Related papers: Intent Mismatch Causes LLMs to Get Lost in Multi-T…

Language confusion -- where large language models (LLMs) generate unintended languages against the user's need -- remains a critical challenge, especially for English-centric models. We present the first mechanistic interpretability (MI)…

LLMs increasingly excel on AI benchmarks, but doing so does not guarantee validity for downstream tasks. This study contrasts LLM alignment on benchmarks, downstream tasks, and, importantly the intended impact of those tasks. We evaluate…

Current Large Language Models (LLMs) safety approaches focus on explicitly harmful content while overlooking a critical vulnerability: the inability to understand context and recognize user intent. This creates exploitable vulnerabilities…

Large language models (LLMs) show potential as simulators of human behavior, offering a scalable way to study responses to interventions. However, because LLMs are trained largely on observational data, interventions in experiments with…

Language Models (LMs) have achieved impressive performance on various linguistic tasks, but their relationship to human language processing in the brain remains unclear. This paper examines the gaps and overlaps between LMs and the brain at…

Research demonstrates that the proactivity of in-vehicle conversational assistants (IVCAs) can help to reduce distractions and enhance driving safety, better meeting users' cognitive needs. However, existing IVCAs struggle with user intent…

Large Language Models (LLMs) often exhibit a gap between their internal knowledge and their explicit linguistic outputs. In this report, we empirically investigate whether Looped Transformers (LTs)--architectures that increase computational…

Large Language Models (LLMs) have developed rapidly and are widely applied to both general-purpose and professional tasks to assist human users. However, they still struggle to comprehend and respond to the true user needs when intentions…

Persona-driven large language models (LLMs) require consistent behavioral tendencies across interactions to simulate human-like personality traits, such as persistence or reliability. However, current LLMs often lack stable internal…

In high-conflict mixed-traffic scenarios involving human-driven and autonomous vehicles, most existing autonomous driving systems default to overly conservative behaviors, lack proactive interaction, and consequently suffer from limited…

Large language models (LLMs) have showcased remarkable capabilities in conversational AI, enabling open-domain responses in chat-bots, as well as advanced processing of conversations like summarization, intent classification, and insights…

Recent large language models (LLMs) show promise in design tasks, yet a fundamental misalignment persists: design thinking requires iterative intent formulation, while LLMs treat inputs as complete specifications. This challenges design…

The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges. This becomes particularly evident when LLMs inadvertently generate harmful or toxic content,…

Fulfilling user needs through Large Language Model multi-turn, multi-step tool-use is rarely a straightforward process. Real user interactions are inherently wild, being intricate, messy, and flexible. We identify three key challenges from…

Understanding user intents from UI interaction trajectories remains a challenging, yet crucial, frontier in intelligent agent development. While massive, datacenter-based, multi-modal large language models (MLLMs) possess greater capacity…

Large language models (LLMs) enable conversational agents (CAs) to express distinctive personalities, raising new questions about how such designs shape user perceptions. This study investigates how personality expression levels and…

Large Language Models (LLMs) in multi-turn conversations often suffer from a ``lost-in-conversation'' phenomenon, where they struggle to recover from early incorrect assumptions, particularly when users provide ambiguous initial…

Today's large language models (LLMs) are trained to align with user preferences through methods such as reinforcement learning. Yet models are beginning to be deployed not merely to satisfy users, but also to generate revenue for the…

Humans often interact with large language models (LLMs) in multi-turn interaction to obtain desired answers or more information. However, most existing studies overlook the multi-turn instruction following ability of LLMs, in terms of…

Turn-taking is a fundamental mechanism in human communication that ensures smooth and coherent verbal interactions. Recent advances in Large Language Models (LLMs) have motivated their use in improving the turn-taking capabilities of Spoken…