相关论文: CRaFT: Circuit-Guided Refusal Feature Selection vi…

Language models are commonly fine-tuned for safety alignment to refuse harmful prompts. One approach fine-tunes them to generate categorical refusal tokens that distinguish different refusal types before responding. In this work, we…

Adapting to latent confounded shift remains a core challenge in modern AI. This setting is driven by hidden variables that induce spurious correlations between inputs and outputs during training, leading models to rely on non-causal…

A physics-informed machine learning framework based on holomorphic neural networks is introduced for detecting cracks in two-dimensional solids from strain or displacement data. Crack detection is formulated as an inverse problem in which…

Current LLM safety research predominantly focuses on mitigating Goal Hijacking, preventing attackers from redirecting a model's high-level objective (e.g., from "summarizing emails" to "phishing users"). In this paper, we argue that this…

Decision Transformers (DT) play a crucial role in modern reinforcement learning, leveraging offline datasets to achieve impressive results across various domains. However, DT requires high-quality, comprehensive data to perform optimally.…

Evaluation and alignment pipelines for large language models increasingly rely on LLM-based judges, whose behavior is guided by natural-language rubrics and validated on benchmarks. We identify a previously under-recognized vulnerability in…

Single-turn safety evaluation is a poor proxy for real fraud defense, where attackers escalate across multiple rounds. This paper evaluates fraud defenders under replay and adaptive multi-round attacks and measures when a defender refuses,…

In this work, we propose BAIT (Boundary-Aware Iterative Trap), a three-step jailbreak framework that approaches malicious goals through internal disclosure. BAIT first asks the model to identify the protection boundary, then requires it to…

Causal chain reasoning (CCR) is an essential ability for many decision-making AI systems, which requires the model to build reliable causal chains by connecting causal pairs. However, CCR suffers from two main transitive problems: threshold…

Since the advent of autonomous driving technology, it has experienced remarkable progress over the last decade. However, most existing research still struggles to address the challenges posed by environments where multiple vehicles have to…

Motivation: Sparse autoencoders (SAEs) decompose foundation model activations into interpretable features, but causal feature-to-feature interactions across network depth remain unknown for biological foundation models. Results: We…

Large language models (LLMs) are typically aligned to refuse harmful instructions through safety fine-tuning. A recent attack, termed abliteration, identifies and suppresses the single latent direction most responsible for refusal behavior,…

Role-playing systems powered by large language models (LLMs) have become increasingly influential in emotional communication applications. However, these systems are susceptible to character hallucinations, where the model deviates from…

Large Vision-Language Models (LVLMs) demonstrate exceptional performance across multimodal tasks, yet remain vulnerable to jailbreak attacks that bypass built-in safety mechanisms to elicit restricted content generation. Existing black-box…

This paper proposes a simple yet effective jailbreak attack named FlipAttack against black-box LLMs. First, from the autoregressive nature, we reveal that LLMs tend to understand the text from left to right and find that they struggle to…

In many domains of empirical sciences, discovering the causal structure within variables remains an indispensable task. Recently, to tackle with unoriented edges or latent assumptions violation suffered by conventional methods, researchers…

In healthcare tabular predictions, classical models with feature engineering often outperform neural approaches. Recent advances in Large Language Models enable the integration of domain knowledge into feature engineering, offering a…

Current LLMs are trained to refuse potentially harmful input queries regardless of whether users actually had harmful intents, causing a tradeoff between safety and user experience. Through a study of 480 participants evaluating 3,840…

Large Language Models (LLMs) face severe safety risks from jailbreak attacks, yet current safety testing largely relies on static datasets and lacks systematic criteria to evaluate test suite quality and adequacy. While coverage criteria…

Large Reasoning Models (LRMs) achieve strong reasoning performance by generating long chains of thought (CoTs), yet only a small fraction of these traces meaningfully contributes to answer prediction, while the majority contains repetitive…