Related papers: AttnDiff: Attention-based Differential Fingerprint…

Large language models (LLMs) excel at natural language understanding and generation but remain vulnerable to factual errors, limiting their reliability in knowledge-intensive tasks. While decoding-time strategies provide a promising…

The growing complexity of network traffic and demand for ultra-low latency communication require smarter packet traffic management. Existing Deep Learning-based queuing approaches struggle with dynamic network scenarios and demand high…

Large language models (LLMs) achieve strong performance across many natural language processing tasks, yet their decision processes remain difficult to interpret. This lack of transparency creates challenges for trust, debugging, and…

Despite the rapid evolution of training paradigms, the decoder backbone of large vision--language models (LVLMs) remains fundamentally rooted in the residual-connection Transformer architecture. Therefore, deciphering the distinct roles of…

Software-Defined Networking (SDN) improves network flexibility but also increases the need for reliable and interpretable intrusion detection. Large Language Models (LLMs) have recently been explored for cybersecurity tasks due to their…

Out-of-distribution (OOD) detection plays a vital role in enhancing the reliability of machine learning (ML) models. The emergence of large language models (LLMs) has catalyzed a paradigm shift within the ML community, showcasing their…

In recent years, Large Language Models (LLMs) have demonstrated remarkable abilities in various natural language processing tasks. However, adapting these models to specialized domains using private datasets stored on resource-constrained…

In this paper, we initiate our discussion by demonstrating how Large Language Models (LLMs), when tasked with responding to queries, display a more even probability distribution in their answers if they are more adept, as opposed to their…

Large language model (LLM) hallucinations, meaning fluent but factually incorrect generations, fall into two types: faithfulness violations, where the model misuses provided context, and factuality violations, where answers reflect errors…

Multilingual Large Language Models (LLMs) often exhibit hallucinations such as unintended code-switching, reducing reliability in downstream tasks. We propose latent-space language steering, a lightweight inference-time method that…

Protecting the intellectual property of Large Language Models (LLMs) has become increasingly critical due to the high cost of training. Model merging, which integrates multiple expert models into a single multi-task model, introduces a…

Recently, Large Language Models (LLMs) have garnered significant attention for their exceptional natural language processing capabilities. However, concerns about their trustworthiness remain unresolved, particularly in addressing…

Large Language Models (LLMs) face threats from jailbreak prompts. Existing methods for defending against jailbreak attacks are primarily based on auxiliary models. These strategies, however, often require extensive data collection or…

Personalizing large language models (LLMs) to individual users requires incorporating extensive interaction histories and profiles, but input token constraints make this impractical due to high inference latency and API costs. Existing…

Automatic detection of hate and abusive language is essential to combat its online spread. Moreover, recognising and explaining hate speech serves to educate people about its negative effects. However, most current detection models operate…

We have uncovered a powerful jailbreak technique that leverages large language models' ability to diverge from prior context, enabling them to bypass safety constraints and generate harmful outputs. By simply instructing the LLM to deviate…

The pretraining and fine-tuning approach has become the leading technique for various NLP applications. However, recent studies reveal that fine-tuning data, due to their sensitive nature, domain-specific characteristics, and…

Protecting the copyright of large language models (LLMs) has become crucial due to their resource-intensive training and accompanying carefully designed licenses. However, identifying the original base model of an LLM is challenging due to…

Vocabulary-free fine-grained image recognition aims to distinguish visually similar categories within a meta-class without a fixed, human-defined label set. Existing solutions for this problem are limited by either the usage of a large and…

The advent of Large Language Models (LLMs) has revolutionized text generation, producing outputs that closely mimic human writing. This blurring of lines between machine- and human-written text presents new challenges in distinguishing one…