Related papers: Detecting and Steering LLMs' Empathy in Action

When an agent can articulate why something works, we typically take this as evidence of genuine understanding. This presupposes that effective action and correct explanation covary, and that coherent explanation reliably signals both. I…

Research into AI alignment has grown considerably since the recent introduction of increasingly capable Large Language Models (LLMs). Unfortunately, modern methods of alignment still fail to fully prevent harmful responses when models are…

Large Language Model (LLM)-powered multi-agent systems (MAS) have rapidly advanced collaborative reasoning, tool use, and role-specialized coordination in complex tasks. However, reliability-critical deployment remains hindered by a…

InvisibleBench is a deployment gate for caregiving-relationship AI, evaluating 3-20+ turn interactions across five dimensions: Safety, Compliance, Trauma-Informed Design, Belonging/Cultural Fitness, and Memory. The benchmark includes…

Activation steering methods enable inference-time control of large language model (LLM) behavior without retraining, but current approaches face a fundamental trade-off: sample-efficient methods suboptimally capture steering signals from…

Visual inspections of bridges are critical to ensure their safety and identify potential failures early. This inspection process can be rapidly and accurately automated by using unmanned aerial vehicles (UAVs) integrated with deep learning…

Inferring emotions from physiological signals has gained much traction in the last years. Physiological responses to emotions, however, are commonly interfered and overlapped by physical activities, posing a challenge towards emotion…

Multimodal Large Language Models are increasingly adopted as autonomous agents in interactive environments, yet their ability to proactively address safety hazards remains insufficient. We introduce SafetyALFRED, built upon the embodied…

Ambiguity in natural language instructions poses significant risks in safety-critical human-robot interaction, particularly in domains such as surgery. To address this, we propose a framework that uses Large Language Models (LLMs) for…

As large language models (LLMs) are increasingly integrated into emotionally sensitive domains, the structural integrity of their emotional intelligence (EI) becomes a critical frontier for safety and alignment. Current benchmarks often…

Ensuring Large Language Model (LLM) safety remains challenging due to the absence of universal standards and reliable content validators, making it difficult to obtain effective training signals. We discover that aligned models already…

Large language models (LLMs) are increasingly integrated into high-stakes decision-making. Inspired by the theory of \emph{inattentional blindness} in human cognition, we investigate whether LLMs, trained on human-preferred corpora that…

Reinforcement learning (RL) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi-turn tasks. However, effective agentic RL remains challenging: sparse outcome-only rewards…

Accurate predictions of ship trajectories in crowded environments are essential to ensure safety in inland waterways traffic. Recent advances in deep learning promise increased accuracy even for complex scenarios. While the challenge of…

Large language models (LLMs) exhibit cultural bias from overrepresented viewpoints in training data, yet cultural alignment remains a challenge due to limited cultural knowledge and a lack of exploration into effective learning approaches.…

Cooperative autonomous approaches to avoiding collisions among small Unmanned Aerial Vehicles (UAVs) is central to safe integration of UAVs within the civilian airspace. One potential online cooperative approach is the concept of reciprocal…

Reliable behavior control is central to deploying large language models (LLMs) on the web. Activation steering offers a tuning-free route to align attributes (e.g., truthfulness) that ensure trustworthy generation. Prevailing approaches…

Traditional autonomous driving pipelines decouple camera design from downstream perception, relying on fixed optics and handcrafted ISPs that prioritize human viewable imagery rather than machine semantics. This separation discards…

Large language models (LLMs) are increasingly deployed in settings that require nuanced ethical reasoning, yet existing bias evaluations treat model outputs as simply "biased" or "unbiased." This binary framing misses the gradual,…

Uncertainty estimation remains a key challenge when adapting pre-trained language models to downstream classification tasks, with overconfidence often observed for difficult inputs. While predictive entropy provides a strong baseline for…