arXiv subjects

Zihao Xue

Publications and source records attributed to Zihao Xue.

5 recordsLinked to original sources

arXiv2026

ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails

Reasoning-based LLM guardrails improve safety moderation by generating explicit rationales before issuing final decisions. However, their rationales do not always lead to faithful enforcement: a model may recognize a harmful intent in its reasoning but still predict a safe label, or issue an unsafe decision without policy-grounded justification. We identify this safety-critical failure mode as the deliberation-to-enforcement gap. Unlike general chain-of-thought faithfulness, guardrail reliability requires policy execution consistency: the generated reasoning should be grounded in the safety policy, and the final decision should be entailed by that reasoning. We propose ConsisGuard, a consistency-aware framework for reasoning-based LLM guardrails. ConsisGuard performs Policy-to-Decision Trajectory Distillation and Functional Coupling Alignment, aligning the internal coupling between safety deliberation and decision enforcement. Experiments on prompt and response harmfulness detection benchmarks show that ConsisGuard improves detection performance while reducing policy execution failures. These results suggest that reliable reasoning-based guardrails require accurate faithful execution of safety policies.

cs.CL↗

arXiv2026

Make LLM Learn to Synthesize from Streaming Experiences through Feedback

Large language models (LLMs) have been widely adopted for synthetic data generation, significantly reducing annotation costs. However, most existing studies treat synthesis as a set of isolated tasks and overlook a more fundamental question: whether a model can learn to synthesize by accumulating experience from past tasks and transferring it to future ones. In this work, we introduce StreamSynth, a new setting in which synthesis tasks arrive sequentially and experience from historical tasks provides informative signals for future synthesis. To address this setting, we propose SynLearner, a general framework that enables synthesis models to acquire reusable synthesis experience over a task stream. Instead of generating data independently for each task, SynLearner encourages the model to explore diverse synthesis patterns, learn from feedback, and balance sample quality with set-level diversity as tasks evolve. Extensive experiments across multiple benchmarks show that SynLearner effectively leverages experience from earlier tasks to improve synthesis performance on later ones, exhibiting consistent cross-task transferability. These findings provide evidence for the feasibility of StreamSynth and highlight synthetic data generation as an experience-driven process that can benefit from task streams.

cs.AI↗

arXiv2026

Robust and Generalizable Safety Steering for Text-to-Image Diffusion Transformers

Diffusion Transformers have become a powerful backbone for text-to-image generation, but their layered and cross-modal generation process makes safety control fundamentally different from prompt-level filtering or output-level detection. Harmful semantics may be weakly expressed in text representations, progressively bound to visual latents, and finally entangled with rendering dynamics. As a result, safety steering at a fixed layer can be unstable, and a steering mechanism learned from known risks may not transfer reliably to a shifted target risk domain. We propose SafeDIG, a safety steering framework that formulates DiT safety adaptation as position-aware sparse feature transfer. SafeDIG first constructs Sparse Autoencoders over functionally distinct DiT intervention positions and uses robustness-aware pre-training routing to prioritize intervention sites that are expected to remain stable under source-target risk shift. It then separates transferable safety features from domain-specific activation geometry by freezing the SAE encoder as a reusable sparse safety dictionary and adapting only the decoder to the target-domain activation manifold. During inference, SafeDIG combines Blend and Repel operations to steer unsafe activations toward transferred safety manifolds or away from harmful sparse directions. Experiments on FLUX.1 Dev and Stable Diffusion 3.5 Large show that SafeDIG consistently reduces target-domain and overall unsafe generation rates while preserving source-domain safety and image quality.

cs.AI↗

arXiv2026

Your One-Stop Solution for AI-Generated Video Detection

Recent advances in generative modeling can create remarkably realistic synthetic videos, making it increasingly difficult for humans to distinguish them from real ones and necessitating reliable detection methods. However, two key limitations hinder the development of this field. \textbf{From the dataset perspective}, existing datasets are often limited in scale and constructed using outdated or narrowly scoped generative models, making it difficult to capture the diversity and rapid evolution of modern generative techniques. Moreover, the dataset construction process frequently prioritizes quantity over quality, neglecting essential aspects such as semantic diversity, scenario coverage, and technological representativeness. \textbf{From the benchmark perspective}, current benchmarks largely remain at the stage of dataset creation, leaving many fundamental issues and in-depth analysis yet to be systematically explored. Addressing this gap, we propose AIGVDBench, a benchmark designed to be comprehensive and representative, covering \textbf{31} state-of-the-art generation models and over \textbf{440,000} videos. By executing more than \textbf{1,500} evaluations on \textbf{33} existing detectors belonging to four distinct categories. This work presents \textbf{8 in-depth analyses} from multiple perspectives and identifies \textbf{4 novel findings} that offer valuable insights for future research. We hope this work provides a solid foundation for advancing the field of AI-generated video detection. Our benchmark is open-sourced at https://github.com/LongMa-2025/AIGVDBench.

cs.CV↗

arXiv2025

Thought Purity: A Defense Framework For Chain-of-Thought Attack

Large Reasoning Models (LRMs) leverage Chain-of-Thought (CoT) reasoning to solve complex tasks, but this explicit reasoning process introduces a critical vulnerability: adversarial manipulation of the thought chain itself, known as Chain-of-Thought Attacks (CoTA). Such attacks subtly corrupt the reasoning path to produce erroneous outputs, challenging conventional defenses that often sacrifice model utility for safety. To address this, we propose Thought Purity(TP), a defense framework that shifts from passive refusal to active reasoning recovery. TP integrates a safety-aware data pipeline with reinforcement learning, employing a dual-reward mechanism to teach models to dynamically identify and isolate malicious logic while preserving correct reasoning. Experiments on multiple model families demonstrate that TP significantly reduces the attack success rate of CoTA while maintaining or enhancing the model's performance on benign tasks.

cs.LG↗