Instant research discovery
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
PreviousNext
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| The Profit Alignment Problem: How Profit Mandates Induce Alignment Failures in LLMs Eric So Published: 2026-09-07Area: cs.AICitations: 12 Tags: ai-safety, alignment-training, csai, preprint | 2026-09-07 | cs.AI | ai-safety, alignment-training, csai, preprint | E18 / R8 (95%) | 12 |
| VoT: Vision-of-Thought for Unified Multimodal Representation Alignment Ceyuan Yang, Chao Liao, Chaorui Deng, Chen-lin Zhang Published: 2026-09-07Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-09-07 | cs.CV | ai-safety, alignment-training, cscv, preprint | E8 / R7 (89%) | - |
| We're Cooked! - Probing LLM Political Alignment Via Conflict-Framed Recipe Translation Angelica Henestrosa, Ivan P. Yamshchikov, Svetlana Gorovaia Published: 2026-09-07Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-09-07 | cs.CL | ai-safety, alignment-training, cscl, preprint | E12 / R8 (95%) | - |
| Inducing Emergent Misalignment from Reward Hacks with Iterative DPO Benjamin M. Marlin, David Lindner, Oliver Daniels, Perusha Moodley Published: 2026-09-06Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-09-06 | cs.LG | ai-safety, alignment-training, cslg, preprint | E10 / R8 (94%) | - |
| SwiftExplorer: Training-free Diffusion Model Alignment with Swift Diversity Exploration Bojin Huang, Jikang Cheng, Ling Liang, Renye Yan Published: 2026-09-06Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-09-06 | cs.LG | ai-safety, alignment-training, cslg, preprint | E7 / R5 (92%) | - |
| You Are What You Read: Misalignment via In-Context Persona Induction Benjamin Berczi, Cozmin Ududec, Kyuhee Kim Published: 2026-09-06Area: cs.CLCitations: 15 Tags: ai-safety, alignment-training, cscl, preprint | 2026-09-06 | cs.CL | ai-safety, alignment-training, cscl, preprint | E9 / R6 (94%) | 15 |
| Spillover-Aware Multi-Value Steering for Pluralistic LLM Alignment Jiawei Zhou, Weici Pan, Xander Barron, Zhenhua Liu Published: 2026-09-05Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-09-05 | cs.AI | ai-safety, alignment-training, csai, preprint | E8 / R6 (92%) | - |
| Language models judge war differently when tested for alignment Maxim Chupilkin Published: 2026-09-04Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-09-04 | cs.AI | ai-safety, alignment-training, csai, preprint | E7 / R5 (93%) | - |
| Moral Competence Before Moral Content: Why LLM Agents Lack the Prerequisites for Coherent Alignment Arno Libert, Daan R. Henselmans, Derck W. E. Prinzhorn Published: 2026-09-04Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-09-04 | cs.AI | ai-safety, alignment-training, csai, preprint | E11 / R8 (93%) | - |
| ProCA: Progressive Contrastive Alignment for Robust EEG Visual Decoding Chunyan Lan, Dongyang Li, Jun Zhu, Kanglei Zhou Published: 2026-09-04Area: cs.AICitations: 40 Tags: ai-safety, alignment-training, csai, preprint | 2026-09-04 | cs.AI | ai-safety, alignment-training, csai, preprint | E8 / R6 (90%) | 40 |
| VICAL: Vicinal Consistency Alignment for Long-Tailed Visual Recognition Bin Zhu, Jiangang Zhu, Jingjing Chen, Yi-Ping Phoebe Chen Published: 2026-09-04Area: cs.CVCitations: 15 Tags: ai-safety, alignment-training, cscv, preprint | 2026-09-04 | cs.CV | ai-safety, alignment-training, cscv, preprint | E12 / R12 (94%) | 15 |
| Cultural Misalignment in Large Language Models: Detection, Measurement, and Mitigation Through Targeted Fine-Tuning Abel Iyasele, Antoni Czolgowski Published: 2026-09-03Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-09-03 | cs.CL | ai-safety, alignment-training, cscl, preprint | E11 / R8 (96%) | - |
| NeoRed: A Knowledge-Logic-Alignment Multimodal Large Language Model for Neonatal Respiratory Disease Diagnosis Haoran Xu, Hongtai Xia, Jiankang Hong, Jingkuan Song Published: 2026-09-03Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-09-03 | cs.AI | ai-safety, alignment-training, csai, preprint | E12 / R9 (93%) | - |
| NeoRed: A Knowledge-Logic-Alignment Multimodal Large Language Model for Neonatal Respiratory Disease Diagnosis Haoran Xu, Hongtai Xia, Jiankang Hong, Jingkuan Song Published: 2026-09-03Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-09-03 | cs.AI | ai-safety, alignment-training, csai, preprint | E11 / R8 (94%) | - |
| Neural Video Compression Based on Deformable Temporal Alignment and Difference-aware Fusion Chuyue Shan, Shen Zihan, Songlin Sun, Wang Chenwei Published: 2026-09-03Area: cs.CVCitations: 12 Tags: ai-safety, alignment-training, cscv, preprint | 2026-09-03 | cs.CV | ai-safety, alignment-training, cscv, preprint | E8 / R5 (94%) | 12 |
