Related papers: TRACE: TRansformer-based Attribution using Contras…

Deploying machine learning models in resource-constrained environments, such as edge devices or rapid prototyping scenarios, increasingly demands distillation of large datasets into significantly smaller yet informative synthetic datasets.…

Computational stylometry studies writing style through quantitative textual patterns, enabling applications such as authorship attribution, identity linking, and plagiarism detection. Existing supervised and contrastive approaches often…

Most Neural Networks (NNs) for classification are trained using Cross-Entropy as a loss function. This approach requires the model to have an explicit classification layer. However, there exist alternative approaches, such as Contrastive…

Prior study has shown that pretrained language models (PLM) can boost the performance of text-based recommendation. In contrast to previous works that either use PLM to encode user history as a whole input text, or impose an additional…

Most modern computational approaches to lexical semantic change detection (LSC) rely on embedding-based distributional word representations with neural networks. Despite the strong performance on LSC benchmarks, they are often opaque. We…

Contrastive learning (CL) is a popular technique for self-supervised learning (SSL) of visual representations. It uses pairs of augmentations of unlabeled training examples to define a classification task for pretext learning of a deep…

Scene graphs are a powerful structured representation of the underlying content of images, and embeddings derived from them have been shown to be useful in multiple downstream tasks. In this work, we employ a graph convolutional network to…

Failure attribution, i.e., identifying the responsible agent and decisive step of a failure, is particularly challenging in LLM-based multi-agent systems (MAS) due to their natural-language reasoning, nondeterministic outputs, and intricate…

Despite their outstanding capabilities, large language models (LLMs) are prone to hallucination and producing factually incorrect information. This challenge has spurred efforts in attributed text generation, which prompts LLMs to generate…

Recent advances in large language models (LLMs) and agent system designs have empowered agents with unprecedented levels of capability. However, existing agent benchmarks are showing a trend of rapid ceiling-hitting by newly developed…

Continual relation extraction (CRE) aims to extract relations towards the continuous and iterative arrival of new data, of which the major challenge is the catastrophic forgetting of old tasks. In order to alleviate this critical problem…

Multiview network embedding aims at projecting nodes in the network to low-dimensional vectors, while preserving their multiple relations and attribute information. Contrastive learning approaches have shown promising performance in this…

Recently, large language models (LLMs) have emerged as a groundbreaking technology and their unparalleled text generation capabilities have sparked interest in their application to the fundamental sentence representation learning task.…

Reward modeling is essential for aligning Large Language Models(LLMs) with human preferences, yet conventional reward models suffer from poor interpretability and heavy reliance on costly expert annotations. While recent rubric-based…

Contrastive learning has been used to learn a high-quality representation of the image in computer vision. However, contrastive learning is not widely utilized in natural language processing due to the lack of a general method of data…

Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language Models (LLMs). However, existing methods rely on limited and inherently biased contrastive prompts and require laborious manual tuning of…

Large language models (LLMs) excel in natural language processing but adapting these LLMs to speech processing tasks efficiently is not straightforward. Direct task-specific fine-tuning is limited by overfitting risks, data requirements,…

Vision-Language Models (VLMs) struggle to translate high-level instructions into the precise spatial affordances required for robotic manipulation. While visual Chain-of-Thought (CoT) methods exist, they are often computationally intensive.…

Contrastive learning has been frequently investigated to learn effective representations for text clustering tasks. While existing contrastive learning-based text clustering methods only focus on modeling instance-wise semantic similarity…

Recent advances in reinforcement learning for code generation have made robust environments essential to prevent reward hacking. As LLMs increasingly serve as evaluators in code-based RL, their ability to detect reward hacking remains…