Related papers: Measuring Safety Alignment Effects in Autonomous S…

This paper investigates the impact of model compression on the way Large Language Models (LLMs) process prompts, particularly concerning jailbreak resistance. We show that moderate WANDA pruning can enhance resistance to jailbreaking…

In perpetrator treatment, a recurring observation is the dissociation between insight and action: offenders articulate remorse yet behavioral change does not follow. We report four preregistered studies (1,584 multi-agent simulations across…

Aggregate metacognitive quality scores mask within-model variation across MMLU benchmark domains. We administered 1,500 MMLU items (250 per domain, under an a priori six-domain grouping) to 33 frontier LLMs from eight model families and…

Current safety evaluations of large language models rely on single-shot testing, implicitly assuming that model responses are deterministic and representative of the model's safety alignment. We challenge this assumption by investigating…

As large language models (LLMs) become increasingly capable, it is prudent to assess whether safety measures remain effective even if LLMs intentionally try to bypass them. Previous work introduced control evaluations, an adversarial…

Multi-agent systems extend large language models (LLMs) by decomposing tasks among specialized agents, but their distributed decision process creates new attack surfaces. We identify semantic hijacking, an attack in which harmful requests…

Given a black-box AI system and a task, at what confidence level can a practitioner trust the system's output? We answer with a reliability level -- a single number per system-task pair, derived from self-consistency sampling and conformal…

Multi-agent systems achieve state-of-the-art outcomes through peer collaboration. However, when an agent in the pipeline silently drops a constraint, the system's final output may look correct even though the reasoning chain was quietly…

The safety alignment of current Large Language Models (LLMs) is vulnerable. Relatively simple attacks, or even benign fine-tuning, can jailbreak aligned models. We argue that many of these vulnerabilities are related to a shared underlying…

Large Language Models (LLMs) demonstrate complex responses to threat-based manipulations, revealing both vulnerabilities and unexpected performance enhancement opportunities. This study presents a comprehensive analysis of 3,390…

The rapid evolution of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) has driven major gains in reasoning, perception, and generation across language and vision, yet whether these advances translate into…

A small but growing body of work has shown that machine learning models which better align with human vision have also exhibited higher robustness to adversarial examples, raising the question: can human-like perception make models more…

We audit alignment-induced shifts in residual-stream activations of three open-weight instruction-tuned LLMs (Llama-3.1-8B-Instruct, Gemma-2-9B-it, Qwen-2.5-7B-Instruct) using the effective rank of the alignment modification matrix on…

As the development of large language models (LLMs) rapidly advances, securing these models effectively without compromising their utility has become a pivotal area of research. However, current defense strategies against jailbreak attacks…

Financial institutions deploy Large Language Models (LLMs) for reconciliations, regulatory reporting, and client communications, but nondeterministic outputs (output drift) undermine auditability and trust. We quantify drift across five…

LLMs can estimate Hospital Anxiety and Depression Scale (HADS) scores from speech in a zero-shot manner, but clinical deployment requires reliability across three dimensions: intra-model consistency, ASR robustness, and evidence…

Safety post-training can improve the harmfulness and policy compliance of Large Language Models (LLMs), but it may also reduce general utility, a phenomenon often described as the \emph{alignment tax}. We study this trade-off through the…

Aligned large language models (LLMs) demonstrate exceptional capabilities in task-solving, following instructions, and ensuring safety. However, the continual learning aspect of these aligned LLMs has been largely overlooked. Existing…

When Large Language Models (LLMs) are deployed in Chinese-language settings, a troubling pattern emerges: safety systems that work well in English break down. These systems struggle to cross linguistic and cultural bound-aries, leaving…

Large language model (LLM) safety classifiers such as Llama Guard are effective at detecting overtly harmful prompts but remain vulnerable to adversarial jailbreak attacks that disguise malicious intent through role-play scenarios,…