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 |
|---|---|---|---|---|---|
| English is Not All You Need: Systematically Exploring the Role of Multilinguality in LLM Post-Training Dezhi Hong, Mehak Dhaliwal, Shashwat Chaurasia, Thomas Butler Published: 2026-04-14Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-14 | cs.CL | ai-safety, cscl, preprint | E6 / R4 (95%) | - |
| Giving Voice to the Constitution: Low-Resource Text-to-Speech for Quechua and Spanish Using a Bilingual Legal Corpus Fabricio Carraro, John E. Ortega, Rodolfo Zevallos Published: 2026-04-14Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-14 | cs.CL | ai-safety, cscl, preprint | E6 / R4 (96%) | - |
| Hessian-Enhanced Token Attribution (HETA): Interpreting Autoregressive LLMs Maisha Maliha, Nathaniel D. Bastian, Sumit Kumar Jha, Vishal Pramanik Published: 2026-04-14Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-14 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| InfiniteScienceGym: An Unbounded, Procedurally-Generated Benchmark for Scientific Analysis Oliver Bentham, Vivek Srikumar Published: 2026-04-14Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-14 | cs.CL | ai-safety, cscl, preprint | E5 / R2 (96%) | - |
| KG-Reasoner: A Reinforced Model for End-to-End Multi-Hop Knowledge Graph Reasoning Shuai Wang, Yinan Yu Published: 2026-04-14Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-14 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| L2D-Clinical: Learning to Defer for Adaptive Model Selection in Clinical Text Classification John E. Ortega, Rishik Kondadadi Published: 2026-04-14Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-14 | cs.CL | ai-safety, cscl, preprint | E6 / R4 (95%) | - |
| Latent Planning Emerges with Scale Emmanuel Ameisen, Michael Hanna Published: 2026-04-14Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-14 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (94%) | - |
| Learning Chain Of Thoughts Prompts for Predicting Entities, Relations, and even Literals on Knowledge Graphs Alkid Baci, Axel-Cyrille Ngonga Ngomo, Caglar Demir, Luke Friedrichs Published: 2026-04-14Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-14 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (94%) | - |
| LLM-Guided Semantic Bootstrapping for Interpretable Text Classification with Tsetlin Machines Jiechao Gao, Jie Wang, Michael Lepech, Rohan Kumar Yadav Published: 2026-04-14Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-14 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| Mining Large Language Models for Low-Resource Language Data: Comparing Elicitation Strategies for Hausa and Fongbe Mahounan Pericles Adjovi, Prasenjit Mitra, Roald Eiselen Published: 2026-04-14Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-14 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| One Token Away from Collapse: The Fragility of Instruction-Tuned Helpfulness Erfan Baghaei Potraghloo, Massoud Pedram, Seyedarmin Azizi, Souvik Kundu Published: 2026-04-14Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-14 | cs.CL | ai-safety, cscl, preprint | E5 / R2 (96%) | - |
| Peer-Predictive Self-Training for Language Model Reasoning Fan Nie, Hanlin Zhang, Sham Kakade, Shi Feng Published: 2026-04-14Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-14 | cs.CL | ai-safety, cscl, preprint | E8 / R3 (97%) | - |
| Representing expertise accelerates learning from pedagogical interaction data Bill D. Thompson, Dhara Yu, Karthikeya Kaushik Published: 2026-04-14Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-14 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (92%) | - |
| Round-Trip Translation Reveals What Frontier Multilingual Benchmarks Miss Ameya Prabhu, Matthias Bethge, Ronald Skorobogat Published: 2026-04-14Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-14 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| SCRIPT: A Subcharacter Compositional Representation Injection Module for Korean Pre-Trained Language Models Eda Atalay, Juhyeong Park, SangKeun Lee, SungHo Kim Published: 2026-04-14Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-14 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (97%) | - |
| SpecBound: Adaptive Bounded Self-Speculation with Layer-wise Confidence Calibration Yang Feng, Zhuofan Wen Published: 2026-04-14Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-14 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (93%) | - |
| Topology-Aware Reasoning over Incomplete Knowledge Graph with Graph-Based Soft Prompting Shuai Wang, Xixi Wang, Yinan Yu Published: 2026-04-14Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-14 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (97%) | - |
| When Does Data Augmentation Help? Evaluating LLM and Back-Translation Methods for Hausa and Fongbe NLP Mahounan Pericles Adjovi, Prasenjit Mitra, Roald Eiselen Published: 2026-04-14Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-14 | cs.CL | ai-safety, cscl, preprint | E7 / R4 (96%) | - |
| Adaptive Conformal Prediction for Improving Factuality of Generations by Large Language Models Aleksandr Rubashevskii, Dzianis Piatrashyn, Maxim Panov, Preslav Nakov Published: 2026-04-15Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-15 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (93%) | - |
| APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AI Amita Misra, Ankit Chadha, Masud Moshtaghi, Pratyay Banerjee Published: 2026-04-15Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-15 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| Applied Explainability for Large Language Models: A Comparative Study Venkata Abhinandan Kancharla Published: 2026-04-15Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-15 | cs.CL | ai-safety, cscl, preprint | E7 / R5 (96%) | - |
| BenGER: A Collaborative Web Platform for End-to-End Benchmarking of German Legal Tasks Matthias Grabmair, Sebastian Nagl Published: 2026-04-15Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-15 | cs.CL | ai-safety, cscl, preprint | E7 / R4 (99%) | - |
| Beyond Arrow's Impossibility: Fairness as an Emergent Property of Multi-Agent Collaboration Antoine Gourru, Julien Velcin, Sayan Kumar Chaki Published: 2026-04-15Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-15 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (94%) | - |
| BiCon-Gate: Consistency-Gated De-colloquialisation for Dialogue Fact-Checking Arkaitz Zubiaga, Hyunkyung Park Published: 2026-04-15Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-15 | cs.CL | ai-safety, cscl, preprint | E5 / R2 (95%) | - |
| Diffusion Language Models for Speech Recognition Albert Zeyer, Davyd Naveriani, Hermann Ney, Ralf Schl眉ter Published: 2026-04-15Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-15 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| Do We Still Need Humans in the Loop? Comparing Human and LLM Annotation in Active Learning for Hostility Detection Ahmad Dawar Hakimi, Hinrich Sch眉tze, Isabelle Augenstein, Lea Hirlimann Published: 2026-04-15Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-15 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| EuropeMedQA Study Protocol: A Multilingual, Multimodal Medical Examination Dataset for Language Model Evaluation Alessandra Piscitelli, Alessia Longo, Antonio Cristiano, Bianca Destro Castaniti Published: 2026-04-15Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-04-15 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E5 / R5 (95%) | - |
| Faithfulness Serum: Mitigating the Faithfulness Gap in Textual Explanations of LLM Decisions via Attribution Guidance Bar Alon, Itamar Zimerman, Lior Wolf Published: 2026-04-15Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-15 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| From Anchors to Supervision: Memory-Graph Guided Corpus-Free Unlearning for Large Language Models Geng Hong, Min Yang, Mi Wen, Mi Zhang Published: 2026-04-15Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-15 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (97%) | - |
| From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMs Eliya Habba, Gabriel Stanovsky, Itay Itzhak, Yonatan Belinkov Published: 2026-04-15Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-15 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (93%) | - |