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 |
|---|---|---|---|---|---|
| Hallucination-R1: Robustness-Oriented Paraphrase Generation for Factual Consistency Hao Wang, Lei Sha, Wenhan Yu, Wenxin Wu Published: 2026-09-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-18 | cs.CL | ai-safety, cscl, preprint | E11 / R10 (91%) | - |
| NemotronLabs VoiceChat: An Open Full-duplex Speech-to-Speech Model with Tool Calling Capabilities Adi Margolin, Aditya Malte, Ameya Mahabaleshwarkar, Anand Joseph Published: 2026-09-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-18 | cs.CL | ai-safety, cscl, preprint | E11 / R9 (92%) | - |
| Preserving What Matters: Semantic Scaffolds Beyond Saturation in Summarization Evaluation Nikhil Reddy Pottanigari, Noah Bolger, Ramin Fahimi, Sepideh Kharaghani Published: 2026-09-18Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-09-18 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E14 / R9 (89%) | 15 |
| Preserving What Matters: Semantic Scaffolds Beyond Saturation in Summarization Evaluation Nikhil Reddy Pottanigari, Noah Bolger, Ramin Fahimi, Sepideh Kharaghani Published: 2026-09-18Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-09-18 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E14 / R8 (88%) | 45 |
| Steering LLMs Responses Towards Moral Foundations on the Norwegian MFQ-30 David Dichas, Hans Andersen Published: 2026-09-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-18 | cs.CL | ai-safety, cscl, preprint | E18 / R15 (94%) | - |
| Talking Past the Machine: Morality, Politeness, and Alignment in Human-AI Dialogue Lu Xiao, Marina Mitiaeva Published: 2026-09-18Area: cs.CLCitations: 45 Tags: ai-safety, alignment-training, cscl, preprint | 2026-09-18 | cs.CL | ai-safety, alignment-training, cscl, preprint | E10 / R6 (91%) | 45 |
| Toward Personalized Sleep Guidance from Wearable Data Using Language Models Alejandra Lastra, Arlene Ruiz de Luzuriaga, Ash Arian, Bonnie W. Leung Published: 2026-09-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-18 | cs.CL | ai-safety, cscl, preprint | E9 / R7 (95%) | - |
| When Steering Fails in Latent Reasoning: A Latent-to-Language Transition Gap Gaoxiang Huang, Lei Qi Published: 2026-09-18Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-09-18 | cs.CL | ai-safety, cscl, preprint | E10 / R10 (92%) | 12 |
| Aligning with Lived Experience: Heterogeneous Benefits of Fine Tuning in Mental Health Support Generation Aamogh Sawant, Eli Min, Mohit Chandra, Munmun De Choudhury Published: 2026-09-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-17 | cs.CL | ai-safety, cscl, preprint | E12 / R10 (93%) | - |
| Benchmarking LLM Compliance with China AI Generated Content Regulations Chenrui Cui, Gang Xu, Hongye Fang, Lisha Song Published: 2026-09-17Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-17 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (94%) | 15 |
| Chronicle: Cut-Point Replay for Regression Testing of LLM Agents Susheem Koul, Tisha Chawla Published: 2026-09-17Area: cs.CLCitations: 25 Tags: ai-safety, cscl, preprint | 2026-09-17 | cs.CL | ai-safety, cscl, preprint | E7 / R6 (92%) | 25 |
| CliniCIRCA: A Modular LLM Framework for Constructing Longitudinal Mental Health Patient Journeys from Raw EHR Narratives Adam Coscia, Aiwei Ivy Zhang, Khatiya Chelidze Moon, Mohit Chandra Published: 2026-09-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-17 | cs.CL | ai-safety, cscl, preprint | E6 / R5 (92%) | - |
| Edustories: A Collection of Real-world Case Studies from Classroom Practices David Kosatka, Jan Nehyba, Jirina Karasova, Lucie 艩karkov谩 Published: 2026-09-17Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-17 | cs.CL | ai-safety, cscl, preprint | E7 / R7 (93%) | 15 |
| Evolution or Illusion? Rethinking Evaluation in LLM Evolutionary Search Oshri Naparstek, Roi Pony, Tal Oved, Udi Barzelay Published: 2026-09-17Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-09-17 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E10 / R12 (91%) | 45 |
| Form Over Content In Gradient-Based Data Attribution Methods Alice Oh, Seokwon Jung, Seong Joon Oh, Sohyung Kim Published: 2026-09-17Area: cs.CLCitations: 18 Tags: ai-safety, cscl, preprint | 2026-09-17 | cs.CL | ai-safety, cscl, preprint | E19 / R10 (96%) | 18 |
