相关论文: Controllable Safety Alignment: Inference-Time Adap…

Current large language models (LLMs) generally show a significant performance gap in alignment between English and other languages. To bridge this gap, existing research typically leverages the model's responses in English as a reference to…

Large Language Models (LLMs) have shown remarkable success in various tasks, yet their safety and the risk of generating harmful content remain pressing concerns. In this paper, we delve into the potential of In-Context Learning (ICL) to…

Recent progress in large language models (LLMs) has focused on producing responses that meet human expectations and align with shared values - a process coined alignment. However, aligning LLMs remains challenging due to the inherent…

Over the last year, significant advancements have been made in the realms of large language models (LLMs) and multi-modal large language models (MLLMs), particularly in their application to autonomous driving. These models have showcased…

We introduce time-to-unsafe-sampling, a novel safety measure for generative models, defined as the number of generations required by a large language model (LLM) to trigger an unsafe (e.g., toxic) response. While providing a new dimension…

Integrating cognitive ergonomics with LLMs is crucial for improving safety, reliability, and user satisfaction in human-AI interactions. Current LLM designs often lack this integration, resulting in systems that may not fully align with…

Safety alignment in large language models (LLMs) is achieved through fine-tuning mechanisms that regulate neuron activations to suppress harmful content. In this work, we propose a novel approach to induce disalignment by identifying and…

We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant…

Multimodal Large Language Models (MLLMs) pose critical safety challenges, as they are susceptible not only to adversarial attacks such as jailbreaking but also to inadvertently generating harmful content for benign users. While internal…

While recent code-specific large language models (LLMs) have greatly enhanced their code generation capabilities, the safety of these models remains under-explored, posing potential risks as insecure code generated by these models may…

As large language models (LLMs) are increasingly deployed in real-world applications, ensuring the safety of their outputs during decoding has become a critical challenge. However, existing decoding-time interventions, such as Contrastive…

Large Language Models (LLMs) exhibit significant safety disparities across languages, with low-resource languages (LRLs) often bypassing safety guardrails established for high-resource languages (HRLs) like English. Existing solutions, such…

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 high-stakes scenarios-such as self-harm, legal, or medical queries-LLMs must be both trustworthy and helpful. However, these goals often conflict. We propose priority alignment, a new alignment paradigm that enforces a strict…

Current LLM-based conversational recommender systems (CRS) primarily optimize recommendation accuracy and user satisfaction. We identify an underexplored vulnerability in which recommendation outputs may negatively impact users by violating…

While Large Language Models (LLMs) and Vision-Language Models (VLMs) demonstrate remarkable capabilities in high-level reasoning and semantic understanding, applying them directly to contact-rich manipulation remains a challenge due to…

Aligning large language models (LLMs) to diverse human preferences is fundamentally challenging since criteria can often conflict with each other. Inference-time alignment methods have recently gained popularity as they allow LLMs to be…

Large Language Models (LLMs) need to be aligned with human expectations to ensure their safety and utility in most applications. Alignment is challenging, costly, and needs to be repeated for every LLM and alignment criterion. We propose to…

Large language models (LLMs) are increasingly being used as decision aids. However, users have diverse values and preferences that can affect their decision-making, which requires novel methods for LLM alignment and personalization.…

Large vision-language models (LVLMs) are vulnerable to harmful input compared to their language-only backbones. We investigated this vulnerability by exploring LVLMs internal dynamics, framing their inherent safety understanding in terms of…