing phrase representation learning methods either simply combine unigram representations in a context-free manner…

Most existing causal structure learning methods assume data collected from one environment and independent and identically distributed (i.i.d.). In some cases, data are collected from different subjects from multiple environments, which…

In-Context Learning (ICL) has emerged as a pivotal capability of auto-regressive large language models, yet it is hindered by a notable sensitivity to the ordering of context examples regardless of their mutual independence. To address this…

Language models, especially pre-trained large language models, have showcased remarkable abilities as few-shot in-context learners (ICL), adept at adapting to new tasks with just a few demonstrations in the input context. However, the…

Contrastive explanations clarify why an event occurred in contrast to another. They are more inherently intuitive to humans to both produce and comprehend. We propose a methodology to produce contrastive explanations for classification…

Contrastive learning has achieved remarkable success in representation learning via self-supervision in unsupervised settings. However, effectively adapting contrastive learning to supervised learning tasks remains as a challenge in…

Predicting events such as political protests, flu epidemics, and criminal activities is crucial to proactively taking necessary measures and implementing required responses to address emerging challenges. Capturing contextual information…

Large-scale models trained on extensive datasets, have emerged as the preferred approach due to their high generalizability across various tasks. In-context learning (ICL), a popular strategy in natural language processing, uses such models…

This paper proposes to perform online clustering by conducting twin contrastive learning (TCL) at the instance and cluster level. Specifically, we find that when the data is projected into a feature space with a dimensionality of the target…

Demonstration learning aims to guide the prompt prediction via providing answered demonstrations in the few shot settings. Despite achieving promising results, existing work only concatenates the answered examples as demonstrations to the…

Contrastive learning has achieved remarkable success in self-supervised representation learning, often guided by information-theoretic objectives such as mutual information maximization. Motivated by the limitations of static augmentations…

Despite its success, existing in-context learning (ICL) relies on in-domain expert demonstrations, limiting its applicability when expert annotations are scarce. We posit that different domains may share underlying reasoning structures,…

In this study, we investigate in-context learning (ICL) in document-level event argument extraction (EAE) to alleviate the dependency on large-scale labeled data for this task. We introduce the Heuristic-Driven Link-of-Analogy (HD-LoA)…

As one of the most effective self-supervised representation learning methods, contrastive learning (CL) relies on multiple negative pairs to contrast against each positive pair. In the standard practice of contrastive learning, data…

This work aims to adapt large-scale pre-trained vision-language models, such as contrastive language-image pretraining (CLIP), to enhance the performance of object reidentification (Re-ID) across various supervision settings. Although…

Contrastive Language-Image Pretraining (CLIP) models excel at understanding image-text relationships but struggle with adapting to new data without forgetting prior knowledge. To address this, models are typically fine-tuned using both new…