| From Task Success to Productive Success: Evaluating Human-AI Collaboration by Quality and Cost Malihe Alikhani, Mert 陌nan, Saki Imai Published: 2026-09-17Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-09-17 | cs.CL | ai-safety, cscl, preprint | E15 / R11 (90%) | 45 |
| Geometry of Values: Task Vector Composition for Ethical Preference Alignment in Language Models Monojit Choudhury, Utkarsh Agarwal Published: 2026-09-17Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-09-17 | cs.CL | ai-safety, alignment-training, cscl, preprint | E14 / R6 (95%) | - |
| Harm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations Noura Al Moubayed, Sarah Wyer, Sue Black Published: 2026-09-17Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-09-17 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (91%) | 12 |
| KoNeoBench: A Curated Evaluation Dataset for LLM Understanding of Korean Neologisms Heesung Yang, Hyeyoung Park, Hyunji Lee, Hyunju Song Published: 2026-09-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-09-17 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E9 / R9 (90%) | - |
| PetriBench: Benchmarking LLM Reasoning over Dynamic State Spaces Ajay Sridhar, Benjamin J盲ger, Chenhao Li, John Hua Yao Published: 2026-09-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-17 | cs.CL | ai-safety, cscl, preprint | E12 / R11 (92%) | - |
| Reading Emotions in the Token Space: Discriminative Adaptation of SpeechLLMs for Emotion Recognition Andreas Stolcke, Esa煤 Villatoro-Tello, Hasindri Watawana, Kadri Hacioglu Published: 2026-09-17Area: cs.CLCitations: 33 Tags: ai-safety, cscl, preprint | 2026-09-17 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (95%) | 33 |
| RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning Aozhe Wang, Hua Yang, Qianglong Chen, Qipeng Chen Published: 2026-09-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-17 | cs.CL | ai-safety, cscl, preprint | E8 / R9 (94%) | - |
| Semantic Layer Induction from Raw Telemetry via Hierarchical LLM and RAG Abstraction Ali Anaissi, Yuanzhe Jia Published: 2026-09-17Area: cs.CLCitations: 14 Tags: ai-safety, cscl, preprint | 2026-09-17 | cs.CL | ai-safety, cscl, preprint | E11 / R10 (91%) | 14 |
| Stress-testing Alignment Midtraining Andrew Draganov, Daniel Tan, David Africa, Jonathan Bostock Published: 2026-09-17Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-09-17 | cs.CL | ai-safety, alignment-training, cscl, preprint | E10 / R5 (91%) | - |
| Xeno-Interpretability: Investigating the Alien Minds of LLMs F. Giarrusso, F. Pierucci, M. Bracale Syrnikov, M. Galisai Published: 2026-09-17Area: cs.CLCitations: - Tags: ai-safety, cscl, interpretability, preprint | 2026-09-17 | cs.CL | ai-safety, cscl, interpretability, preprint | E10 / R6 (90%) | - |
| Xeno-Interpretability: Investigating the Alien Minds of LLMs F. Giarrusso, F. Pierucci, M. Bracale Syrnikov, M. Galisai Published: 2026-09-17Area: cs.CLCitations: - Tags: ai-safety, cscl, interpretability, preprint | 2026-09-17 | cs.CL | ai-safety, cscl, interpretability, preprint | E10 / R6 (91%) | - |
| Zarya: A Hybrid Autoregressive--Masked Diffusion Language Model with Flexible Training and Dual-Mode Inference Ilya Koziev, Leonid Sinev, Vladislav Leshchuk Published: 2026-09-17Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-17 | cs.CL | ai-safety, cscl, preprint | E15 / R12 (92%) | 15 |
| A Scalable Framework for Automated NER Annotation Correction in Low-Resource Languages Thamar Solorio, Toqeer Ehsan Published: 2026-09-16Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-16 | cs.CL | ai-safety, cscl, preprint | E9 / R6 (96%) | - |
| A Zeroth-Order Paradigm for LLM Preference Alignment Peter Chen, Tianyi Lin, Wotao Yin, Xi Chen Published: 2026-09-16Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-09-16 | cs.CL | ai-safety, alignment-training, cscl, preprint | E16 / R11 (91%) | - |
| Beyond Accuracy: How Procedural Traces Shift the Decision Criterion of LLM Overseers Di Zhu, Lei Zheng, Weiling Li, Zihan Chen Published: 2026-09-16Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-16 | cs.CL | ai-safety, cscl, preprint | E12 / R6 (91%) | - |