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 |
|---|---|---|---|---|---|
| SEAHateCheck: Functional Tests for Detecting Hate Speech in Low-Resource Languages of Southeast Asia Aditi Kumaresan, Ri Chi Ng, Roy Ka-Wei Lee, Yujia Hu Published: 2026-03-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-17 | cs.CL | ai-safety, cscl, preprint | E8 / R4 (98%) | - |
| TharuChat: Bootstrapping Large Language Models for a Low-Resource Language via Synthetic Data and Human Validation Agniva Maiti, Prajwal Panth Published: 2026-03-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-17 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (97%) | - |
| TurnWise: The Gap between Single- and Multi-turn Language Model Capabilities Hannaneh Hajishirzi, Nathan Lambert, Nouha Dziri, Valentina Pyatkin Published: 2026-03-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-17 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (97%) | - |
| Who Benchmarks the Benchmarks? A Case Study of LLM Evaluation in Icelandic Bjarki 脕rmannsson, Finnur 脕g煤st Ingimundarson, Iris Edda Nowenstein, Steinunn Rut Fri冒riksd贸ttir Published: 2026-03-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-03-17 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E6 / R4 (96%) | - |
| Adaptive Guidance for Retrieval-Augmented Masked Diffusion Models Jaemin Kim, Jong Chul Ye Published: 2026-03-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-18 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution Guiyang Hou, Jun Xiao, Ruiqing Zhang, Teng Pan Published: 2026-03-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-18 | cs.CL | ai-safety, cscl, preprint | E27 / R23 (96%) | - |
| CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution Gaiyang Han, Jun Xiao, Ruiqing Zhang, Teng Pan Published: 2026-03-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-18 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (94%) | - |
| Detecting the Machine: A Comprehensive Benchmark of AI-Generated Text Detectors Across Architectures, Domains, and Adversarial Conditions Chirag Chawla, Madhav S. Baidya, S. S. Baidya Published: 2026-03-18Area: cs.CLCitations: - Tags: adversarial-robustness, ai-safety, cscl, preprint | 2026-03-18 | cs.CL | adversarial-robustness, ai-safety, cscl, preprint | E6 / R3 (96%) | - |
| From Noise to Signal: When Outliers Seed New Topics Benjamin Icard, Evangelia Zve, Gauvain Bourgne, Jean-Gabriel Ganascia Published: 2026-03-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-18 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| From Words to Worlds: Benchmarking Cross-Cultural Cultural Understanding in Machine Translation Abibulla Atawulla, Ahtamjan Ahmat, Bangju Han, Fengyi Yang Published: 2026-03-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-18 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (93%) | - |
| Harm or Humor: A Multimodal, Multilingual Benchmark for Overt and Covert Harmful Humor Ahmed Sharshar, Hosam Elgendy, Saad El Dine Ahmed, Yasser Rohaim Published: 2026-03-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-18 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (97%) | - |
| How do LLMs Compute Verbal Confidence Arthur Conmy, Dharshan Kumaran, Federico Barbero, Petar Velickovic Published: 2026-03-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-18 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| How LLMs Distort Our Written Language Ibrahim Qureshi, Isadora White, Joel Leibo, Marwa Abdulhai Published: 2026-03-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-18 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (94%) | - |
| IndicSafe: A Benchmark for Evaluating Multilingual LLM Safety in South Asia Priyaranjan Pattnayak, Sanchari Chowdhuri Published: 2026-03-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-18 | cs.CL | ai-safety, cscl, preprint | E4 / R2 (94%) | - |
| Mitigating LLM Hallucinations through Domain-Grounded Tiered Retrieval Aasar Mehdi, Maaz Mahboob, Md. Asraful Haque, Tamkeen Fatima Published: 2026-03-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-18 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| Text-to-Stage: Spatial Layouts from Long-form Narratives Calvin Murdock, Chenxi Whitehouse, Ishwarya Ananthabhotla, Jefferson Hernandez Published: 2026-03-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-18 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (93%) | - |
| Adaptive Decoding via Test-Time Policy Learning for Self-Improving Generation Asmita Bhardwaj, Basel Shbita, Eelaaf Zahid, Yuya Jeremy Ong Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (97%) | - |
| DaPT: A Dual-Path Framework for Multilingual Multi-hop Question Answering Jiaoyang Li, Jingbo Zhu, Qiaozhi He, Tong Xiao Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (95%) | - |
| Evaluating LLM-Generated Lessons from the Language Learning Students' Perspective: A Short Case Study on Duolingo Carlos Rafael Catalan, Gap Estrella, Lheane Marie Dizon, Marie Antoinette Patalagsa Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (94%) | - |
| Evaluating LLM-Generated Lessons from the Language Learning Students' Perspective: A Short Case Study on Duolingo Carlos Rafael Catalan, Gap Estrella, Lheane Marie Dizon, Marie Antoinette Patalagsa Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E22 / R17 (93%) | - |
| F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World Hang Yu, Peng Di, Rui Wang, Zihan Liao Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| Hypothesis-Conditioned Query Rewriting for Decision-Useful Retrieval Changsun Lee, Hangeol Chang, Jong Chul Ye, Junho Yeo Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (97%) | - |
| ICE: Intervention-Consistent Explanation Evaluation with Statistical Grounding for LLMs Abhinaba Basu, Pavan Chakraborty Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-03-19 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E5 / R3 (98%) | - |
| Inducing Sustained Creativity and Diversity in Large Language Models Gary King, Michael D. Smith, Michael Puett, Queenie Luo Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (98%) | - |
| Is Evaluation Awareness Just Format Sensitivity? Limitations of Probe-Based Evidence under Controlled Prompt Structure Viliana Devbunova Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-03-19 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E5 / R3 (94%) | - |
| Learning to Self-Evolve Boyi Liu, Canwen Xu, Xiaoyin Chen, Yite Wang Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (94%) | - |
| Mi:dm K 2.5 Pro KT Tech innovation Group Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| Mi:dm K 2.5 Pro KT Tech innovation Group Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation Alexander Bukharin, Boxin Wang, Bryan Catanzaro, Chankyu Lee Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E54 / R30 (96%) | - |
| Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation Alexander Bukharin, Boxin Wang, Bryan Catanzaro, Chankyu Lee Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (99%) | - |