Cover Image

ALERT: Zero-shot LLM Jailbreak Detection via Internal Discrepancy Amplification

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Xiao, Li, Philip, Zeng, Zhichen, Li, Tingwei, Wei, Tianxin, Ning, Xuying, Li, Gaotang, Chen, Yuzhong, Tong, Hanghang
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Information Retrieval
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FeDecider: An LLM-Based Framework for Federated Cross-Domain Recommendation
by: He, Xinrui, et al.
Published: (2026)

i$^2$VAE: Interest Information Augmentation with Variational Regularizers for Cross-Domain Sequential Recommendation
by: Ning, Xuying, et al.
Published: (2024)

Taming Knowledge Conflicts in Language Models
by: Li, Gaotang, et al.
Published: (2025)

PaperMind: Benchmarking Agentic Reasoning and Critique over Scientific Papers in Multimodal LLMs
by: Zhao, Yanjun, et al.
Published: (2026)

CATS: Mitigating Correlation Shift for Multivariate Time Series Classification
by: Lin, Xiao, et al.
Published: (2025)

THeGCN: Temporal Heterophilic Graph Convolutional Network
by: Yan, Yuchen, et al.
Published: (2024)

Harnessing Consistency for Robust Test-Time LLM Ensemble
by: Zeng, Zhichen, et al.
Published: (2025)

Mixture of Sequence: Theme-Aware Mixture-of-Experts for Long-Sequence Recommendation
by: Lin, Xiao, et al.
Published: (2026)

A Zero-shot Explainable Doctor Ranking Framework with Large Language Models
by: Zeng, Ziyang, et al.
Published: (2025)

Saffron-1: Safety Inference Scaling
by: Qiu, Ruizhong, et al.
Published: (2025)

Hierarchical LoRA MoE for Efficient CTR Model Scaling
by: Zeng, Zhichen, et al.
Published: (2025)

RALLM-POI: Retrieval-Augmented LLM for Zero-shot Next POI Recommendation with Geographical Reranking
by: Li, Kunrong, et al.
Published: (2025)

CoFiRec: Coarse-to-Fine Tokenization for Generative Recommendation
by: Wei, Tianxin, et al.
Published: (2025)

Continual Low-Rank Adapters for LLM-based Generative Recommender Systems
by: Yoo, Hyunsik, et al.
Published: (2025)

RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
by: Li, Shijun, et al.
Published: (2026)

An Investigation of Prompt Variations for Zero-shot LLM-based Rankers
by: Sun, Shuoqi, et al.
Published: (2024)

Zero-shot Cross-domain Knowledge Distillation: A Case study on YouTube Music
by: Ranganathan, Srivaths, et al.
Published: (2026)

Unleashing the Power of Large Language Models in Zero-shot Relation Extraction via Self-Prompting
by: Liu, Siyi, et al.
Published: (2024)

Synergistic Integration and Discrepancy Resolution of Contextualized Knowledge for Personalized Recommendation
by: Mu, Lingyu, et al.
Published: (2025)

Ensuring User-side Fairness in Dynamic Recommender Systems
by: Yoo, Hyunsik, et al.
Published: (2023)

Beyond Reproducibility: Advancing Zero-shot LLM Reranking Efficiency with Setwise Insertion
by: Podolak, Jakub, et al.
Published: (2025)

Internalizing Multi-Agent Reasoning for Accurate and Efficient LLM-based Recommendation
by: Wu, Yang, et al.
Published: (2026)

Modality and Task Adaptation for Enhanced Zero-shot Composed Image Retrieval
by: Li, Haiwen, et al.
Published: (2024)

Continual Recommender Systems
by: Yoo, Hyunsik, et al.
Published: (2025)

Graph Homophily Booster: Rethinking the Role of Discrete Features on Heterophilic Graphs
by: Qiu, Ruizhong, et al.
Published: (2025)

Graph homophily booster: Reimagining the role of discrete features in heterophilic graph learning
by: Qiu, Ruizhong, et al.
Published: (2026)

Enhancing Complex Question Answering over Knowledge Graphs through Evidence Pattern Retrieval
by: Ding, Wentao, et al.
Published: (2024)

InRanker: Distilled Rankers for Zero-shot Information Retrieval
by: Laitz, Thiago, et al.
Published: (2024)

Flow Matching Meets Biology and Life Science: A Survey
by: Li, Zihao, et al.
Published: (2025)

Subspace Alignment for Vision-Language Model Test-time Adaptation
by: Zeng, Zhichen, et al.
Published: (2026)

Decoding Matters: Addressing Amplification Bias and Homogeneity Issue for LLM-based Recommendation
by: Bao, Keqin, et al.
Published: (2024)

iAgent: LLM Agent as a Shield between User and Recommender Systems
by: Xu, Wujiang, et al.
Published: (2025)

Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals
by: Zeng, Linda, et al.
Published: (2025)

A Collaborative Ensemble Framework for CTR Prediction
by: Liu, Xiaolong, et al.
Published: (2024)

ListT5: Listwise Reranking with Fusion-in-Decoder Improves Zero-shot Retrieval
by: Yoon, Soyoung, et al.
Published: (2024)

Bias Amplification Enhances Minority Group Performance
by: Li, Gaotang, et al.
Published: (2023)

Retrieval-Augmented Purifier for Robust LLM-Empowered Recommendation
by: Ning, Liangbo, et al.
Published: (2025)

Fishing for Answers: Exploring One-shot vs. Iterative Retrieval Strategies for Retrieval Augmented Generation
by: Lin, Huifeng, et al.
Published: (2025)

A Pre-trained Sequential Recommendation Framework: Popularity Dynamics for Zero-shot Transfer
by: Wang, Junting, et al.
Published: (2024)

Soft Filtering: Guiding Zero-shot Composed Image Retrieval with Prescriptive and Proscriptive Constraints
by: Jung, Youjin, et al.
Published: (2025)