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 |
|---|---|---|---|---|---|
| TCMQA: A 38K-Question Traditional Chinese Medicine Benchmark with a Licensed-Practitioner Reference Eric Lin, Jet Lin, Tzu-Heng Huang Published: 2026-09-26Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-26 | cs.CL | ai-safety, cscl, preprint | - | - |
| The Alignment Paradox: How Post-Training Amplifies Confident Hallucinations in Language Models Aimin Yu, Jianguo Wu, Luping Ma, Qihang Zhou Published: 2026-09-26Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-09-26 | cs.CL | ai-safety, alignment-training, cscl, preprint | - | - |
| TRAP: Understanding and Mitigating Privacy Memorization in Language Models Guannan Qu, Hanshen Xiao, Holger R. Roth, Muhammed Ustaomeroglu Published: 2026-09-26Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-26 | cs.CL | ai-safety, cscl, preprint | - | - |
| Typed Decision Models: An Early Evidence Audit and Evaluation Checklist Lijuan Tang, Yuemeng Zheng Published: 2026-09-26Area: cs.CLCitations: 86 Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-09-26 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E8 / R7 (92%) | 86 |
| When Users Change Their Minds: Measuring and Repairing Intent Drift in LLM Agents Bowen Cao, Yanjie Zhang, Yushi Sun, Zixin Chen Published: 2026-09-26Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-26 | cs.CL | ai-safety, cscl, preprint | - | - |
| Communication between Frozen Large Language Models via Prompt Optimization in a Referential Game Muthu Chandrasekaran, Shiva Chaitanya, Vivek Anand Published: 2026-09-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-25 | cs.CL | ai-safety, cscl, preprint | E9 / R10 (95%) | - |
| Estimating and Orthogonalizing Unknown Pre-training Gradients for Continual Fine-tuning of Large Language Models Bing Wang, Changchun Li, Gang Niu, Lin Yuanbo Wu Published: 2026-09-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-25 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (92%) | - |
| Evaluating Cultural Awareness of LLMs for Haitian Creole Christelle Clervilsson, Yanzhu Guo Published: 2026-09-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-25 | cs.CL | ai-safety, cscl, preprint | - | - |
| Extraction of clinical findings from mammography and breast ultrasound reports: a comparison between specialists and Artificial Intelligence Ana Laura Brill Thum, Ana Paula Wernz da Cunha M眉ller, Cristiane Drebes Pedron, Daniela Duarte da Silva Bagatini Published: 2026-09-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-25 | cs.CL | ai-safety, cscl, preprint | E14 / R9 (90%) | - |
| G$^2$PTQ: Improving LLM Post-Training Quantization with Generalized Gradient Compensation Feiyu Wang, Haoli Bai, Qian Zhang, Ruikang Liu Published: 2026-09-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-25 | cs.CL | ai-safety, cscl, preprint | E11 / R9 (91%) | - |
| Highlight-Then-Summarize: Learning to Compress Evidence for Long-Context Understanding Dai Dai, Gaofeng Lu, Jianguang Jiang, Long Zeng Published: 2026-09-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-25 | cs.CL | ai-safety, cscl, preprint | - | - |
| Improving Visual Sensitivity of LLMs on Multimodal Machine Translation with Metric-based Loss Weighting Gerasimos Spanakis, Jan Scholtes, Pawe艂 M膮ka, Piotr Andruszkiewicz Published: 2026-09-25Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-09-25 | cs.CL | ai-safety, cscl, preprint | E13 / R10 (96%) | 12 |
| MoSAR: Mixture of Semantic Attention Regimes for Learning Adaptive and Approximable Attention Geometries Alessandro Franceso Maria Martina, Alessandro Petruzzelli, Cataldo Musto, Giovanni Semeraro Published: 2026-09-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-25 | cs.CL | ai-safety, cscl, preprint | - | - |
| Persistent Negatives for Adversarial Black-Box On-Policy Distillation Abhishek Kumar, Dongzhuo Li, Gedi Zhou, Haixu Ma Published: 2026-09-25Area: cs.CLCitations: 15 Tags: adversarial-robustness, ai-safety, cscl, preprint | 2026-09-25 | cs.CL | adversarial-robustness, ai-safety, cscl, preprint | E8 / R6 (89%) | 15 |
| Regime Boundary Alignment for Evidence-Gated Question Answering Chun Li, Hu Xu, Jianfeng Xu, Qirong Guo Published: 2026-09-25Area: cs.CLCitations: 15 Tags: ai-safety, alignment-training, cscl, preprint | 2026-09-25 | cs.CL | ai-safety, alignment-training, cscl, preprint | E12 / R10 (94%) | 15 |
