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 |
|---|---|---|---|---|---|
| Leveraging Computerized Adaptive Testing for Cost-effective Evaluation of Large Language Models in Medical Benchmarking Jiayi Liu, Shicong Feng, Tianpeng Zheng, Zhehan Jiang Published: 2026-02-28Area: cs.CLCitations: 33 Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-02-28 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E15 / R14 (93%) | 33 |
| Rubric-Guided Fine-tuning of SpeechLLMs for Multi-Aspect, Multi-Rater L2 Reading-Speech Assessment Aditya Kamlesh Parikh, Catia Cucchiarini, Cristian Tejedor-Garcia, Helmer Strik Published: 2026-02-28Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-02-28 | cs.CL | ai-safety, cscl, preprint | E9 / R7 (93%) | 15 |
| SSKG Hub: An Expert-Guided Platform for LLM-Empowered Sustainability Standards Knowledge Graphs Chaoyue He, Chunyan Miao, Di Wang, Hong Xu Published: 2026-02-28Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-28 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (90%) | - |
| CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning Olli Saarikivi, Pingzhi Li, Xianzhi Du, Xinyu Zhu Published: 2026-03-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-01 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (91%) | - |
| Conformal Prediction for Risk-Controlled Medical Entity Extraction Across Clinical Domains Edward Kim, Manil Shrestha Published: 2026-03-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-01 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (95%) | - |
| Enhancing Safety of Large Language Models via Embedding Space Separation Weiran Shen, Xiting Wang, Xu Zhao Published: 2026-03-01Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-03-01 | cs.CL | ai-safety, cscl, preprint | E12 / R11 (90%) | 15 |
| From Feature-Based Models to Generative AI: Validity Evidence for Constructed Response Scoring Daniel F. McCaffrey, Jodi M. Casabianca, Matthew S. Johnson, Naim Alper Published: 2026-03-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-01 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (93%) | - |
| HypeLoRA: Hyper-Network-Generated LoRA Adapters for Calibrated Language Model Fine-Tuning Bartosz Trojan, Filip G臋bala Published: 2026-03-01Area: cs.CLCitations: 26 Tags: ai-safety, cscl, preprint | 2026-03-01 | cs.CL | ai-safety, cscl, preprint | E22 / R16 (94%) | 26 |
| Linking Knowledge to Care: Knowledge Graph-Augmented Medical Follow-Up Question Generation Anqi Cheng, Ashutosh Joshi, Chenyan Xiong, Liwen Sun Published: 2026-03-01Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-03-01 | cs.CL | ai-safety, cscl, preprint | E9 / R7 (94%) | 45 |
| LLM Self-Explanations Fail Semantic Invariance Stefan Szeider Published: 2026-03-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-01 | cs.CL | ai-safety, cscl, preprint | E11 / R10 (91%) | - |
| Prompt Sensitivity and Answer Consistency of Small Open-Source Language Models for Clinical Question Answering in Low-Resource Healthcare Shravani Hariprasad Published: 2026-03-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-01 | cs.CL | ai-safety, cscl, preprint | E13 / R8 (94%) | - |
| Self-Anchoring Calibration Drift in Large Language Models: How Multi-Turn Conversations Reshape Model Confidence Harshavardhan Published: 2026-03-01Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-03-01 | cs.CL | ai-safety, cscl, preprint | E12 / R11 (93%) | 12 |
| Spectral Attention Steering for Prompt Highlighting Keshuang Li, Shay B. Cohen, Tiejun Ma, Weixian Waylon Li Published: 2026-03-01Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-03-01 | cs.CL | ai-safety, cscl, preprint | E8 / R7 (92%) | 15 |
| Thoth: Mid-Training Bridges LLMs to Time Series Understanding Huakun Luo, Jiafeng Lin, Jialong Wu, Jianmin Wang Published: 2026-03-01Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-03-01 | cs.CL | ai-safety, cscl, preprint | E13 / R18 (89%) | 15 |
| Token-level Data Selection for Safe LLM Fine-tuning Jun Zhang, Yanping Li, Zehong Lin, Zhening Liu Published: 2026-03-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-01 | cs.CL | ai-safety, cscl, preprint | E13 / R13 (92%) | - |
