With the rapid advancement of large language models (LLMs), the safety of LLMs has become a critical concern. Despite significant efforts in safety alignment, current LLMs remain vulnerable to jailbreaking attacks. However, the root causes of such vulnerabilities are still poorly understood, necessitating a rigorous investigation into jailbreak mechanisms across both academic and industrial communities. In this work, we focus on a continuation-triggered jailbreak phenomenon, whereby simply relocating a continuation-triggered instruction suffix can substantially increase jailbreak success rates. To uncover the intrinsic mechanisms of this phenomenon, we conduct a comprehensive mechanistic interpretability analysis at the level of attention heads. Through causal interventions and activation scaling, we show that this jailbreak behavior primarily arises from an inherent competition between the model’s intrinsic continuation drive and the safety defenses acquired through alignment training. Furthermore, we perform a detailed behavioral analysis of the identified safety-critical attention heads, revealing notable differences in the behaviors of safety heads across different model architectures. Grounded in these mechanistic findings, we propose Head Competition Steering (HCS), a mechanistically grounded inference-time strategy that explicitly leverages the competition between safety heads and continuation heads to suppress harmful generation, and further distill its behavioral signal into a student model via knowledge distillation, achieving inference-time safety improvements without additional computational overhead.

Large language models are commonly adapted to downstream tasks through supervised fine-tuning (SFT), but substantial distribution mismatch between downstream supervision and a model’s generation distribution can intensify catastrophic forgetting. Data rewriting offers a data-centric way to narrow this mismatch before SFT. Existing methods, however, typically sample rewrites from a prompt-induced conditional distribution, which need not align with the backbone’s natural question-answering generation distribution, and fixed templates can reduce output diversity. We formulate data rewriting as a policy-learning problem and train a lightweight LoRA rewriting policy with reinforcement learning. The policy optimizes question-answering-style distributional alignment and semantic diversity under a hard task-consistency gate, producing verified supervision for downstream SFT. Across three instruction-tuned backbones, the resulting models attain downstream gains broadly comparable to standard SFT while reducing degradation on non-downstream benchmarks in every evaluated setting. Additional experiments on logical reasoning and medical question answering provide preliminary evidence that a rewriting policy can be reused across domains for the same backbone.

Recent advancements in Spatial Intelligence (SI) have predominantly relied on Vision-Language Models (VLMs), yet a critical question remains: does spatial understanding originate from visual encoders or the fundamental reasoning backbone? Inspired by this question, we introduce SiT-Bench, a novel benchmark designed to evaluate the SI performance of Large Language Models (LLMs) without pixel-level input, comprises over 3,800 expert-annotated items across five primary categories and 17 subtasks, ranging from egocentric navigation and perspective transformation to fine-grained robotic manipulation. By converting single/multi-view scenes into high-fidelity, coordinate-aware textual descriptions, we challenge LLMs to perform symbolic textual reasoning rather than visual pattern matching. Evaluation results of state-of-the-art (SOTA) LLMs reveals that while models achieve proficiency in localized semantic tasks, a significant “spatial gap” remains in global consistency. Notably, we find that explicit spatial reasoning significantly boosts performance, suggesting that LLMs possess latent world-modeling potential. Our proposed dataset SiT-Bench serves as a foundational resource to foster the development of spatially-grounded LLM backbones for future VLMs and embodied agents.

Despite the remarkable performance across numerous tasks, Large Language Models (LLMs) still exhibit notable deficiencies in temporal reasoning, even in simple event ordering tasks. For instance, a slight alteration in the temporal phrasing of the question (e.g., changing "Is event A before B?” to “Is event A after B?”) can lead LLMs to hallucinate and produce inconsistent answers, reflecting a lack of robust temporal reasoning. Although many prior studies have focused on benchmarking and improving the temporal reasoning ability of LLMs, little is known about the intrinsic mechanisms within LLMs when performing temporal reasoning. In this work, we investigate the mechanistic interpretability of temporal ordering within event temporal reasoning through a structured "Identify-Interpret-Verify” pipeline. We first employ path patching to identify a sparse subset of attention heads that are causally responsible for reasoning outcomes. Detailed pattern analysis reveals that these key heads specialize in attending to either temporal keywords (semantic cues) or structural delimiters (syntactic cues). Furthermore, we rigorously validate the observed mechanism through comprehensive intervention-based experiments, ranging from head ablation to targeted attention modulation. We demonstrate that dynamically modulating the attention of these specific heads can robustly enhance model performance, which serves as strong empirical evidence that our identified mechanism faithfully captures the internal logic of temporal ordering in LLMs.

Over the past year, spatial intelligence has drawn increasing attention. Many prior works study it from the perspective of visual-spatial intelligence, where models have access to visuospatial information from visual inputs. However, in the absence of visual information, whether linguistic intelligence alone is sufficient to endow models with spatial intelligence, and how models perform relevant tasks with text-only inputs still remain unexplored. Therefore, in this paper, we focus on a fundamental and critical capability in spatial intelligence from a linguistic perspective: viewpoint rotation understanding (VRU). Specifically, LLMs and VLMs are asked to infer their final viewpoint and predict the corresponding observation in an environment given textual description of viewpoint rotation and observation over multiple steps. We find that both LLMs and VLMs perform poorly on our proposed dataset while human can easily achieve 100% accuracy, indicating a substantial gap between current model capabilities and the requirements of spatial intelligence. To uncover the underlying mechanisms, we conduct a layer-wise probing analysis and head-wise causal intervention. Our findings reveal that although models encode viewpoint information in the hidden states, they appear to struggle to bind the viewpoint position with corresponding observation, resulting in a hallucination in final layers. Finally, we selectively fine-tune the key attention heads identified by causal intervention to improve VRU performance. Experimental results demonstrate that such selective fine-tuning achieves improved VRU performance while avoiding catastrophic forgetting of generic abilities.

“Chinese Frame Semantic Parsing (CFSP) is an important task in the field of Chinese Natural Language Processing(NLP). Its goal is to extract the frame semantic structure from the sentence and realize the deep understanding of the events or situations involved in the sentence. This paper mainly studies the application of Large Language Model (LLM) for reasoning through Prompt Engineering without fine-tuning the model, and completes three subtasks of Chinese Framework Semantic Parsing tasks: frame identification, argument Identification and role identification. This paper proposes a Retrieval Augmented Generation (RAG) method for target words, and constructs more refined sample Few-Shot method. We achieved the second place on the B rankings in the open track in the “CCL2024-Eval The Second Chinese Frame Semantic Parsing”competition*.”