相关论文: FaithSteer-BENCH: A Deployment-Aligned Stress-Test…

Multimodal large language models (MLLMs) enable interaction over both text and images, but their safety behavior can be driven by unimodal shortcuts instead of true joint intent understanding. We introduce CSR-Bench, a benchmark for…

In recent years, the remarkable progress of large language models (LLMs) has sparked interest in task automation, which involves decomposing complex tasks described by user instructions into sub-tasks and invoking external tools to execute…

Large language models (LLMs) are shown to be vulnerable to jailbreaking attacks where adversarial prompts are designed to elicit harmful responses. While existing defenses effectively mitigate single-turn attacks by detecting and filtering…

We examine two properties of AI systems: capability (what a system can do) and steerability (how reliably one can shift behavior toward intended outcomes). A central question is whether capability growth reduces steerability and risks…

Activation steering has emerged as a powerful tool to shape LLM behavior without the need for weight updates. While its inherent brittleness and unreliability are well-documented, its safety implications remain underexplored. In this work,…

Model steering represents a powerful technique that dynamically aligns large language models (LLMs) with human preferences during inference. However, conventional model-steering methods rely heavily on externally annotated data, not only…

Tool-using LLM agents increasingly rely on external tools to make consequential decisions, yet most existing agent-security benchmarks and defenses implicitly assume that tool feedback is trustworthy once a tool has been selected. We study…

Harness engineering has emerged as an important inference-time technique for large language model (LLM) agents, aiming to improve long-term performance through task decomposition and guided execution. However, more elaborate harnesses are…

With the advancement of automated software engineering, research focus is increasingly shifting toward practical tasks reflecting the day-to-day work of software engineers. Among these tasks, software migration, a critical process of…

A popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations. Namely, identify a well-chosen direction depending on the task at hand and perturbs representations along…

LLM-based financial agents increasingly produce investment rationales before the outcomes needed to evaluate them are observable. This creates a delayed-ground-truth evaluation problem: realized returns remain the eventual arbiter of…

Leaderboard scores on public benchmarks have been steadily rising and converging, with many frontier language models now separated by only marginal differences. However, these scores often fail to match users' day to day experience, because…

Large language models (LLMs) power many state-of-the-art systems in natural language processing. However, these models are extremely computationally expensive, even at inference time, raising the natural question: when is the extra cost of…

Despite the fact that large language models (LLMs) show exceptional skill in instruction following tasks, this strength can turn into a vulnerability when the models are required to disregard certain instructions. Instruction-following…

LLM-based agents are increasingly used to simulate deliberative interactions such as negotiation, conflict resolution, and multi-turn opinion exchange. Yet generated transcripts often do not reveal why an agent's stance changes: movement…

Recent advances in large language models have enabled LLM-based agents to achieve strong performance on a variety of benchmarks. However, their performance in real-world deployments often that observed on benchmark settings, especially in…

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…

Despite strong medical benchmark accuracy, LLMs can exhibit severe multi-turn sycophancy in clinical dialogue, abandoning initial correct diagnosis under escalating pressure. We propose \textbf{\textsc{Med-Stress}}, a targeted stress test…

This paper studies whether multimodal large language models (LLMs) can serve as inspectable spatial proposal modules for stress-aware topology optimization. IterSIMP-{\sigma} keeps the SIMP optimizer as a compliance-minimizing…

Reflection, the ability of large language models (LLMs) to evaluate and revise their own reasoning, has been widely used to improve performance on complex reasoning tasks. Yet, most prior works emphasizes designing reflective prompting…