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 |
|---|---|---|---|---|---|
| To Reason or Not to: Selective Chain-of-Thought in Medical Question Answering Min Zeng, Rui Zhang, Shuang Zhou, Xiaoyi Chen Published: 2026-02-23Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-23 | cs.CL | ai-safety, cscl, preprint | E9 / R9 (92%) | - |
| What Makes a Good Query? Measuring the Impact of Human-Confusing Linguistic Features on LLM Performance Manuela Veloso, Nicole Cho, Sumitra Ganesh, William Watson Published: 2026-02-23Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-23 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (92%) | - |
| Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment Alfy Samuel, Anoop Kumar, Daben Liu, Mengxuan Hu Published: 2026-02-24Area: cs.CLCitations: 45 Tags: ai-safety, alignment-training, cscl, preprint | 2026-02-24 | cs.CL | ai-safety, alignment-training, cscl, preprint | E6 / R5 (91%) | 45 |
| Beyond Accuracy: An Explainability-Driven Analysis of Harmful Content Detection Siddhesh Sheth, Trishita Dhara Published: 2026-02-24Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-02-24 | cs.CL | ai-safety, cscl, preprint | E7 / R7 (95%) | 15 |
| CAMEL: Confidence-Gated Reflection for Reward Modeling Hailun Xu, Kanchan Sarkar, Kun Xu, Yang Luo Published: 2026-02-24Area: cs.CLCitations: 150 Tags: ai-safety, cscl, preprint | 2026-02-24 | cs.CL | ai-safety, cscl, preprint | E9 / R8 (91%) | 150 |
| DynaRAG: Bridging Static and Dynamic Knowledge in Retrieval-Augmented Generation Jianan Liu, Jing Yang, Mengwei Yuan, Penghao Liang Published: 2026-02-24Area: cs.CLCitations: 10 Tags: ai-safety, cscl, preprint | 2026-02-24 | cs.CL | ai-safety, cscl, preprint | E8 / R8 (90%) | 10 |
| Enhancing Hate Speech Detection on Social Media: A Comparative Analysis of Machine Learning Models and Text Transformation Approaches Radhika Mamidi, Saurabh Mishra, Shivani Thakur Published: 2026-02-24Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-02-24 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (96%) | 15 |
| MineDraft: A Framework for Batch Parallel Speculative Decoding Alok Prakash, Arun Verma, Bryan Kian Hsiang Low, Daniela Rus Published: 2026-02-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-24 | cs.CL | ai-safety, cscl, preprint | E10 / R10 (91%) | - |
| MrBERT: Modern Multilingual Encoders via Vocabulary, Domain, and Dimensional Adaptation Aitor Gonzalez-Agirre, Daniel Tamayo, I帽aki Lacunza, Javier Aula-Blasco Published: 2026-02-24Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-02-24 | cs.CL | ai-safety, cscl, preprint | E14 / R12 (87%) | 15 |
| Personal Information Parroting in Language Models Kshitish Ghate, Mona Diab, Nishant Subramani Published: 2026-02-24Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-02-24 | cs.CL | ai-safety, cscl, preprint | E12 / R8 (95%) | 45 |
| PVminer: A Domain-Specific Tool to Detect the Patient Voice in Patient Generated Data Afshan Khan, Aimee Roundtree, Ashley Hagaman, Ganesh Puthiaraju Published: 2026-02-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-24 | cs.CL | ai-safety, cscl, preprint | E10 / R10 (93%) | - |
| SibylSense: Adaptive Rubric Learning via Memory Tuning and Adversarial Probing Adam Atkinson, Emre K谋c谋man, Guilherme Potje, Leonardo de Oliveira Nunes Published: 2026-02-24Area: cs.CLCitations: - Tags: adversarial-robustness, ai-safety, cscl, preprint | 2026-02-24 | cs.CL | adversarial-robustness, ai-safety, cscl, preprint | E11 / R9 (92%) | - |
| Small Language Models for Privacy-Preserving Clinical Information Extraction in Low-Resource Languages Ali Akbar Omidvarian, AmirBahador Boroumand, Atena Farangi, Ebrahim Heidari-Farsani Published: 2026-02-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-24 | cs.CL | ai-safety, cscl, preprint | E16 / R11 (93%) | - |
| Steering at the Source: Style Modulation Heads for Robust Persona Control Gouki Minegishi, Kenjiro Taura, Koshi Eguchi, Sosuke Hosokawa Published: 2026-02-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-24 | cs.CL | ai-safety, cscl, preprint | E8 / R5 (89%) | - |
| The Art of Efficient Reasoning: Data, Reward, and Optimization Bo Zhou, Ngai Wong, Taiqiang Wu, Zenan Xu Published: 2026-02-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-24 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (92%) | - |
