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 |
|---|---|---|---|---|---|
| Efficient Task Adaptation in Large Language Models via Selective Parameter Optimization Jiangjiang Zhao, Weijie Wan Published: 2026-04-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-18 | cs.CL | ai-safety, cscl, preprint | E10 / R5 (97%) | - |
| From Legal Text to Executable Decision Models: Evaluating Structured Representations for Legal Decision Model Generation David Graus Published: 2026-04-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-18 | cs.CL | ai-safety, cscl, preprint | E8 / R4 (98%) | - |
| Improving LLM Code Reasoning via Semantic Equivalence Self-Play with Formal Verification Antonio Valerio Miceli Barone, Poon Tsz Nok Published: 2026-04-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-18 | cs.CL | ai-safety, cscl, preprint | E10 / R5 (99%) | - |
| Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation Deyi Xiong, Hao Wang, Heng Liu, Jiang Zhou Published: 2026-04-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-18 | cs.CL | ai-safety, cscl, preprint | E7 / R5 (98%) | - |
| PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations Guangyu Wang, Guang Zhang, Jiaming Shang, Jiatong Zhang Published: 2026-04-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-18 | cs.CL | ai-safety, cscl, preprint | E8 / R3 (96%) | - |
| StageMem: Lifecycle-Managed Memory for Language Models Jiarui Han Published: 2026-04-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-18 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (99%) | - |
| The Consensus Trap: Rescuing Multi-Agent LLMs from Adversarial Majorities via Token-Level Collaboration Jiayuan Liu, Mingyu Guo, Shiyi Du, Vincent Conitzer Published: 2026-04-18Area: cs.CLCitations: - Tags: adversarial-robustness, ai-safety, cscl, preprint | 2026-04-18 | cs.CL | adversarial-robustness, ai-safety, cscl, preprint | E6 / R3 (95%) | - |
| When Informal Text Breaks NLI: Tokenization Failure, Distribution Shift, and Targeted Mitigations Avinash Goutham Aluguvelly Published: 2026-04-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-18 | cs.CL | ai-safety, cscl, preprint | E10 / R5 (100%) | - |
| Where is the Mind? Persona Vectors and LLM Individuation Patrick Butlin, Pierre Beckmann Published: 2026-04-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-18 | cs.CL | ai-safety, cscl, preprint | E9 / R3 (97%) | - |
| ArgBench: Benchmarking LLMs on Computational Argumentation Tasks Carlotta Quensel, Henning Wachsmuth, Nedim Lipka, Yamen Ajjour Published: 2026-04-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-19 | cs.CL | ai-safety, cscl, preprint | E10 / R4 (100%) | - |
| Beyond Overlap Metrics: Rewarding Reasoning and Preferences for Faithful Multi-Role Dialogue Summarization Chao Duan, Da Chen, Fudan Zheng, Guangyu Hu Published: 2026-04-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-19 | cs.CL | ai-safety, cscl, preprint | E10 / R5 (98%) | - |
| Calibrated? Not for Everyone: How Sexual Orientation and Religious Markers Distort LLM Accuracy and Confidence in Medical QA Alberto Testoni, Iacer Calixto Published: 2026-04-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-19 | cs.CL | ai-safety, cscl, preprint | E8 / R5 (98%) | - |
| Cat-DPO: Category-Adaptive Safety Alignment Kaize Ding, Ruiyao Xu, Tiankai Yang, Xinyuan Li Published: 2026-04-19Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-04-19 | cs.CL | ai-safety, alignment-training, cscl, preprint | E8 / R0 (100%) | - |
| Cat-DPO: Category-Adaptive Safety Alignment Kaize Ding, Ruiyao Xu, Tiankai Yang, Xinyuan Li Published: 2026-04-19Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-04-19 | cs.CL | ai-safety, alignment-training, cscl, preprint | E8 / R4 (98%) | - |
| DORA Explorer: Improving the Exploration Ability of LLMs Without Training Kenneth Marino, Md Farhan Ishmam, Priya Gurjar Published: 2026-04-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-19 | cs.CL | ai-safety, cscl, preprint | E8 / R5 (98%) | - |
