相关论文: Towards Interactive Deepfake Analysis

In the swiftly expanding domain of Natural Language Processing (NLP), the potential of GPT-based models for the financial sector is increasingly evident. However, the integration of these models with financial datasets presents challenges,…

The increasing realism and accessibility of deepfakes have raised critical concerns about media authenticity and information integrity. Despite recent advances, deepfake detection models often struggle to generalize beyond their training…

Instruction tuning large language models (LLMs) using machine-generated instruction-following data has improved zero-shot capabilities on new tasks, but the idea is less explored in the multimodal field. In this paper, we present the first…

Deepfake detection automatically recognizes the manipulated medias through the analysis of the difference between manipulated and non-altered videos. It is natural to ask which are the top performers among the existing deepfake detection…

Large language models (LLMs) often hallucinate, yet most existing fact-checking methods treat factuality evaluation as a binary classification problem, offering limited interpretability and failing to capture fine-grained error types. In…

Deep generative models can create remarkably photorealistic fake images while raising concerns about misinformation and copyright infringement, known as deepfake threats. Deepfake detection technique is developed to distinguish between real…

Advancements in Large Language Models (LLMs) have significantly enhanced instruction-following capabilities. However, most Instruction Fine-Tuning (IFT) datasets are predominantly in English, limiting model performance in other languages.…

Prior research shows that large language models (LLMs) exhibit systematic extrapolation bias when forming predictions from both experimental and real-world data, and that prompt-based approaches appear limited in alleviating this bias. We…

Instruction tuning is a pivotal technique for aligning large language models (LLMs) with human intentions, safety constraints, and domain-specific requirements. This survey provides a comprehensive overview of the full pipeline,…

Multimodal deepfake detection (MDD) aims to uncover manipulations across visual, textual, and auditory modalities, thereby reinforcing the reliability of modern information systems. Although large vision-language models (LVLMs) exhibit…

There have been emerging a number of benchmarks and techniques for the detection of deepfakes. However, very few works study the detection of incrementally appearing deepfakes in the real-world scenarios. To simulate the wild scenes, this…

Deep learning-based vulnerability detection has shown great performance and, in some studies, outperformed static analysis tools. However, the highest-performing approaches use token-based transformer models, which are not the most…

While multimodal fusion has been extensively studied in Multimodal Sentiment Analysis (MSA), the role of fusion depth and multimodal capacity allocation remains underexplored. In this work, we position fusion depth, scalability, and…

Instruction Fine-Tuning (IFT) is a powerful paradigm that strengthens the zero-shot capabilities of Large Language Models (LLMs), but in doing so induces new evaluation metric requirements. We show LLM-based metrics to be well adapted to…

The proliferation of deepfake faces poses huge potential negative impacts on our daily lives. Despite substantial advancements in deepfake detection over these years, the generalizability of existing methods against forgeries from unseen…

The remarkable advancements in Multimodal Large Language Models (MLLMs) have not rendered them immune to challenges, particularly in the context of handling deceptive information in prompts, thus producing hallucinated responses under such…

Previous studies in deepfake detection have shown promising results when testing face forgeries from the same dataset as the training. However, the problem remains challenging when one tries to generalize the detector to forgeries from…

Understanding the behavior of large language models (LLMs) is crucial for ensuring their safe and reliable use. However, existing explainable AI (XAI) methods for LLMs primarily rely on word-level explanations, which are often…

Emerging multimodal large language models (MLLMs) exhibit great potential for chart question answering (CQA). Recent efforts primarily focus on scaling up training datasets (i.e., charts, data tables, and question-answer (QA) pairs) through…

Instruction tuning is essential for large language models (LLMs) to become interactive. While many instruction tuning datasets exist in English, there is a noticeable lack in other languages. Also, their effectiveness has not been well…