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 |
|---|---|---|---|---|---|
| Learning to Learn from Language Feedback with Social Meta-Learning Claudiu Musat, Diego Antognini, Edward Grefenstette, Jonathan Cook Published: 2026-02-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-18 | cs.CL | ai-safety, cscl, preprint | E9 / R6 (93%) | - |
| Long-Tail Knowledge in Large Language Models: Taxonomy, Mechanisms, Interventions and Implications Deep Shah, Nehal Kathrotia, Sanket Badhe Published: 2026-02-18Area: cs.CLCitations: 127 Tags: ai-safety, cscl, preprint | 2026-02-18 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (90%) | 127 |
| Measuring and Eliminating Refusals in Military Large Language Models Aman Sharma, Aristotelis Lazaridis, Brian King, Colton Malkerson Published: 2026-02-18Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-02-18 | cs.CL | ai-safety, cscl, preprint | E12 / R8 (95%) | 45 |
| References Improve LLM Alignment in Non-Verifiable Domains Alexander R. Fabbri, Arman Cohan, Kejian Shi, Peifeng Wang Published: 2026-02-18Area: cs.CLCitations: 15 Tags: ai-safety, alignment-training, cscl, preprint | 2026-02-18 | cs.CL | ai-safety, alignment-training, cscl, preprint | E17 / R8 (92%) | 15 |
| Task-Specific Knowledge Distillation via Intermediate Probes Chris Russell, Ryan Brown Published: 2026-02-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-18 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (93%) | - |
| Team of Thoughts: Efficient Test-time Scaling of Agentic Systems through Orchestrated Tool Calling Jeffrey T. H. Wong, Junyi Liu, Yiren Zhao, Zixi Zhang Published: 2026-02-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-18 | cs.CL | ai-safety, cscl, preprint | E8 / R7 (93%) | - |
| When Semantic Overlap Is Not Enough: Cross-Lingual Euphemism Transfer Between Turkish and English Anna Feldman, Hasan Can Biyik, Jing Peng, Libby Barak Published: 2026-02-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-18 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (92%) | - |
| Who can we trust? LLM-as-a-jury for Comparative Assessment Guangzhi Sun, Kate M. Knill, Mark J. F. Gales, Mengjie Qian Published: 2026-02-18Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-02-18 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (90%) | 15 |
| ALPS: A Diagnostic Challenge Set for Arabic Linguistic & Pragmatic Reasoning Ahmad Alshareef, Hussein S. Al-Olimat Published: 2026-02-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-19 | cs.CL | ai-safety, cscl, preprint | E8 / R9 (91%) | - |
| Evaluating Cross-Lingual Classification Approaches Enabling Topic Discovery for Multilingual Social Media Data Deepak Uniyal, Md Abul Bashar, Richi Nayak Published: 2026-02-19Area: cs.CLCitations: 23 Tags: ai-safety, cscl, preprint | 2026-02-19 | cs.CL | ai-safety, cscl, preprint | E14 / R15 (94%) | 23 |
| Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study David Skarbrevik, Dylan Bouchard, Mohit Singh Chauhan, Viren Bajaj Published: 2026-02-19Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-02-19 | cs.CL | ai-safety, cscl, preprint | E13 / R14 (88%) | 45 |
| Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History Dongha Lee, Sangam Lee, Serin Kim Published: 2026-02-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-19 | cs.CL | ai-safety, cscl, preprint | E9 / R8 (93%) | - |
| QueryPlot: Generating Geological Evidence Layers using Natural Language Queries for Mineral Exploration Georgina Lukoczki, Graham W. Lederer, Meng Ye, Xiao Lin Published: 2026-02-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-19 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (92%) | - |
| ReIn: Conversational Error Recovery with Reasoning Inception Chandrayee Basu, Chengyuan Ma, Dilek Hakkani-T眉r, Gokhan Tur Published: 2026-02-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-19 | cs.CL | ai-safety, cscl, preprint | E9 / R8 (89%) | - |
| Same Meaning, Different Scores: Lexical and Syntactic Sensitivity in LLM Evaluation Alexander L枚ser, Bogdan Kosti膰, Conor Fallon, Julian Risch Published: 2026-02-19Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-02-19 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E10 / R9 (94%) | 15 |
