Search

Search Results

• Debate Helps Weak-to-Strong Generalization

  Hao Lang, Fei Huang, Yongbin Li

  27410-27418

  2025-04-11

• JailPO: A Novel Black-Box Jailbreak Framework via Preference Optimization Against Aligned LLMs

  Hongyi Li, Jiawei Ye, Jie Wu, Tianjie Yan, Chu Wang, Zhixin Li

  27419-27427

  2025-04-11

• Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update

  Qing Li, Jiahui Geng, Derui Zhu, Zongxiong Chen, Kun Song, Lei Ma, Fakhri Karray

  27428-27436

  2025-04-11

• Strong Empowered and Aligned Weak Mastered Annotation for Weak-to-Strong Generalization

  Yongqi Li, Xin Miao, Mayi Xu, Tieyun Qian

  27437-27445

  2025-04-11

• Retention Score: Quantifying Jailbreak Risks for Vision Language Models

  Zaitang LI, Pin-Yu Chen, Tsung-Yi Ho

  27446-27454

  2025-04-11

• Exploring Intrinsic Alignments Within Text Corpus

  Zi Liang, Pinghui Wang, Ruofei Zhang, Haibo Hu, Shuo Zhang, Qingqing Ye, Nuo Xu, Yaxin Xiao, Chen Zhang, Lizhen Cui

  27455-27463

  2025-04-11

• Is Your Autonomous Vehicle Safe? Understanding the Threat of Electromagnetic Signal Injection Attacks on Traffic Scene Perception

  Wenhao Liao, Sineng Yan, Youqian Zhang, Xinwei Zhai, Yuanyuan Wang, Eugene Fu

  27464-27472

  2025-04-11

• Single Character Perturbations Break LLM Alignment

  Leon Lin, Hannah Brown, Kenji Kawaguchi, Michael Shieh

  27473-27481

  2025-04-11

• Data with High and Consistent Preference Difference Are Better for Reward Model

  Qi Lin, Hengtong Lu, Caixia Yuan, Xiaojie Wang, Huixing Jiang, Wei Chen

  27482-27490

  2025-04-11

• Bias Unveiled: Investigating Social Bias in LLM-Generated Code

  Lin Ling, Fazle Rabbi, Song Wang, Jinqiu Yang

  27491-27499

  2025-04-11

• Stream Aligner: Efficient Sentence-Level Alignment via Distribution Induction

  Hantao Lou, Jiaming Ji, Kaile Wang, Yaodong Yang

  27500-27508

  2025-04-11

• Sequential Preference Optimization: Multi-Dimensional Preference Alignment with Implicit Reward Modeling

  Xingzhou Lou, Junge Zhang, Jian Xie, Lifeng Liu, Dong Yan, Kaiqi Huang

  27509-27517

  2025-04-11

• MAPLE: A Framework for Active Preference Learning Guided by Large Language Models

  Saaduddin Mahmud, Mason Nakamura, Shlomo Zilberstein

  27518-27528

  2025-04-11

• SYNAPSE: SYmbolic Neural-Aided Preference Synthesis Engine

  Sadanand Modak, Noah Tobias Patton, Isil Dillig, Joydeep Biswas

  27529-27537

  2025-04-11

• Neural Continuous-Time Supermartingale Certificates

  Grigory Neustroev, Mirco Giacobbe, Anna Lukina

  27538-27546

  2025-04-11

• Text-Diffusion Red-Teaming of Large Language Models: Unveiling Harmful Behaviors with Proximity Constraints

  Jonathan Nöther, Adish Singla, Goran Radanovic

  27547-27555

  2025-04-11

• Is Poisoning a Real Threat to DPO? Maybe More So Than You Think

  Pankayaraj Pathmanathan, Souradip Chakraborty, Xiangyu Liu, Yongyuan Liang, Furong Huang

  27556-27564

  2025-04-11

• Do Transformer Interpretability Methods Transfer to RNNs?

  Gonçalo Paulo, Thomas Marshall, Nora Belrose

  27565-27572

  2025-04-11

• Multi-Agent Security Tax: Trading Off Security and Collaboration Capabilities in Multi-Agent Systems

  Pierre Peigné, Mikolaj Kniejski, Filip Sondej, Matthieu David, Jason Hoelscher-Obermaier, Christian Schroeder de Witt, Esben Kran

  27573-27581

  2025-04-11

• Increased Compute Efficiency and the Diffusion of AI Capabilities

  Konstantin F. Pilz, Lennart Heim, Nicholas Brown

  27582-27590

  2025-04-11

• Neurons to Words: A Novel Method for Automated Neural Network Interpretability and Alignment

  Lukas-Santo Puglisi, Fabio Valdés, Jakob Johannes Metzger

  27591-27598

  2025-04-11

• SEAL: Systematic Error Analysis for Value ALignment

  Manon Revel, Matteo Cargnelutti, Tyna Eloundou, Greg Leppert

  27599-27607

  2025-04-11

• ME: Modelling Ethical Values for Value Alignment

  Eryn Rigley, Adriane Chapman, Christine Evers, Will McNeill

  27608-27616

  2025-04-11

• SafetyPrompts: A Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety

  Paul Röttger, Fabio Pernisi, Bertie Vidgen, Dirk Hovy

  27617-27627

  2025-04-11

• Reinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion Filters

  Soumyendu Sarkar, Ashwin Ramesh Babu, Sajad Mousavi, Vineet Gundecha, Sahand Ghorbanpour, Avisek Naug, Ricardo Luna Gutiérrez, Antonio Guillen, Desik Rengarajan

  27628-27635

  2025-04-11