Related papers: State-Dependent Safety Failures in Multi-Turn Lang…

As an essential component in task-oriented dialogue systems, dialogue state tracking (DST) aims to track human-machine interactions and generate state representations for managing the dialogue. Representations of dialogue states are…

Multimodal large language models (MLLMs) have achieved remarkable progress, yet remain critically vulnerable to adversarial attacks that exploit weaknesses in cross-modal processing. We present a systematic study of multimodal jailbreaks…

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to adversarial manipulations such as jailbreaking via prompt injection attacks. These attacks bypass safety mechanisms…

Large language models are increasingly used for mental health support, yet their conversational coherence alone does not ensure clinical appropriateness. Existing general-purpose safeguards often fail to distinguish between therapeutic…

Large language models are being deployed as mental health support agents at scale, yet only 16% of LLM-based chatbot interventions have undergone rigorous clinical efficacy testing, and simulations reveal psychological deterioration in over…

Ensuring the safety of Large Language Models (LLMs) is critical for real-world deployment. However, current safety measures often fail to address implicit, domain-specific risks. To investigate this gap, we introduce a dataset of 3,000…

Although there have been remarkable advances in dialogue systems through the dialogue systems technology competition (DSTC), it remains one of the key challenges to building a robust task-oriented dialogue system with a speech interface.…

Recent large language model (LLM) defenses have greatly improved models' ability to refuse harmful queries, even when adversarially attacked. However, LLM defenses are primarily evaluated against automated adversarial attacks in a single…

Large language models (LLMs) are increasingly deployed in a wide range of applications, yet remain vulnerable to adversarial jailbreak attacks that circumvent their safety guardrails. Existing evaluation frameworks typically report binary…

Large Language Models (LLMs) are increasingly popular, powering a wide range of applications. Their widespread use has sparked concerns, especially through jailbreak attacks that bypass safety measures to produce harmful content. In this…

Large language models (LLMs) have demonstrated remarkable performance in zero-shot dialogue state tracking (DST), reducing the need for task-specific training. However, conventional DST benchmarks primarily focus on structured user-agent…

Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond healthcare, software engineering, and conversational systems.…

Despite the growing use of large language models (LLMs) in clinical dialogue systems, existing evaluations focus on task completion or fluency, offering little insight into the behavioral and risk management requirements essential for…

Session types provide a typing discipline for message-passing systems. However, their theory often assumes an ideal world: one in which everything is reliable and without failures. Yet this is in stark contrast with distributed systems in…

Recent LLMs increasingly integrate reasoning mechanisms like Chain-of-Thought (CoT). However, this explicit reasoning exposes a new attack surface for inference-time backdoors, which inject malicious reasoning paths without altering model…

We present a scalable methodology for evaluating language models in multi-turn interactions, using a suite of collaborative games that require effective communication about private information. This enables an interactive scaling analysis,…

As Large Language Models transition to autonomous agents, user inputs frequently violate cooperative assumptions (e.g., implicit intent, missing parameters, false presuppositions, or ambiguous expressions), creating execution risks that…

Large Language Models (LLMs) trained for average correctness often exhibit mode collapse, producing narrow decision behaviors on tasks where multiple responses may be reasonable. This limitation is particularly problematic in ordinal…

This paper introduces FRACTURED-SORRY-Bench, a framework for evaluating the safety of Large Language Models (LLMs) against multi-turn conversational attacks. Building upon the SORRY-Bench dataset, we propose a simple yet effective method…

Aligned large language models (LLMs) remain vulnerable to jailbreak attacks. Recent mechanistic studies have identified latent features and representation shifts associated with jailbreak success, but they leave a more fundamental question…