| Training-Free Agentic AI: Probabilistic Control and Coordination in Multi-Agent LLM Systems Alex Huang, Ankit Shah, Connie Miao, Mohammad Parsa Hosseini Published: 2026-02-24Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-02-24 | cs.CL | ai-safety, cscl, preprint | E7 / R7 (88%) | 15 |
| Under the Influence: Quantifying Persuasion and Vigilance in Large Language Models Ilia Sucholutsky, Katherine M. Collins, Kelsey R. Allen, Sasha Robinson Published: 2026-02-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-24 | cs.CL | ai-safety, cscl, preprint | E13 / R11 (96%) | - |
| A comprehensive study of LLM-based argument classification: from Llama through DeepSeek to GPT-5.2 Andrzej Tomski, Filip Gampel, Jakub Gomu艂ka, Marcin Pietro艅 Published: 2026-02-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-25 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (91%) | - |
| A Fusion of context-aware based BanglaBERT and Two-Layer Stacked LSTM Framework for Multi-Label Cyberbullying Detection Asif Pervez Polok, Kedar Nath Biswas, Mirza Raquib, Nick Rahimi Published: 2026-02-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-25 | cs.CL | ai-safety, cscl, preprint | E7 / R7 (96%) | - |
| BenchBrowser: Retrieving Evidence for Evaluating Benchmark Validity Daphne Ippolito, Gregory Yauney, Harshita Diddee, Swabha Swayamdipta Published: 2026-02-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-25 | cs.CL | ai-safety, cscl, preprint | E13 / R11 (90%) | - |
| Decoder-based Sense Knowledge Distillation Georgios Kollias, Mohammed J. Zaki, Qitong Wang, Vasileios Kalantzis Published: 2026-02-25Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-02-25 | cs.CL | ai-safety, cscl, preprint | E8 / R8 (91%) | 45 |
| DuCCAE: A Hybrid Engine for Immersive Conversation via Collaboration, Augmentation, and Evolution Chenxi Miao, Deguo Xia, Guanqiang QI, Haibo Liu Published: 2026-02-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-25 | cs.CL | ai-safety, cscl, preprint | E12 / R11 (92%) | - |
| Enhancing Multilingual Embeddings via Multi-Way Parallel Text Alignment Barah Fazili, Koustava Goswami Published: 2026-02-25Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-02-25 | cs.CL | ai-safety, alignment-training, cscl, preprint | E17 / R16 (95%) | - |
| Evaluating the relationship between regularity and learnability in recursive numeral systems using Reinforcement Learning Andrea Silvi, Devdatt Dubhashi, Jennifer Culbertson, Kenny Smith Published: 2026-02-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-25 | cs.CL | ai-safety, cscl, preprint | E11 / R8 (88%) | - |
| Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge Distillation Minsang Kim, Seung Jun Baek Published: 2026-02-25Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-02-25 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (92%) | 12 |
| GeoChallenge: A Multi-Answer Multiple-Choice Benchmark for Geometric Reasoning with Diagrams Bo Zhao, Jian Zhang, Jiaxing Huang, Jun Liu Published: 2026-02-25Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-02-25 | cs.CL | ai-safety, cscl, preprint | E6 / R5 (91%) | 15 |
| How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing Javier Mar铆n Published: 2026-02-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-25 | cs.CL | ai-safety, cscl, preprint | E13 / R20 (93%) | - |
| Importance of Prompt Optimisation for Error Detection in Medical Notes Using Language Models Craig Myles, David Harris-Birtill, Patrick Schrempf Published: 2026-02-25Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-02-25 | cs.CL | ai-safety, cscl, preprint | E6 / R6 (92%) | 15 |
| LARFT: Closing the Cognition-Action Gap for Length Instruction Following in Large Language Models Kun Wang, Lintong Du, Li Sun, Sen Su Published: 2026-02-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-25 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (93%) | - |
| Mitigating Structural Noise in Low-Resource S2TT: An Optimized Cascaded Nepali-English Pipeline with Punctuation Restoration Amrit Sarki, Anku Jaiswal, Pranesh Pyara Shrestha, Tangsang Chongbang Published: 2026-02-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-25 | cs.CL | ai-safety, cscl, preprint | E12 / R9 (95%) | - |