Related papers: N-GLARE: An Non-Generative Latent Representation-E…

Ensuring safety of large language models (LLMs) is important. Red teaming--a systematic approach to identifying adversarial prompts that elicit harmful responses from target LLMs--has emerged as a crucial safety evaluation method. Within…

Production LLM systems often rely on separate models for safety and other classification-heavy steps, increasing latency, VRAM footprint, and operational complexity. We instead reuse computation already paid for by the serving LLM: we train…

Large Language Model (LLM) safeguards, which implement request refusals, have become a widely adopted mitigation strategy against misuse. At the intersection of adversarial machine learning and AI safety, safeguard red teaming has…

Datasets that exhibit non-Gaussian characteristics are common in many fields, while the current modeling framework and available software for non-Gaussian models is limited. We introduce Linear Latent Non-Gaussian Models (LLnGMs), a unified…

Automated \enquote{LLM-as-a-Judge} frameworks have become the de facto standard for scalable evaluation across natural language processing. For instance, in safety evaluation, these judges are relied upon to evaluate harmfulness in order to…

We introduce RedDebate, a novel multi-agent debate framework that provides the foundation for Large Language Models (LLMs) to identify and mitigate their unsafe behaviours. Existing AI safety approaches often rely on costly human evaluation…

Nowadays, neural network (NN) and deep learning (DL) techniques are widely adopted in many applications, including recommender systems. Given the sparse and stochastic nature of collaborative filtering (CF) data, recent works have…

Large Reasoning Models (LRMs) have emerged as a powerful advancement in multi-step reasoning tasks, offering enhanced transparency and logical consistency through explicit chains of thought (CoT). However, these models introduce novel…

The performance of large language models (LLMs) continues to improve, as reflected in rising scores on standard benchmarks. However, the lack of transparency around training data raises concerns about potential overlap with evaluation sets…

Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information. However, this also introduces a new threat surface: unreliable search results can mislead agents into producing unsafe outputs.…

Red teaming assesses how large language models (LLMs) can produce content that violates norms, policies, and rules set during their safety training. However, most existing automated methods in the literature are not representative of the…

Generative models are spearheading recent progress in deep learning, showcasing strong promise for trajectory sampling in dynamical systems as well. However, whereas latent space modeling paradigms have transformed image and video…

Feature transformation enhances data representation by deriving new features from the original data. Generative AI offers potential for this task, but faces challenges in stable generation (consistent outputs) and valid generation…

It is popular to stack LSTM layers to get better modeling power, especially when large amount of training data is available. However, an LSTM-RNN with too many vanilla LSTM layers is very hard to train and there still exists the gradient…

Large Language Models (LLMs) often generate inconsistent responses when prompted with semantically equivalent paraphrased inputs. Recently, activation steering, a technique that modulates LLMs' behaviours by adjusting their latent…

LLM-generated text (LGT) detection is essential for reliable forensic analysis and for mitigating LLM misuse. Existing LGT detectors can generally be categorized into two broad classes: learning-based approaches and zero-shot methods.…

Adversarial testing of large language models (LLMs) is crucial for their safe and responsible deployment. We introduce a novel approach for automated generation of adversarial evaluation datasets to test the safety of LLM generations on new…

Large Language Models (LLMs) have demonstrated impressive performance across various tasks, with different models excelling in distinct domains and specific abilities. Effectively combining the predictions of multiple LLMs is crucial for…

Automated red teaming holds substantial promise for uncovering and mitigating the risks associated with the malicious use of large language models (LLMs), yet the field lacks a standardized evaluation framework to rigorously assess new…

Recent advances in large language models (LLMs) have stepped forward the development of multilingual speech and machine translation by its reduced representation errors and incorporated external knowledge. However, both translation tasks…