| Sorry Robot, Happy Human: Vision-Language Models Read Only One of Two Legible Typographic Layers Asya Berker, Mert 陌ncidelen, Murat Aydo臒an, Yamen Kashkash Published: 2026-09-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-25 | cs.CL | ai-safety, cscl, preprint | - | - |
| The Detectability Gap: Hidden Heterogeneity in Hallucination Detection Across Language Models Ivan P. Yamshchikov, Minal Moharir, Pranav A, Pranav Darshan Published: 2026-09-25Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-25 | cs.CL | ai-safety, cscl, preprint | E13 / R8 (90%) | 15 |
| ViSTA: A Simple Bridge Extends Visual Alignment to Clinical Time-Series Understanding in Multimodal LLMs Ewen M Harrison, Junyi Gao, Pingzhao Hu, Yu Shi Published: 2026-09-25Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-09-25 | cs.CL | ai-safety, alignment-training, cscl, preprint | - | - |
| Words Speak Louder Than Order: A Behavioral Evaluation of Gemma 4 Amanda Fitch Published: 2026-09-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-09-25 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E7 / R6 (93%) | - |
| agentic-ger: terminology recovery in long-form speech using global context Wupeng Wang, Xiangang Li, Xie Chen, Yanqiao Zhu Published: 2026-09-24Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-24 | cs.CL | ai-safety, cscl, preprint | E11 / R7 (91%) | 15 |
| An Empirical Study of VLM Pipelines for Long-Document QA Dimitrios Dimitriadis, Gwang Gook Lee, Jay Mohta, Kenan E. Ak Published: 2026-09-24Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-24 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (93%) | 15 |
| ArGuard Shared Task: Harmful Content Detection in Arabic Memes and LLM Prompts Abul Hasnat, Ali Ezzat Shahroor, Firoj Alam, George Mikros Published: 2026-09-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-24 | cs.CL | ai-safety, cscl, preprint | E16 / R13 (92%) | - |
| ArGuard Shared Task: Harmful Content Detection in Arabic Memes and LLM Prompts Abul Hasnat, Ali Ezzat Shahroor, Firoj Alam, George Mikros Published: 2026-09-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-24 | cs.CL | ai-safety, cscl, preprint | E16 / R13 (96%) | - |
| A Unified Account of Concepts and Chunks Karthik Singaravadivelan, Pat Langley Published: 2026-09-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-24 | cs.CL | ai-safety, cscl, preprint | E9 / R7 (94%) | - |
| Automated Regulatory Compliance Question Answering in Financial Services with Domain-Adapted Retrieval-Augmented Generation Abhishek Pillai, Aurelio F. Bariviera, Christian Bauckhage, David Berghaus Published: 2026-09-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-24 | cs.CL | ai-safety, cscl, preprint | E10 / R10 (91%) | - |
| Benchmarking and Domain Adaptation of Automatic Speech Recognition (ASR) for Adolescent Health Communication in Ghanaian Languages Akwasi Asare, Joel Budu, Lawrence A. Adu-Gyamfi, Mich-Seth Owusu Published: 2026-09-24Area: cs.CLCitations: 32 Tags: ai-safety, cscl, preprint | 2026-09-24 | cs.CL | ai-safety, cscl, preprint | E12 / R8 (95%) | 32 |
| Breaking Homogeneity: Diversifying Persona Sets for Creative LLM Outputs Abolfazl Hashemi, Daniel Borrajo, Nicole Cho, Sang Bin Moon Published: 2026-09-24Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-09-24 | cs.CL | ai-safety, cscl, preprint | E17 / R11 (96%) | 12 |
| Can Classical Semantic-Extractive Summarization Be Evaluated in Hindi? A Replication Study Abid Hussain Wani, Hilal Ahmad Khanday, Mohsin Altaf Wani, Mudasir Mohd Published: 2026-09-24Area: cs.CLCitations: 8 Tags: ai-safety, cscl, preprint | 2026-09-24 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (95%) | 8 |
| CARGO: Context-Aware Retrieval-Gated Evaluation of Agentic AI in Production Luigi Medrano, Mukul Chhabra, Shail Patel Published: 2026-09-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-09-24 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E8 / R5 (92%) | - |
| Cultural Divergence Preservation: Diagnosing Flattening and Caricature in LLM-Simulated Survey Populations IL Im, Seunghyun Lee, Yeeun Chae, Yewon Choi Published: 2026-09-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-24 | cs.CL | ai-safety, cscl, preprint | E13 / R11 (90%) | - |