Related papers: Adversarial Representation Engineering: A General …

Pre-trained large language models (LLMs) exhibit powerful capabilities for generating natural text. Evolutionary algorithms (EAs) can discover diverse solutions to complex real-world problems. Motivated by the common collective and…

Aligning Large Language Models (LLMs) is crucial for enhancing their safety and utility. However, existing methods, primarily based on preference datasets, face challenges such as noisy labels, high annotation costs, and privacy concerns.…

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…

Intervention is one of the most representative and widely used methods for understanding the internal representations of large language models (LLMs). However, existing intervention methods are confined to linear interventions grounded in…

Representation Misdirection for Unlearning (RMU), which steers model representation in the intermediate layer to a target random representation, is an effective method for large language model (LLM) unlearning. Despite its high performance,…

This study investigates the capabilities of Large Language Models (LLMs), specifically GPT-4, in the context of Binary Reverse Engineering (RE). Employing a structured experimental approach, we analyzed the LLM's performance in interpreting…

Argument mining (AM) is the process of automatically extracting arguments, their components and/or relations amongst arguments and components from text. As the number of platforms supporting online debate increases, the need for AM becomes…

Recent years have seen important advances in the building of interpretable models, machine learning models that are designed to be easily understood by humans. In this work, we show that large language models (LLMs) are remarkably good at…

In this paper we proposed a novel Adversarial Training (AT) approach for end-to-end speech recognition using a Criticizing Language Model (CLM). In this way the CLM and the automatic speech recognition (ASR) model can challenge and learn…

The increasing use of Large Language Models (LLMs) offers significant opportunities across the engineering lifecycle, including requirements engineering, software development, process optimization, and decision support. Despite this…

Software development has entered a new era where large language models (LLMs) now serve as general-purpose reasoning engines, enabling natural language interaction and transformative applications across diverse domains. This paradigm is now…

Simulations, although powerful in accurately replicating real-world systems, often remain inaccessible to non-technical users due to their complexity. Conversely, large language models (LLMs) provide intuitive, language-based interactions…

This research develops advanced methodologies for Large Language Models (LLMs) to better manage linguistic behaviors related to emotions and ethics. We introduce DIKE, an adversarial framework that enhances the LLMs' ability to internalize…

Machine unlearning aims to remove unwanted information from a model, but many methods are inefficient for LLMs with large numbers of parameters or fail to fully remove the intended information without degrading performance on knowledge that…

The current landscape of defensive mechanisms for LLMs is fragmented and underdeveloped, unlike prior work on classifiers. To further promote adversarial robustness in LLMs, we propose Inverse Language Modeling (ILM), a unified framework…

Reinforcement learning (RL) has become a pivotal component of large language model (LLM) post-training, and agentic RL extends this paradigm to operate as agents through multi-turn interaction and tool use. Scaling such systems exposes two…

Adversarial Machine Learning (AML) addresses vulnerabilities in AI systems where adversaries manipulate inputs or training data to degrade performance. This article provides a comprehensive analysis of evasion and poisoning attacks,…

This paper investigates how Large Language Models (LLMs) represent non-English tokens -- a question that remains underexplored despite recent progress. We propose a lightweight intervention method using representation steering, where a…

In this paper, we identify and characterize the emerging area of representation engineering (RepE), an approach to enhancing the transparency of AI systems that draws on insights from cognitive neuroscience. RepE places population-level…

Using AI to create autonomous researchers has the potential to accelerate scientific discovery. A prerequisite for this vision is understanding how well an AI model can identify the underlying structure of a black-box system from its…