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 |
|---|---|---|---|---|---|
| Parallelograms Strike Back: LLMs Generate Better Analogies than People Adele E. Goldberg, Jian-Qiao Zhu, Qiawen Ella Liu, Raja Marjieh Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (93%) | - |
| PowerFlow: Unlocking the Dual Nature of LLMs via Principled Distribution Matching Longbo Huang, Ruishuo Chen, Yu Chen, Zhuoran Li Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (94%) | - |
| Progressive Training for Explainable Citation-Grounded Dialogue: Reducing Hallucination to Zero in English-Hindi LLMs Vedant Pandya Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E7 / R3 (96%) | - |
| Scalable Prompt Routing via Fine-Grained Latent Task Discovery Ashwin Ganesh, George Karypis, Huzefa Rangwala, Patrick Guan Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (96%) | - |
| Scalable Prompt Routing via Fine-Grained Latent Task Discovery Ashwin Ganesh, George Karypis, Huzefa Rangwala, Sheng Guan Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E42 / R26 (96%) | - |
| TARo: Token-level Adaptive Routing for LLM Test-time Alignment Arushi Rai, Dipesh Tamboli, Hanqing Zeng, Lizhu Zhang Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, alignment-training, cscl, preprint | E6 / R3 (96%) | - |
| UGID: Unified Graph Isomorphism for Debiasing Large Language Models Hongbo Liu, Junchi Yao, Junhao Li, Lijie Hu Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (96%) | - |
| VEPO: Variable Entropy Policy Optimization for Low-Resource Language Foundation Models Chonghan Liu, Cunqi Zhai, Fei Tan, Qi An Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| Vocabulary shapes cross-lingual variation of word-order learnability in language models Jaap Jumelet, Jonas Mayer Martins, Lisa Beinborn, Viola Priesemann Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (93%) | - |
| WASD: Locating Critical Neurons as Sufficient Conditions for Explaining and Controlling LLM Behavior Haonan Yu, Haoran Lin, Junhao Liu, Xin Zhang Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| What Really Controls Temporal Reasoning in Large Language Models: Tokenisation or Representation of Time? Ahmad Muhammad Isa, Gagan Bhatia, Maxime Peyrard, Wei Zhao Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E4 / R2 (94%) | - |
| When Names Change Verdicts: Intervention Consistency Reveals Systematic Bias in LLM Decision-Making Abhinaba Basu, Pavan Chakraborty Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (94%) | - |
| An Empirical Study of SFT-DPO Interaction and Parameterization in Small Language Models Christy Yang, Yuming Feng Published: 2026-03-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-20 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (96%) | - |
| Coding Agents are Effective Long-Context Processors Bhuwan Dhingra, Shuyan Zhou, Weili Cao, Xunjian Yin Published: 2026-03-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-20 | cs.CL | ai-safety, cscl, preprint | E28 / R25 (95%) | - |
| Diffutron: A Masked Diffusion Language Model for Turkish Language 艦uayp Talha Kocabay, Talha R眉zgar Akku艧 Published: 2026-03-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-20 | cs.CL | ai-safety, cscl, preprint | E50 / R35 (96%) | - |
| Enhancing Hyperspace Analogue to Language (HAL) Representations via Attention-Based Pooling for Text Classification Ali Sakour, Zoalfekar Sakour Published: 2026-03-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-20 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (96%) | - |
| Evaluating Large Language Models on Historical Health Crisis Knowledge in Resource-Limited Settings: A Hybrid Multi-Metric Study Mohammed Rakibul Hasan Published: 2026-03-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-20 | cs.CL | ai-safety, cscl, preprint | E26 / R33 (96%) | - |
| FDARxBench: Benchmarking Regulatory and Clinical Reasoning on FDA Generic Drug Assessment Benjamin Newman, Betty Xiong, Jillian Fisher, Lanyan Fang Published: 2026-03-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-20 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (98%) | - |
| FrameNet Semantic Role Classification by Analogy Emiliano Lorini, Miguel Couceiro, Stergos Afantenos, Van-Duy Ngo Published: 2026-03-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-20 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (94%) | - |
| LoASR-Bench: Evaluating Large Speech Language Models on Low-Resource Automatic Speech Recognition Across Language Families Jianan Chen, Nancy F. Chen, Tatsuya Kawahara, Xiaoxue Gao Published: 2026-03-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-20 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (98%) | - |
| Measuring Faithfulness Depends on How You Measure: Classifier Sensitivity in LLM Chain-of-Thought Evaluation Richard J. Young Published: 2026-03-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-03-20 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E6 / R4 (98%) | - |
| Measuring Faithfulness Depends on How You Measure: Classifier Sensitivity in LLM Chain-of-Thought Evaluation Richard J. Young Published: 2026-03-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-03-20 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E7 / R4 (99%) | - |
| Permutation-Consensus Listwise Judging for Robust Factuality Evaluation Elsa Fan, Justin Tang, Nathan Huang, Tianyi Huang Published: 2026-03-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-03-20 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E33 / R25 (94%) | - |
| Policies Permitting LLM Use for Polishing Peer Reviews Are Currently Not Enforceable Danish Pruthi, Dayita Chaudhuri, Gurusha Juneja, Naveeja Sajeevan Published: 2026-03-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-20 | cs.CL | ai-safety, cscl, preprint | E47 / R28 (98%) | - |
| Semantic Delta: An Interpretable Signal Differentiating Human and LLMs Dialogue Francesco Bertolotti, Giacomo Buonanno, Mauro Mezzanzana, Riccardo Scantamburlo Published: 2026-03-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-20 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (96%) | - |
| Semantic Token Clustering for Efficient Uncertainty Quantification in Large Language Models Andrew Gambardella, Qi Cao, Takeshi Kojima, Yusuke Iwasawa Published: 2026-03-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-20 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (97%) | - |
| Span-Level Machine Translation Meta-Evaluation Eric Morales Agostinho, Hugo Zaragoza, Stefano Perrella Published: 2026-03-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-03-20 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E4 / R3 (94%) | - |
| The production of meaning in the processing of natural language Christopher J. Agostino, Louis van der Elst, Nayan D'Souza, Quan Le Thien Published: 2026-03-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-20 | cs.CL | ai-safety, cscl, preprint | E65 / R35 (94%) | - |
| Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models Jane C. Ginsburg, Niloofar Mireshghallah, Tuhin Chakrabarty, Xinyue Liu Published: 2026-03-21Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-03-21 | cs.CL | ai-safety, alignment-training, cscl, preprint | E5 / R3 (94%) | - |
| Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models Jane C. Ginsburg, Niloofar Mireshghallah, Tuhin Chakrabarty, Xinyue Liu Published: 2026-03-21Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-03-21 | cs.CL | ai-safety, alignment-training, cscl, preprint | E5 / R2 (96%) | - |