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 |
|---|---|---|---|---|---|
| AI Appeals Processor: A Deep Learning Approach to Automated Classification of Citizen Appeals in Government Services Vladimir Beskorovainyi Published: 2026-04-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-04 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (98%) | - |
| LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering A. B. Siddique, Hassan Sajjad, Sing Hieng Wong Published: 2026-04-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-04 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| LightThinker++: From Reasoning Compression to Memory Management Da Zheng, Huajun Chen, Jintian Zhang, Lei Liang Published: 2026-04-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-04 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (96%) | - |
| Testing the Limits of Truth Directions in LLMs Angelos Poulis, Evimaria Terzi, Mark Crovella Published: 2026-04-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-04 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (94%) | - |
| Unlocking Prompt Infilling Capability for Diffusion Language Models Keisuke Sakaguchi, Yoshinari Fujinuma Published: 2026-04-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-04 | cs.CL | ai-safety, cscl, preprint | E7 / R3 (98%) | - |
| Unveiling Language Routing Isolation in Multilingual MoE Models for Interpretable Subnetwork Adaptation Hanrong Zhang, Henry Peng Zou, Jiahao Huo, Jungang Li Published: 2026-04-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-04 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| When Models Know More Than They Say: Probing Analogical Reasoning in LLMs Caroline Craig, Hale Sirin, Hope McGovern, Thomas Lippincott Published: 2026-04-04Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-04 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (93%) | - |
| AdaptFuse: Training-Free Sequential Preference Learning via Externalized Bayesian Inference Fangzhou Lin, Haichong Zhang, Kazunori Yamada, Peiran Li Published: 2026-04-05Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-05 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (94%) | - |
| Embedding Enhancement via Fine-Tuned Language Models for Learner-Item Cognitive Modeling Aimin Zhou, Hong Qian, Jiajun Guo, Kaiying Wu Published: 2026-04-05Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-05 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (96%) | - |
| Extracting and Steering Emotion Representations in Small Language Models: A Methodological Comparison Jihoon Jeong Published: 2026-04-05Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-05 | cs.CL | ai-safety, cscl, preprint | E8 / R4 (97%) | - |
| I-CALM: Incentivizing Confidence-Aware Abstention for LLM Hallucination Mitigation Binze Li, Gillian K. Hadfield, Haotian Zong, Jialong Wu Published: 2026-04-05Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-05 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| Many Preferences, Few Policies: Towards Scalable Language Model Personalization Andrew Perrault, Cheol Woo Kum, Jai Moondra, Milind Tambe Published: 2026-04-05Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-05 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (94%) | - |
| Uncertainty as a Planning Signal: Multi-Turn Decision Making for Goal-Oriented Conversation Reza Averly, Xia Ning, Xinyi Ling, Ye Liu Published: 2026-04-05Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-05 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| Which English Do LLMs Prefer? Triangulating Structural Bias Towards American English in Foundation Models Davood Rafiei, Mir Tafseer Nayeem Published: 2026-04-05Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-05 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| $蟺^2$: Structure-Originated Reasoning Data Improves Long-Context Reasoning Ability of Large Language Models Nguyen Nguyen, Pratibha Zunjare, Quyet V. Do, Sha Li Published: 2026-04-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-06 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (98%) | - |
| Beyond LLM-as-a-Judge: Deterministic Metrics for Multilingual Generative Text Evaluation Firoj Alam, Gagan Bhatia, Sahinur Rahman Laskar, Shammur Absar Chowdhury Published: 2026-04-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-04-06 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E5 / R3 (97%) | - |
| BiST: A Gold Standard Bangla-English Bilingual Corpus for Sentence Structure and Tense Classification with Inter-Annotator Agreement Abdullah Al Shafi, Abdul Muntakim, M. A. Moyeen, Shoumik Barman Polok Published: 2026-04-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-06 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (98%) | - |
| Compressible Softmax-Attended Language under Incompressible Attention Wonsuk Lee Published: 2026-04-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-06 | cs.CL | ai-safety, cscl, preprint | E4 / R2 (93%) | - |
| Conversational Control with Ontologies for Large Language Models: A Lightweight Framework for Constrained Generation Barbara Gendron, Ga毛l Guibon, Mathieu d'Aquin Published: 2026-04-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-06 | cs.CL | ai-safety, cscl, preprint | E5 / R2 (96%) | - |
| Early Stopping for Large Reasoning Models via Confidence Dynamics Mahdi Salmani, Meisam Razaviyayn, Parsa Hosseini, Soheil Feizi Published: 2026-04-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-06 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (94%) | - |
| Exemplar Retrieval Without Overhypothesis Induction: Limits of Distributional Sequence Learning in Early Word Learning Jon-Paul Cacioli Published: 2026-04-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-06 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| GROUNDEDKG-RAG: Grounded Knowledge Graph Index for Long-document Question Answering Andreas Marfurt, Tianyi Zhang Published: 2026-04-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-06 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| Hallucination Basins: A Dynamic Framework for Understanding and Controlling LLM Hallucinations Kalyan Cherukuri, Lav R. Varshney Published: 2026-04-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-06 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models Gregory N. Frank Published: 2026-04-06Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-04-06 | cs.CL | ai-safety, alignment-training, cscl, preprint | E6 / R3 (94%) | - |
| Improving Clinical Trial Recruitment using Clinical Narratives and Large Language Models Cheng Peng, Mengxian Lyu, Yonghui Wu, Ziyi Chen Published: 2026-04-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-06 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (97%) | - |
| Individual and Combined Effects of English as a Second Language and Typos on LLM Performance Arnav Sharma, Marina Lin, Mengyu Wang, Minda Zhao Published: 2026-04-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-06 | cs.CL | ai-safety, cscl, preprint | E8 / R3 (95%) | - |
| Is a Picture Worth a Thousand Words? Adaptive Multimodal Fact-Checking with Visual Evidence Necessity Jaeyoon Jung, Kunwoo Park, Yejun Yoon Published: 2026-04-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-06 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| LiveFact: A Dynamic, Time-Aware Benchmark for LLM-Driven Fake News Detection Changhong Jin, Cheng Xu, Liming Chen, M-Tahar Kechadi Published: 2026-04-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-06 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (99%) | - |
| Metaphors We Compute By: A Computational Audit of Cultural Translation vs. Thinking in LLMs Jiaming Qu, Yuan Chang, Zhu Li Published: 2026-04-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-06 | cs.CL | ai-safety, cscl, preprint | E4 / R2 (93%) | - |
| Multilingual Prompt Localization for Agent-as-a-Judge: Language and Backbone Sensitivity in Requirement-Level Evaluation Alhasan Mahmood, Hasan Kurban, Samir Abdaljalil Published: 2026-04-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-04-06 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E5 / R4 (96%) | - |