相关论文: Detecting and Steering LLMs' Empathy in Action

Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but…

Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making contexts. While prior work has shown that LLMs exhibit cognitive biases behaviorally, whether these biases correspond to identifiable internal…

Personality imbuing customizes LLM behavior, but safety evaluations almost always study prompt-based personas alone. We show this is incomplete: prompting and activation steering expose *different*, architecture-dependent vulnerability…

State-of-the-art reasoning LLMs are powerful problem solvers, but they still occasionally make mistakes. However, adopting AI models in risk-sensitive domains often requires error rates near 0%. To address this gap, we propose collaboration…

Prior behavioural work suggests that some LLMs alter choices when options are framed as causing pain or pleasure, and that such deviations can scale with stated intensity. To bridge behavioural evidence (what the model does) with…

Empathy is critical for effective and satisfactory conversational communication. Prior efforts to measure conversational empathy mostly focus on expressed communicative intents -- that is, the way empathy is expressed. Yet, these works…

Complex social behaviors, such as empathy and strategic politeness, are widely assumed to resist the directional decomposition that makes activation steering effective for coarse attributes like sentiment or toxicity. We present STAR:…

Steering vectors have emerged as a lightweight and effective approach for aligning large language models (LLMs) at inference time, enabling modulation over model behaviors by shifting LLM representations towards a target behavior. However,…

Background: Systems of systems are becoming increasingly dynamic and heterogeneous, and this adds pressure on the long-standing challenge of interoperability. Besides its technical aspect, interoperability has also an economic side, as…

Activation steering is a promising technique for controlling LLM behavior by adding semantically meaningful vectors directly into a model's hidden states during inference. It is often framed as a precise, interpretable, and potentially…

LLM agents are emerging as a key enabler for autonomous wireless network management. Reliably deploying them, however, demands benchmarks that reflect real engineering risk. Existing wireless benchmarks evaluate single isolated capabilities…

Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept -- a phenomenon termed "introspective awareness." We investigate the mechanisms underlying…

Steering, or direct manipulation of internal activations to guide LLM responses toward specific semantic concepts, is emerging as a promising avenue for both understanding how semantic concepts are stored within LLMs and advancing LLM…

Robots operating in shared workspaces must maintain safe coordination with other agents whose behavior may change during task execution. When a collaborating agent switches strategy mid-episode, continuing under outdated assumptions can…

Large Language Models (LLMs) are widely used by students, yet their tendency to provide fast and complete answers may discourage reflection and foster overconfidence. We examined how alternative LLM interaction designs support deeper…

Safety benchmarks are routinely treated as evidence about how a language model will behave once deployed, but this inference is fragile if behavior depends on whether a prompt looks like an evaluation. We define evaluation-context…

We present ReflexGrad, a dual-process architecture for within-episode failure recovery in LLM agents without demonstrations. When agents commit to a wrong approach early and exhaust the step budget, the post-failure trajectory contains the…

Exploration and goal-directed navigation in unknown layouts are central to inspection, logistics, and search-and-rescue. We ask whether large language models (LLMs) can function as \emph{text-only} controllers under partial observability --…

Can linearly decodable failure signals in LLM hidden states be leveraged to correct those failures? We investigate this classification-correction gap via Overthinking (OT)--a stable behavioral regime (Jaccard >= 0.81, 94% inter-annotator…

Detecting sandbagging--the deliberate underperformance on capability evaluations--is an open problem in AI safety. We tested whether symptom validity testing (SVT) logic from clinical malingering detection could identify sandbagging through…