Related papers: State-Dependent Safety Failures in Multi-Turn Lang…
Large language models (LLMs) are widely used in real-world applications, raising concerns about their safety and trustworthiness. While red-teaming with jailbreak prompts exposes the vulnerabilities of LLMs, current efforts focus primarily…
Larger language models (LLMs) have taken the world by storm with their massive multi-tasking capabilities simply by optimizing over a next-word prediction objective. With the emergence of their properties and encoded knowledge, the risk of…
Safety alignment in large language models (LLMs) and multimodal large language models (MLLMs) is commonly assumed to operate as a near-binary threshold mechanism. We challenge this assumption by revealing that safety behavior is governed by…
With the wide application of multimodal foundation models in intelligent agent systems, scenarios such as mobile device control, intelligent assistant interaction, and multimodal task execution are gradually relying on such large…
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…
Large language models trained for safety and harmlessness remain susceptible to adversarial misuse, as evidenced by the prevalence of "jailbreak" attacks on early releases of ChatGPT that elicit undesired behavior. Going beyond recognition…
Large language models, LLMs, are increasingly deployed in multiturn settings where earlier responses shape later ones, making reliability dependent on whether a conversation remains consistent over time. When this consistency degrades…
Large Language Models (LLMs) have achieved strong performance on static reasoning benchmarks, yet their effectiveness as interactive agents operating in adversarial, time-sensitive environments remains poorly understood. Existing…
MLLMs are increasingly deployed in multi-turn settings, where attackers can escalate unsafe intent through the evolving visual-text history and exploit long-context safety decay. Yet safety alignment is still dominated by single-turn data…
The inability of Large Language Models (LLMs) to modulate their personality expression in response to evolving dialogue dynamics hinders their performance in complex, interactive contexts. We propose a model-agnostic framework for dynamic…
Large language models (LLMs) excel on static benchmarks, but their performance across multi-turn conversations, which better reflect real-world usage, remains understudied. Addressing this gap is critical in high-stakes settings like…
As large language models (LLMs) constantly evolve, ensuring their safety remains a critical research problem. Previous red-teaming approaches for LLM safety have primarily focused on single prompt attacks or goal hijacking. To the best of…
AI is increasingly being used to assist fraud and cybercrime. However, it is unclear the extent to which current large language models can provide useful information for complex criminal activity. Working with law enforcement and policy…
Despite significant advances in alignment techniques, we demonstrate that state-of-the-art language models remain vulnerable to carefully crafted conversational scenarios that can induce various forms of misalignment without explicit…
While Large Language Model (LLM) capabilities have scaled, safety guardrails remain largely stateless, treating multi-turn dialogues as a series of disconnected events. This lack of temporal awareness facilitates a "Safety Gap" where…
Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…
We present MultiBreak, a scalable and diverse multi-turn jailbreak benchmark to evaluate large language model (LLM) safety. Multi-turn jailbreaks mimic natural conversational settings, making them easier to bypass safety-aligned LLM than…
Conversational large language models are trained to refuse to answer harmful questions. However, emergent jailbreaking techniques can still elicit unsafe outputs, presenting an ongoing challenge for model alignment. To better understand how…
Current jailbreaking work on large language models (LLMs) aims to elicit unsafe outputs from given prompts. However, it only focuses on single-turn jailbreaking targeting one specific query. On the contrary, the advanced LLMs are designed…
Multi-turn interaction in the dialogue system research refers to a system's ability to maintain context across multiple dialogue turns, enabling it to generate coherent and contextually relevant responses. Recent advancements in large…