Related papers: Mitigating Over-Refusal in Aligned Large Language …

As large language models span dense, mixture-of-experts, and state-space architectures and are deployed on heterogeneous accelerators under increasingly diverse multimodal workloads, optimising inference energy has become as critical as…

Despite remarkable progress in autoregressive language models, alternative generative paradigms beyond left-to-right generation are still being actively explored. Discrete diffusion models, with the capacity for parallel generation, have…

Large Language Models (LLMs) are powerful reasoners in natural language, but their actions are typically confined to outputting vocabulary tokens. As a result, interactions with external environments -- such as symbolic operators or…

Recent work on activation and latent steering has demonstrated that modifying internal representations can effectively guide large language models (LLMs) toward improved reasoning and efficiency without additional training. However, most…

In the last decade, the free energy principle (FEP) and active inference (AIF) have achieved many successes connecting conceptual models of learning and cognition to mathematical models of perception and action. This effort is driven by a…

Existing Audio Large Models (ALMs) alignment focuses on clean inputs, neglecting security risks in complex environments. We propose ERIS, a framework transforming real-world interference into a strategically optimized carrier for…

Recent advancements in large language models (LLMs) have accelerated progress toward artificial general intelligence, yet their potential to generate harmful content poses critical safety challenges. Existing alignment methods often…

Large language models (LLMs) increasingly serve as reasoners and automated evaluators, yet they remain susceptible to cognitive biases -- often altering their reasoning when faced with spurious prompt-level cues such as consensus claims or…

We propose a novel approach for training large language models (LLMs) to adhere to objectives defined within a latent embedding space. Our method leverages reinforcement learning (RL), treating a pre-trained LLM as an environment. Our…

Generalizable alignment is a core challenge for deploying Large Language Models (LLMs) safely in real-world NLP applications. Current alignment methods, including Reinforcement Learning from Human Feedback (RLHF), often fail to guarantee…

Safety-aligned language models are trained to refuse harmful requests, yet refusal behavior can be suppressed by steering their internal representations. Existing methods do so by ablating a refusal direction from model activations, aiming…

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…

The deep reinforcement learning-based energy management strategies (EMS) have become a promising solution for hybrid electric vehicles (HEVs). When driving cycles are changed, the neural network will be retrained, which is a time-consuming…

The rapid adoption of Mixture-of-Experts (MoE) architectures marks a major shift in the deployment of Large Language Models (LLMs). MoE LLMs improve scaling efficiency by activating only a small subset of parameters per token, but their…

Large language models (LLMs) trained via KL-regularized reinforcement learning demonstrate strong instruction following, self-correction, and reasoning abilities. Yet their theoretical underpinnings remain limited. We exploit the…

Large language models (LLMs) are prone to hallucination stemming from misaligned self-awareness, particularly when processing queries exceeding their knowledge boundaries. While existing mitigation strategies employ uncertainty estimation…

In LLM-based text-to-SQL systems, unanswerable and underspecified user queries may generate not only incorrect text but also executable programs that yield misleading results or violate safety constraints, posing a major barrier to safe…

Despite extensive efforts in safety alignment, large language models (LLMs) remain vulnerable to jailbreak attacks. Activation steering offers a training-free defense method but relies on fixed steering coefficients, resulting in suboptimal…

Safe reinforcement learning (RL) agents accomplish given tasks while adhering to specific constraints. Employing constraints expressed via easily-understandable human language offers considerable potential for real-world applications due to…

Large language models (LLMs) exhibit reasoning biases, often conflating content plausibility with formal logical validity. This can lead to wrong inferences in critical domains, where plausible arguments are incorrectly deemed logically…