| Patterns of Priming in Production: Lexical, Semantic and Structural Alignment in Language Model Generation Arabella Sinclair, Giulia Pucci, Ruizhe Li Published: 2026-09-03Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-09-03 | cs.CL | ai-safety, alignment-training, cscl, preprint | E12 / R10 (93%) | - |
| Representational alignment yields generalizable safety in language models Lingyu Li, Xia Hu, Yan Teng, Yingchun Wang Published: 2026-09-03Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-09-03 | cs.CL | ai-safety, alignment-training, cscl, preprint | E12 / R7 (93%) | - |
| SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignment Dadi Guo, Dongrui Liu, Guanxu Chen, Leitao Yuan Published: 2026-09-02Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-09-02 | cs.AI | ai-safety, alignment-training, csai, preprint | E8 / R6 (94%) | - |
| SALA: Semantic-Aware Logical Alignment for Complex Reasoning in In-Context Learning Jianxing Yu, Jingping Liu, Shanhe Zhao, Wenqing Chen Published: 2026-09-02Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-09-02 | cs.AI | ai-safety, alignment-training, csai, preprint | E6 / R5 (93%) | - |
| SEAL: Reinforcing Global Safety in Mixture-of-Experts through Shared Expert ALignment Herbert Bos, Jiahuan Pei, Koen Hindriks, Min Chen Published: 2026-09-02Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-09-02 | cs.LG | ai-safety, alignment-training, cslg, preprint | E9 / R7 (93%) | - |
| Confess What You Know: Forget-Set Misalignment with Model Knowledge in LLM Unlearning Georu Lee, Miso Kim, Seungwon Jeong, Woojin Lee Published: 2026-09-01Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-09-01 | cs.LG | ai-safety, alignment-training, cslg, preprint | E7 / R7 (93%) | - |
| Consistency Without Alignment: Item-Sensitive Language Models Indistinguishable From Random Cris Huynh Published: 2026-09-01Area: cs.AICitations: 14 Tags: ai-safety, alignment-training, csai, preprint | 2026-09-01 | cs.AI | ai-safety, alignment-training, csai, preprint | E12 / R12 (94%) | 14 |
| Mechanism Design for Alignment and Control Andrew Koh, Dirk Bergemann, Stephen Morris Published: 2026-09-01Area: econ.THCitations: - Tags: ai-safety, alignment-training, econth, preprint | 2026-09-01 | econ.TH | ai-safety, alignment-training, econth, preprint | E15 / R8 (95%) | - |
| On the Human and Computer Alignment of Attribute-Based Music Matches Emilia G贸mez, Fabio Morreale, Joan Serr脿, Roser Batlle-Roca Published: 2026-09-01Area: cs.SDCitations: 15 Tags: ai-safety, alignment-training, cssd, preprint | 2026-09-01 | cs.SD | ai-safety, alignment-training, cssd, preprint | E11 / R11 (95%) | 15 |
| When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-Tuning Haixu Tang, Siyuan Zhang, Xiaofeng Wang, Xiaoyi Chen Published: 2026-09-01Area: cs.CRCitations: - Tags: ai-safety, alignment-training, cscr, preprint | 2026-09-01 | cs.CR | ai-safety, alignment-training, cscr, preprint | E9 / R7 (92%) | - |
| Assessing Alignment and Stability of Feature Importance Explanations via Weight of Evidence 脕lvaro Parafita, Antonio L. Alfeo, Axel Brando, Claudio Daka Published: 2026-08-31Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-08-31 | cs.LG | ai-safety, alignment-training, cslg, preprint | E6 / R6 (91%) | - |
| Beyond Token-Level Guidance: Inference-Time Alignment of Specialized LLMs via Cross-Family Representation Steering Jin Gan, Jun Luo, Xin Li Published: 2026-08-31Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-08-31 | cs.CL | ai-safety, alignment-training, cscl, preprint | E10 / R7 (88%) | - |
| Beyond Token Positions: Safety Alignment Across Denoising Steps in Diffusion Language Models An Wang, Guoli Wang, Haonan Shi, Tu Ouyang Published: 2026-08-31Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-08-31 | cs.CL | ai-safety, alignment-training, cscl, preprint | E8 / R6 (94%) | - |
| OntoAligner-Ensemble: Voting-Based Fusion across Heterogeneous Ontology Alignment Techniques Hamed Babaei Giglou, Jennifer D'Souza, Mahsa Sanaei, Peio Popov Published: 2026-08-31Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-08-31 | cs.AI | ai-safety, alignment-training, csai, preprint | - | - |
| PAVE: Predictive Alignment and Value-Guided Evolution for World-Action Policies Botong Zhao, Fang Yu, Senhua Zhu, Tim Yu Published: 2026-08-31Area: cs.ROCitations: - Tags: ai-safety, alignment-training, csro, preprint | 2026-08-31 | cs.RO | ai-safety, alignment-training, csro, preprint | E10 / R8 (93%) | - |