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 |
|---|---|---|---|---|---|
| Knowing the Rules, Applying the Rules: Evaluating Language Models on Traditional Chinese Bazi Jiulin Li, Ping Huang Published: 2026-10-05Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-05 | cs.CL | ai-safety, cscl, preprint | - | - |
| LightMTP: Lightweight Latent Multi-Token Prediction Chen Shani, Gerard de Melo, Julie Kallini, Tamara Czinczoll Published: 2026-10-05Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-05 | cs.CL | ai-safety, cscl, preprint | - | - |
| LRCC: Generalizing Low-Rank Compression with Conditional Computation Donatella Genovese, Federico Alvetreti, Maximo Eduardo Rulli, Simone Scardapane Published: 2026-10-05Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-05 | cs.CL | ai-safety, cscl, preprint | E10 / R10 (93%) | - |
| MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents Bohan Liu, Haodong Yue, Haozhen Zhang, Jianzhu Bao Published: 2026-10-05Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-05 | cs.CL | ai-safety, cscl, preprint | - | - |
| The Assistance Dilemma: Learning to Teach via Multi-Turn Reinforcement Learning Jakub Macina, Manu Kapur, Mrinmaya Sachan Published: 2026-10-05Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-05 | cs.CL | ai-safety, cscl, preprint | - | - |
| TIDE 2.0: an open, model-agnostic engine for keyed de-identification of clinical notes Jose D. Posada, Priya Desai, Somalee Datta Published: 2026-10-05Area: cs.CLCitations: 26 Tags: ai-safety, cscl, preprint | 2026-10-05 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (93%) | 26 |
| Word-Level Text Unmixing via Evidence-Preserving Ownership Routing with Language Models Guoliang Xing, Hongkai Chen, Jinglin He, Lixing He Published: 2026-10-05Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-05 | cs.CL | ai-safety, cscl, preprint | - | - |
| AraYoungVoices: A Diverse L1/L2 Corpus of Arabic Child and Adolescent Speech Hamdy Mubarak, Houssam Eddine-Othman Lachemat, Shammur Absar Chowdhury, Zien Sheikh Ali Published: 2026-10-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-04 | cs.CL | ai-safety, cscl, preprint | - | - |
| A Systematic Analysis of the Predictive Power of LM Surprisal in Reading Chinese Byung-Doh Oh, Hai Hu, Hongao Zhu, Muxiaoqiao Xu Published: 2026-10-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-04 | cs.CL | ai-safety, cscl, preprint | - | - |
| A Systematic Analysis of the Predictive Power of LM Surprisal in Reading Chinese Byung-Doh Oh, Hai Hu, Hongao Zhu, Muxiaoqiao Xu Published: 2026-10-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-04 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (91%) | - |
| Can Prosodic Style Be Inferred from Text Alone? Evidence from Unsupervised Acoustic Clusters Abdul Rehman, Jian-Jun Zhang, Xiaosong Yang Published: 2026-10-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-04 | cs.CL | ai-safety, cscl, preprint | - | - |
| Cluster Validation Indices as Self-Supervised Objectives for Text Representation Learning Evangelos E. Papalexakis, Jia Chen, Kishor Kumar Bhaumik, Neil Shah Published: 2026-10-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-04 | cs.CL | ai-safety, cscl, preprint | - | - |
| How Much Do LLM-as-a-Judge Design Choices Matter? A Systematic Comparison of Prompt Designs, Rating Scales, and Models Laur猫ne Vaugrante, Thilo Hagendorff Published: 2026-10-04Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-10-04 | cs.CL | ai-safety, cscl, preprint | E13 / R8 (92%) | 45 |
| Investigating Model Compression for Neural Machine Translation in the Biomedical Domain Maria Zafar, Rejwanul Haque, Souhail Bakkali Published: 2026-10-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-04 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (92%) | - |
| Scaling Verifiable Environments for Long-horizon Work Agents Aiden Adams, Boyang Liu, Changzhi Zhou, Chenyang Liao Published: 2026-10-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-04 | cs.CL | ai-safety, cscl, preprint | E6 / R6 (94%) | - |
