Cover Image

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Junxiao, Liu, Haoran, Tu, Jinzhe, Cheng, Jiale, Zhang, Zhexin, Cui, Shiyao, Weng, Jiaqi, Tao, Jialing, Xue, Hui, Wang, Hongning, Qiu, Han, Huang, Minlie
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Agent-SafetyBench: Evaluating the Safety of LLM Agents
by: Zhang, Zhexin, et al.
Published: (2024)

Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints
by: Yang, Junxiao, et al.
Published: (2025)

Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!
by: Zhang, Zhexin, et al.
Published: (2025)

SMSP: A Plug-and-Play Strategy of Multi-Scale Perception for MLLMs to Perceive Visual Illusions
by: Tu, Jinzhe, et al.
Published: (2026)

BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
by: Yang, Junxiao, et al.
Published: (2025)

LongSafety: Evaluating Long-Context Safety of Large Language Models
by: Lu, Yida, et al.
Published: (2025)

From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks
by: Zhang, Zhexin, et al.
Published: (2024)

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity
by: Cui, Shiyao, et al.
Published: (2025)

The Missing Half: Unveiling Training-time Implicit Safety Risks Beyond Deployment
by: Zhang, Zhexin, et al.
Published: (2026)

Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
by: Zhang, Zhexin, et al.
Published: (2023)

How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study
by: Zhang, Zhexin, et al.
Published: (2025)

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs
by: Cui, Shiyao, et al.
Published: (2025)

A Single Neuron Works: Precise Concept Erasure in Text-to-Image Diffusion Models
by: He, Qinqin, et al.
Published: (2025)

AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement
by: Zhang, Zhexin, et al.
Published: (2025)

JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering
by: Chen, Renmiao, et al.
Published: (2025)

Learning to Detect Unseen Jailbreak Attacks in Large Vision-Language Models
by: Liang, Shuang, et al.
Published: (2025)

Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval
by: Xiao, Jian, et al.
Published: (2025)

LLM-Agnostic Semantic Representation Attack
by: Lian, Jiawei, et al.
Published: (2026)

Task-Agnostic Semantic Communications Relying on Information Bottleneck and Federated Meta-Learning
by: Wei, Hao, et al.
Published: (2025)

ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors
by: Zhang, Zhexin, et al.
Published: (2024)

Task-Agnostic Learnable Weighted-Knowledge Base Scheme for Robust Semantic Communications
by: Jiang, Shiyao, et al.
Published: (2025)

Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training
by: Weng, Fenghua, et al.
Published: (2025)

Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework
by: Weng, Jiaqi, et al.
Published: (2025)

Seeker: Towards Exception Safety Code Generation with Intermediate Language Agents Framework
by: Zhang, Xuanming, et al.
Published: (2024)

Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning Models
by: Wang, Shuqiang, et al.
Published: (2026)

Towards Efficient Exact Optimization of Language Model Alignment
by: Ji, Haozhe, et al.
Published: (2024)

Black-Box Prompt Optimization: Aligning Large Language Models without Model Training
by: Cheng, Jiale, et al.
Published: (2023)

Language Model Decoding as Direct Metrics Optimization
by: Ji, Haozhe, et al.
Published: (2023)

The Side Effects of Being Smart: Safety Risks in MLLMs' Multi-Image Reasoning
by: Chen, Renmiao, et al.
Published: (2026)

The Superalignment of Superhuman Intelligence with Large Language Models
by: Huang, Minlie, et al.
Published: (2024)

SafetyBench: Evaluating the Safety of Large Language Models
by: Zhang, Zhexin, et al.
Published: (2023)

Video Anomaly Detection with Semantics-Aware Information Bottleneck
by: Li, Juntong, et al.
Published: (2025)

ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
by: Hu, Xiwei, et al.
Published: (2024)

LASA: Enhancing SoC Security Verification with LLM-Aided Property Generation
by: Ankireddy, Dinesh Reddy, et al.
Published: (2025)

Survive at All Costs: Exploring LLM's Risky Behaviors under Survival Pressure
by: Lu, Yida, et al.
Published: (2026)

AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models
by: Cheng, Jiale, et al.
Published: (2024)

LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Models
by: Gui, Jiayi, et al.
Published: (2024)

CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation
by: Ke, Pei, et al.
Published: (2023)

Steins;Gate Drive: Semantic Safety Arbitration over Structured Futures for Latency-Decoupled LLM Planning
by: Qiu, Anjie, et al.
Published: (2026)

AlignBench: Benchmarking Chinese Alignment of Large Language Models
by: Liu, Xiao, et al.
Published: (2023)