| DuConTE: Dual-Granularity Text Encoder with Topology-Constrained Attention for Text-attributed Graphs Lexuan Liang, Tao Zou, Xuxiang Ta, Zekun Qiu Published: 2026-04-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-19 | cs.CL | ai-safety, cscl, preprint | E6 / R4 (95%) | - |
| HorizonBench: Long-Horizon Personalization with Evolving Preferences Asli Celikyilmaz, Bhargavi Paranjape, Diyi Yang, Gelin Zhou Published: 2026-04-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-19 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (97%) | - |
| Jupiter-N Technical Report George Drayson Published: 2026-04-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-19 | cs.CL | ai-safety, cscl, preprint | E11 / R7 (96%) | - |
| MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation Hung-yi Lee, I-Ning Tsai, Sung-Feng Huang, Szu-Chi Chen Published: 2026-04-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-19 | cs.CL | ai-safety, cscl, preprint | E9 / R5 (98%) | - |
| OPSDL: On-Policy Self-Distillation for Long-Context Language Models Chun Kang, Jingnan Gu, Run Yang, Tianjun Pan Published: 2026-04-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-19 | cs.CL | ai-safety, cscl, preprint | E7 / R5 (98%) | - |
| Probabilistic Programs of Thought Daniel Israel, Guy Van den Broeck, Kyle Richardson, Poorva Garg Published: 2026-04-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-19 | cs.CL | ai-safety, cscl, preprint | E8 / R4 (98%) | - |
| REZE: Representation Regularization for Domain-adaptive Text Embedding Pre-finetuning Hyunkuk Lim, Jeonghwan Lee, Mingi Sung, Sejoon Kim Published: 2026-04-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-19 | cs.CL | ai-safety, cscl, preprint | E10 / R4 (97%) | - |
| REZE: Representation Regularization for Domain-adaptive Text Embedding Pre-finetuning Hyunkuk Lim, Jeonghwan Lee, Mingi Sung, Sejoon Kim Published: 2026-04-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-19 | cs.CL | ai-safety, cscl, preprint | E11 / R4 (97%) | - |
| RoTRAG: Rule of Thumb Reasoning for Conversation Harm Detection with Retrieval-Augmented Generation Haihua Chen, Juhyeon Lee, Junseo Koh, Seunghyun Lee Published: 2026-04-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-19 | cs.CL | ai-safety, cscl, preprint | E8 / R4 (98%) | - |
| Seeing Isn't Believing: Mitigating Belief Inertia via Active Intervention in Embodied Agents Chak Tou Leong, Hanlin Wang, Jian Wang, Wenjie Li Published: 2026-04-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-19 | cs.CL | ai-safety, cscl, preprint | E10 / R4 (97%) | - |
| Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning Majd Hawasly, Md Rizwan Parvez, Mohammad Raza, Raman Saparkhan Published: 2026-04-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-19 | cs.CL | ai-safety, cscl, preprint | E9 / R5 (98%) | - |
| Semantic Density Effect (SDE): Maximizing Information Per Token Improves LLM Accuracy Amr Ahmed Published: 2026-04-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-19 | cs.CL | ai-safety, cscl, preprint | E9 / R4 (98%) | - |
| Still Between Us? Evaluating and Improving Voice Assistant Robustness to Third-Party Interruptions Che Hyun Lee, Dongwook Lee, Eunwoo Song, Heeseung Kim Published: 2026-04-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-19 | cs.CL | ai-safety, cscl, preprint | E7 / R4 (97%) | - |
| Adversarial Humanities Benchmark: Results on Stylistic Robustness in Frontier Model Safety Daniele Nardi, Federico Pierucci, Federico Sartore, Francesco Giarrusso Published: 2026-04-20Area: cs.CLCitations: - Tags: adversarial-robustness, ai-safety, cscl, preprint | 2026-04-20 | cs.CL | adversarial-robustness, ai-safety, cscl, preprint | E11 / R4 (97%) | - |
| AlphaContext: An Evolutionary Tree-based Psychometric Context Generator for Creativity Assessment Aimin Zhou, Hong Qian, Jiajun Guo, Wenkai Wang Published: 2026-04-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-20 | cs.CL | ai-safety, cscl, preprint | E8 / R5 (96%) | - |