相关论文: AdvSumm: Adversarial Training for Bias Mitigation …

Adversarial attack is commonly regarded as a huge threat to neural networks because of misleading behavior. This paper presents an opposite perspective: adversarial attacks can be harnessed to improve neural models if amended correctly.…

Handwritten Word Recognition and Spotting is a challenging field dealing with handwritten text possessing irregular and complex shapes. The design of deep neural network models makes it necessary to extend training datasets in order to…

Previous works have shown that automatic speaker verification (ASV) is seriously vulnerable to malicious spoofing attacks, such as replay, synthetic speech, and recently emerged adversarial attacks. Great efforts have been dedicated to…

This paper proposes an automatic speech recognition (ASR) model for hate speech using large language models (LLMs). The proposed method integrates the encoder of the ASR model with the decoder of the LLMs, enabling simultaneous…

While task-agnostic debiasing provides notable generalizability and reduced reliance on downstream data, its impact on language modeling ability and the risk of relearning social biases from downstream task-specific data remain as the two…

Autoregressive language models decode left-to-right with irreversible commitments, limiting revision during multi-step reasoning. We propose \textbf{VDLM}, a modular variable diffusion language model that separates semantic planning from…

In this paper, we consider the problem of domain generalization in semantic segmentation, which aims to learn a robust model using only labeled synthetic (source) data. The model is expected to perform well on unseen real (target) domains.…

Pretraining large language models (LLMs) on vast and heterogeneous datasets is crucial for achieving state-of-the-art performance across diverse downstream tasks. However, current training paradigms treat all samples equally, overlooking…

Vision-language models (VLMs) have significantly advanced autonomous driving (AD) by enhancing reasoning capabilities. However, these models remain highly vulnerable to adversarial attacks. While existing research has primarily focused on…

The wide-ranging applications of large language models (LLMs), especially in safety-critical domains, necessitate the proper evaluation of the LLM's adversarial robustness. This paper proposes an efficient tool to audit the LLM's…

Short text clustering has far-reaching effects on semantic analysis, showing its importance for multiple applications such as corpus summarization and information retrieval. However, it inevitably encounters the severe sparsity of short…

In recent years, Large Language Models (LLM) have emerged as pivotal tools in various applications. However, these models are susceptible to adversarial prompt attacks, where attackers can carefully curate input strings that mislead LLMs…

Recent studies on AI security have highlighted the vulnerability of Vision-Language Pre-training (VLP) models to subtle yet intentionally designed perturbations in images and texts. Investigating multimodal systems' robustness via…

Large language models (LLMs) have significantly benefited from training on diverse, high-quality task-specific data, leading to impressive performance across a range of downstream applications. Current methods often rely on human-annotated…

While Large Language Models (LLMs) have achieved remarkable success in various fields, the efficiency of training and inference remains a major challenge. To address this issue, we propose SUBLLM, short for Subsampling-Upsampling-Bypass…

Over the past two years, the use of large language models (LLMs) has advanced rapidly. While these LLMs offer considerable convenience, they also raise security concerns, as LLMs are vulnerable to adversarial attacks by some well-designed…

Topic models are used to identify and group similar themes in a set of documents. Recent advancements in deep learning based neural topic models has received significant research interest. In this paper, an approach is proposed that further…

Learning transferable data representations from abundant unlabeled data remains a central challenge in machine learning. Although numerous self-supervised learning methods have been proposed to address this challenge, a significant class of…

The prevailing approach to aligning Large Language Models (LLMs) typically relies on human or AI feedback and assumes access to specific types of preference datasets. In our work, we question the efficacy of such datasets and explore…

Large language models (LLMs) possess strong multilingual capabilities, and combining Reinforcement Learning from Human Feedback (RLHF) with translation tasks has shown great potential. However, we observe that this paradigm performs…