| Abductive Reasoning with Syllogistic Forms in Large Language Models Hirohiko Abe, Koji Mineshima, Mitsuhiro Okada, Risako Ando Published: 2026-03-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-06 | cs.CL | ai-safety, cscl, preprint | E7 / R3 (95%) | - |
| A Causal Graph Approach to Oppositional Narrative Analysis Aritz Bilbao-Jayo, Diego Revilla, Lingfeng Chen, Martin Fernandez-de-Retana Published: 2026-03-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-06 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| CRIMSON: A Clinically-Grounded LLM-Based Metric for Generative Radiology Report Evaluation Hassan AlOmaish, Mahmoud Alabbad, Mohammed Baharoon, Mona Alhammad Published: 2026-03-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-03-06 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E5 / R3 (94%) | - |
| "Dark Triad" Model Organisms of Misalignment: Narrow Fine-Tuning Mirrors Human Antisocial Behavior Fiona Collins, Jonas Kaplan, Roshni Lulla, Sanaya Parekh Published: 2026-03-06Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-03-06 | cs.CL | ai-safety, alignment-training, cscl, preprint | E5 / R4 (95%) | - |
| Evaluating Austrian A-Level German Essays with Large Language Models for Automated Essay Scoring Clemens Havas, Jonas Kubesch, Lena Huber Published: 2026-03-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-06 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (94%) | - |
| Experiences Build Characters: The Linguistic Origins and Functional Impact of LLM Personality Jiqun Liu, Mengdie Zhuang, Xi Wang Published: 2026-03-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-06 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (94%) | - |
| FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling Bingning Wang, Huaibo Huang, Juqiu Wang, Qihang Fan Published: 2026-03-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-06 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| Making Implicit Premises Explicit in Logical Understanding of Enthymemes Anthony Hunter, Xuyao Feng Published: 2026-03-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-06 | cs.CL | ai-safety, cscl, preprint | E6 / R4 (95%) | - |
| MAPO: Mixed Advantage Policy Optimization for Long-Horizon Multi-Turn Dialogue Hengjie Yang, Jinwei Su, Naifan Zhang, Ruihan Sun Published: 2026-03-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-06 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (98%) | - |
| MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing Cheng Yang, Chen Qian, Chuan Shi, Jinxuan Cai Published: 2026-03-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-06 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (95%) | - |
| PONTE: Personalized Orchestration for Natural Language Trustworthy Explanations Filippo Betello, Gabriele Tolomei, Lorenzo Antonelli, Matteo Silvestri Published: 2026-03-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-06 | cs.CL | ai-safety, cscl, preprint | E6 / R4 (96%) | - |
| A Systematic Investigation of Document Chunking Strategies and Embedding Sensitivity Carlos C. N. Kuhn, Muhammad Arslan Shaukat, Muntasir Adnan Published: 2026-03-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-07 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| Can Safety Emerge from Weak Supervision? A Systematic Analysis of Small Language Models Debjyoti Mondal, Punyajoy Saha, Subhadarshi Panda, Sudipta Halder Published: 2026-03-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-07 | cs.CL | ai-safety, cscl, preprint | E7 / R3 (96%) | - |
| Domain-Specific Quality Estimation for Machine Translation in Low-Resource Scenarios Akashdeep Ranu, Archchana Sindhujan, Diptesh Kanojia, Namrata Patil Gurav Published: 2026-03-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-07 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (97%) | - |
| Elenchus: Generating Knowledge Bases from Prover-Skeptic Dialogues Bradley P. Allen Published: 2026-03-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-03-07 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (97%) | - |