Related papers: RADAR: Retrieval-Augmented Detector with Adversari…
The proliferation of misinformation in the digital age has led to significant societal challenges. Existing approaches often struggle with capturing long-range dependencies, complex semantic relations, and the social dynamics influencing…
This paper presents RADAR, a tracking algorithm for vehicles participating in Cooperative Intelligent Transportation Systems (C-ITS) that exploits multiple radio signals emitted by a modern vehicle to break privacy-preserving pseudonym…
Recent strides in large language models (LLMs) have yielded remarkable performance, leveraging reinforcement learning from human feedback (RLHF) to significantly enhance generation and alignment capabilities. However, RLHF encounters…
Hallucination remains a critical bottleneck for large language models (LLMs), undermining their reliability in real-world applications, especially in Retrieval-Augmented Generation (RAG) systems. While existing hallucination detection…
The widespread adoption of large language models (LLMs) has created an urgent need for robust tools to detect LLM-generated text, especially in light of \textit{paraphrasing} techniques that often evade existing detection methods. To…
The peer review process is fundamental to scientific progress, determining which papers meet the quality standards for publication. Yet, the rapid growth of scholarly production and increasing specialization in knowledge areas strain…
Retrieval-Augmented Generation (RAG) can alleviate hallucinations of Large Language Models (LLMs) by referencing external documents. However, the misinformation in external documents may mislead LLMs' generation. To address this issue, we…
Retrieval-Augmented Generation (RAG) has become ubiquitous when deploying Large Language Models (LLMs), as it can address typical limitations such as generating hallucinated or outdated information. However, when building real-world RAG…
Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm to enhance large language models (LLMs) by conditioning generation on external evidence retrieved at inference time. While RAG addresses critical limitations of…
Retrieval-augmented language models have exhibited promising performance across various areas of natural language processing (NLP), including fact-critical tasks. However, due to the black-box nature of advanced large language models (LLMs)…
The proliferation of fake news has emerged as a severe societal problem, raising significant interest from industry and academia. While existing deep-learning based methods have made progress in detecting fake news accurately, their…
Large Vision-Language Models (LVLMs) can be vulnerable to adversarial images that subtly bias their outputs toward plausible yet incorrect responses. We introduce a general, efficient, and training-free defense that combines image…
Autoregressive decoding in Large Language Models (LLMs) generates one token per step, causing high inference latency. Speculative decoding (SD) mitigates this through a guess-and-verify strategy, but existing training-free variants face…
Reinforcement Learning with Human Feedback (RLHF) has been demonstrated to significantly enhance the performance of large language models (LLMs) by aligning their outputs with desired human values through instruction tuning. However, RLHF…
The combination of deep unfolding with vector approximate message passing (VAMP) algorithm, results in faster convergence and higher sparse recovery accuracy than traditional compressive sensing approaches. However, deep unfolding alters…
Large language model (LLM) agents are increasingly employing retrieval-augmented generation (RAG) to improve the factuality of their responses. However, in practice, these systems often need to handle ambiguous user queries and potentially…
Retrieval-Augmented Generation (RAG) improves reliability of large language models by incorporating external knowledge, but the retrieval process can introduce bias that propagates to generated outputs. This issue is particularly…
Large language models (LLMs) have shown remarkable capabilities in various natural language processing tasks, yet they often struggle with maintaining factual accuracy, particularly in knowledge-intensive domains like healthcare. This study…
Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adversarial attacks is to…
The existing fake audio detection systems often rely on expert experience to design the acoustic features or manually design the hyperparameters of the network structure. However, artificial adjustment of the parameters can have a…