| Scaling Verifiable Environments for Long-horizon Work Agents Aiden Adams, Boyang Liu, Changzhi Zhou, Chenyang Liao Published: 2026-10-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-04 | cs.CL | ai-safety, cscl, preprint | - | - |
| Self-Generated Feedback Destabilizes Test-Time Training: A Causal Decomposition of Long-Horizon Adaptation Bernard Ghanem, Bing Li, Cheng Luo Published: 2026-10-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-04 | cs.CL | ai-safety, cscl, preprint | - | - |
| Viva La Vida: Verification and Accumulation Failures in Multi-Agent Proof Search Benji Xu, Ken Zheng, Noah Han Published: 2026-10-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-04 | cs.CL | ai-safety, cscl, preprint | - | - |
| When Verifiable Counts Depend on Wording: Auditing Wording Robustness in Instruction Following Minxuan Hu, Qishi Zhan, Seoyeon Jang, Tonghui Qu Published: 2026-10-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-04 | cs.CL | ai-safety, cscl, preprint | - | - |
| AI-Enabled Quality Assurance for Multiple-Choice Assessment Items Nicholas Diana, Steven Moore Published: 2026-10-03Area: cs.CLCitations: 14 Tags: ai-safety, cscl, preprint | 2026-10-03 | cs.CL | ai-safety, cscl, preprint | E11 / R7 (89%) | 14 |
| Evidence and Intervention: A Coupled Active-Inference Extension of Rational Speech Act Models Chun Kee Chung, Elliot Murphy, Yonghyeon Gwon Published: 2026-10-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-03 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (95%) | - |
| Extracting Persona Subspaces Through Iterative Nullspace Projection For Modulation Ananya Malik, Mai ElSherief Published: 2026-10-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-03 | cs.CL | ai-safety, cscl, preprint | - | - |
| From Probe Scores to Alarm Policies: Operational Validity of Activation Monitors for Language-Model Agents Xueping Gao Published: 2026-10-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-03 | cs.CL | ai-safety, cscl, preprint | - | - |
| GlitchPatch: Repairing Glitch Tokens in Frozen Language Models via Local Retokenization Kunsheng Tang, Nenghai Yu, Peigui Qi, Peijun Huang Published: 2026-10-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-03 | cs.CL | ai-safety, cscl, preprint | - | - |
| More Value per Key: Asymmetric Sparse Attention for Faster LLM Decoding Daniel Ohayon, Daniel Soudry, Itay Hubara, Itay Lamprecht Published: 2026-10-03Area: cs.CLCitations: 38 Tags: ai-safety, cscl, preprint | 2026-10-03 | cs.CL | ai-safety, cscl, preprint | E7 / R7 (90%) | 38 |
| More Value per Key: Asymmetric Sparse Attention for Faster LLM Decoding Daniel Ohayon, Daniel Soudry, Itay Hubara, Itay Lamprecht Published: 2026-10-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-03 | cs.CL | ai-safety, cscl, preprint | - | - |
| Playing social deduction games with reinforcement fine-tuned large language models Bolin Ding, Chiming Duan, Kening Zheng, Lingzhe Zhang Published: 2026-10-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-03 | cs.CL | ai-safety, cscl, preprint | E9 / R6 (93%) | - |
| QuanLing: Cross-Branch Validation of Language Distance Quantification on Western Romance Yiping Bai Published: 2026-10-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-03 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (93%) | - |
| Understanding and Mitigating Hallucination Escape in Tool-Using LLM Agents Kunsheng Tang, Nenghai Yu, Peigui Qi, Weiming Zhang Published: 2026-10-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-03 | cs.CL | ai-safety, cscl, preprint | - | - |
| Verdicts Without Annotated Evidence: Rejection Sampling or Label-Only Post-Training for Evidence Recovery? Ashutosh Bilthare, Kevin Paul, Nishanth Nayakanti, Prasang Gupta Published: 2026-10-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-03 | cs.CL | ai-safety, cscl, preprint | E10 / R10 (95%) | - |