| Sink-Aware Pruning for Diffusion Language Models Aidar Myrzakhan, Bowei Guo, Shengkun Tang, Tianyi Li Published: 2026-02-19Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-02-19 | cs.CL | ai-safety, cscl, preprint | E11 / R8 (88%) | 15 |
| The Cascade Equivalence Hypothesis: When Do Speech LLMs Behave Like ASR$\rightarrow$LLM Pipelines? Jayadev Billa Published: 2026-02-19Area: cs.CLCitations: 31 Tags: ai-safety, cscl, preprint | 2026-02-19 | cs.CL | ai-safety, cscl, preprint | E16 / R9 (93%) | 31 |
| Towards Cross-lingual Values Judgment: A Consensus-Pluralism Perspective Baosong Yang, Boyi Deng, Fei Huang, Jialong Tang Published: 2026-02-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-19 | cs.CL | ai-safety, cscl, preprint | E19 / R16 (87%) | - |
| Understanding Unreliability of Steering Vectors in Language Models: Geometric Predictors and the Limits of Linear Approximations Joschka Braun Published: 2026-02-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-19 | cs.CL | ai-safety, cscl, preprint | E8 / R5 (90%) | - |
| Agentic Adversarial QA for Improving Domain-Specific LLMs Ciprian Tomoiaga, Marcin Detyniecki, Sylvain Lamprier, Tatsunori Hashimoto Published: 2026-02-20Area: cs.CLCitations: 45 Tags: adversarial-robustness, ai-safety, cscl, preprint | 2026-02-20 | cs.CL | adversarial-robustness, ai-safety, cscl, preprint | E9 / R6 (90%) | 45 |
| Click it or Leave it: Detecting and Spoiling Clickbait with Informativeness Measures and Large Language Models Anna Wroblewska, Mateusz Kubita, Soveatin Kuntur, Tymoteusz Urban Published: 2026-02-20Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-02-20 | cs.CL | ai-safety, cscl, preprint | E14 / R10 (94%) | 45 |
| Condition-Gated Reasoning for Context-Dependent Biomedical Question Answering Chih-Hsuan Wei, Jash Rajesh Parekh, Jiawei Han, Joey Chan Published: 2026-02-20Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-02-20 | cs.CL | ai-safety, cscl, preprint | E7 / R6 (89%) | 15 |
| CUICurate: A GraphRAG-based Framework for Automated Clinical Concept Curation for NLP applications Blanca Gallego, Jamie Novak, Mathew Miller, Sze-yuan Ooi Published: 2026-02-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-20 | cs.CL | ai-safety, cscl, preprint | E17 / R16 (88%) | - |
| Do Large Language Models Possess a Theory of Mind? A Comparative Evaluation Using the Strange Stories Paradigm Andras Lukacs, Anna Babarczy, Peter Vedres, Zeteny Bujka Published: 2026-02-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-02-20 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E7 / R5 (92%) | - |
| FENCE: A Financial and Multimodal Jailbreak Detection Dataset Mirae Kim, Seonghun Jeong, Youngjun Kwak Published: 2026-02-20Area: cs.CLCitations: 45 Tags: adversarial-robustness, ai-safety, cscl, preprint | 2026-02-20 | cs.CL | adversarial-robustness, ai-safety, cscl, preprint | E10 / R10 (89%) | 45 |
| Improving Topic Modeling by Distilling Soft Labels from Language Models Amirhossein Abaskohi, Chuyuan Li, Gabriel Murray, Giuseppe Carenini Published: 2026-02-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-20 | cs.CL | ai-safety, cscl, preprint | E14 / R13 (86%) | - |
| Luna-2: Scalable Single-Token Evaluation with Small Language Models Amey Ramesh Rambatla, Nikhil Ega, Rishon Dsouza, Rob Friel Published: 2026-02-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-02-20 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E10 / R9 (89%) | - |
| Perceived Political Bias in LLMs Reduces Persuasive Abilities Joshua Robison, Matthew DiGiuseppe Published: 2026-02-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-20 | cs.CL | ai-safety, cscl, preprint | E3 / R0 (95%) | - |
| Simplifying Outcomes of Language Model Component Analyses with ELIA Aaron Louis Eidt, Nils Feldhus Published: 2026-02-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-20 | cs.CL | ai-safety, cscl, preprint | E9 / R8 (93%) | - |
| Thinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoning Bang Yang, Bingchen Zhao, Lexiang Tang, Lu Ma Published: 2026-02-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-20 | cs.CL | ai-safety, cscl, preprint | E6 / R5 (93%) | - |