Related papers: ContraCLM: Contrastive Learning For Causal Languag…

Recent Visual Question Answering (VQA) models have shown impressive performance on the VQA benchmark but remain sensitive to small linguistic variations in input questions. Existing approaches address this by augmenting the dataset with…

Causal reasoning (CR) is a crucial aspect of intelligence, essential for problem-solving, decision-making, and understanding the world. While language models (LMs) can generate rationales for their outputs, their ability to reliably perform…

Large Language Models (LLMs) have achieved remarkable performance across various reasoning tasks, yet post-training is constrained by inefficient sample utilization and inflexible difficulty samples processing. To address these limitations,…

As LLMs evolve, significant effort is spent on manually crafting prompts. While existing prompt optimization methods automate this process, they rely solely on learning from incorrect samples, leading to a sub-optimal performance.…

Stance detection classifies stance relations (namely, Favor, Against, or Neither) between comments and targets. Pretrained language models (PLMs) are widely used to mine the stance relation to improve the performance of stance detection…

Text representation plays a critical role in tasks like clustering, retrieval, and other downstream applications. With the emergence of large language models (LLMs), there is increasing interest in harnessing their capabilities for this…

Multi-modal large language models (MLLMs) have been shown to efficiently integrate natural language with visual information to handle multi-modal tasks. However, MLLMs still face a fundamental limitation of hallucinations, where they tend…

The pre-training for language models captures general language understanding but fails to distinguish the affective impact of a particular context to a specific word. Recent works have sought to introduce contrastive learning (CL) for…

Visual recognition is recently learned via either supervised learning on human-annotated image-label data or language-image contrastive learning with webly-crawled image-text pairs. While supervised learning may result in a more…

Neural networks have revolutionized various domains, exhibiting remarkable accuracy in tasks like natural language processing and computer vision. However, their vulnerability to slight alterations in input samples poses challenges,…

Contrastive learning is a powerful framework for learning self-supervised representations that generalize well to downstream supervised tasks. We show that multiple existing contrastive learning methods can be reinterpreted as learning…

Currently, learning better unsupervised sentence representations is the pursuit of many natural language processing communities. Lots of approaches based on pre-trained language models (PLMs) and contrastive learning have achieved promising…

Multimodal representation learning is a challenging task in which previous work mostly focus on either uni-modality pre-training or cross-modality fusion. In fact, we regard modeling multimodal representation as building a skyscraper, where…

Despite significant advancements in Vision-Language Models (VLMs), the performance of existing VLMs remains hindered by object hallucination, a critical challenge to achieving accurate visual understanding. To address this issue, we propose…

Prevailing methods for training Large Language Models (LLMs) as text encoders rely on contrastive losses that treat the model as a black box function, discarding its generative and reasoning capabilities in favor of static embeddings. We…

Reliable AI systems require large language models (LLMs) to exhibit behaviors aligned with human preferences and values. However, most existing alignment approaches operate at training time and rely on additional high-quality data,…

Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes. Existing debiasing methods for classification models, such as adversarial…

Contrastive learning has achieved state-of-the-art performance in various self-supervised learning tasks and even outperforms its supervised counterpart. Despite its empirical success, theoretical understanding of the superiority of…

Protein language models often take into consideration the alignment between a protein sequence and its textual description. However, they do not take structural information into consideration. Traditional methods treat sequence and…

The deployment of large language models (LLMs) faces considerable challenges concerning resource constraints and inference efficiency. Recent research has increasingly focused on smaller, task-specific models enhanced by distilling…