Related papers: JAMDEC: Unsupervised Authorship Obfuscation using …

The recent (2019-02) demonstration of the power of huge language models such as GPT-2 to memorise the answers to factoid questions raises questions about the extent to which knowledge is being embedded directly within these large models.…

The widespread deployment of large language models (LLMs) has intensified concerns around intellectual property (IP) protection, as model theft and unauthorized redistribution become increasingly feasible. To address this, model…

Large language models (LLMs) have opened up enormous opportunities while simultaneously posing ethical dilemmas. One of the major concerns is their ability to create text that closely mimics human writing, which can lead to potential…

The rising cost of acquiring supervised data has driven significant interest in self-improvement for large language models (LLMs). Straightforward unsupervised signals like majority voting have proven effective in generating pseudo-labels…

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…

Large vision-language models (LVLMs) excel at multimodal tasks but are prone to misinterpreting visual inputs, often resulting in hallucinations and unreliable outputs. We present DROPOUT DECODING, a novel inference-time approach that…

Deobfuscating binary code remains a fundamental challenge in reverse engineering, as obfuscation is widely used to hinder analysis and conceal program logic. Although large language models (LLMs) have shown promise in recovering semantics…

In recent times, large language models (LLMs) have shown impressive performance on various document-level tasks such as document classification, summarization, and question-answering. However, research on understanding their capabilities on…

The rapid development of large language models (LLMs) has significantly improved the generation of fluent and convincing text, raising concerns about their potential misuse on social media platforms. We present a comprehensive methodology…

As Large Language Models (LLMs) become increasingly sophisticated, they raise significant security concerns, including the creation of fake news and academic misuse. Most detectors for identifying model-generated text are limited by their…

This paper presents epistemic blinding in the context of an agentic system that uses large language models to reason across multiple biological datasets for drug target prioritization. During development, it became apparent that LLM outputs…

Text sanitization aims to rewrite parts of a document to prevent disclosure of personal information. The central challenge of text sanitization is to strike a balance between privacy protection (avoiding the leakage of personal information)…

Large Language Models (LLMs) have demonstrated advanced capabilities in both text generation and comprehension, and their application to data archives might facilitate the privatization of sensitive information about the data subjects. In…

Recent advances in large language and vision-language models have enabled zero-shot inference, allowing models to solve new tasks without task-specific training. Various adaptation techniques such as prompt engineering, In-Context Learning…

Large Language Models (LLMs) are currently used extensively to generate code by professionals and students, motivating the development of tools to detect LLM-generated code for applications such as academic integrity and cybersecurity. We…

Despite recent advances in natural language generation, it remains challenging to control attributes of generated text. We propose DExperts: Decoding-time Experts, a decoding-time method for controlled text generation that combines a…

With the advent of Web 2.0, the development in social technology coupled with global communication systematically brought positive and negative impacts to society. Copyright claims and Author identification are deemed crucial as there has…

Understanding code represents a core ability needed for automating software development tasks. While foundation models like LLMs show impressive results across many software engineering challenges, the extent of their true semantic…

While large code language models have made significant strides in AI-assisted coding tasks, there are growing concerns about privacy challenges. The user code is transparent to the cloud LLM service provider, inducing risks of unauthorized…

Large language models (LLMs) can generate fluent text, but their ability to replicate the distinctive style of a specific human author remains unclear. We present a fast, training-free framework for authorship verification and style…