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 |
|---|---|---|---|---|---|
| text2ql: Multi-Target Natural Language Querying via a Language-Agnostic Intermediate Representation Ritesh Kumar Published: 2026-09-02Area: cs.CLCitations: 19 Tags: ai-safety, cscl, preprint | 2026-09-02 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (92%) | 19 |
| Untangling the Mechanisms of Misleading Context in Medical Question Answering No茅mie Elhadad, Robin Linzmayer Published: 2026-09-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-02 | cs.CL | ai-safety, cscl, preprint | E9 / R6 (90%) | - |
| Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling Chen Zhi, Hang Song, Haozhan Shen, Jiajun Li Published: 2026-09-01Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E15 / R9 (94%) | 15 |
| CHARM: Character Hallucination for Multicultural Role Play Benchmark Gaeun Seo, JinYeong Bak, Nahyeon Park, Seunghyun Yoon Published: 2026-09-01Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E15 / R9 (93%) | 15 |
| Context-Grounding Gains Are Mediated by Pre-existing Machinery: Auditing GRPO, SFT, and DPO Prakhar Gupta, Vaibhav Gupta Published: 2026-09-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E8 / R7 (90%) | - |
| CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses? Damien Sileo, Dimitri Kachler Published: 2026-09-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E7 / R8 (94%) | - |
| Disclosure-Gated User Simulation for Companion-Agent Evaluation Yao Liu, Yu He Published: 2026-09-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-09-01 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E6 / R5 (93%) | - |
| DualStake: Dual-Path Confidence Calibration in Deep Research Agents Jianjie Cheng, Jian Liang, Meng Wang, Shuo Lu Published: 2026-09-01Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E22 / R14 (91%) | 15 |
| EDRAC: Benchmarking Arabic Dialect Reading Comprehension Abed Alhakim Freihat, Alham Fikri Aji, Besher Hassan, Hamad Alshehhi Published: 2026-09-01Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E13 / R13 (93%) | 12 |
| EM^2Mem: Event-Centric Multimodal Memory for Large Language Models Boyi Xiao, Buqiang Xu, Huajun Chen, Hui Li Published: 2026-09-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E8 / R8 (93%) | - |
| From Confusion to Clarity: Confusion-Aware Retrieval and Knowledge Injection for Text Classification Chaitanya Giri, Jayasimha Talur, Manish Gupta Published: 2026-09-01Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E11 / R9 (93%) | 15 |
| GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactions Carlos Bonetti, Elias Stengel-Eskin, Hale Sirin, James Bowler Published: 2026-09-01Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E11 / R10 (93%) | 45 |
| Inspicio: Open-Vocabulary, LLM-Based Sense Retrieval for Historical Languages Michele Ciletti Published: 2026-09-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E11 / R10 (92%) | - |
| Instella-MoE Technical Report Chaojun Hou, Emad Barsoum, Gowtham Ramesh, Jialian Wu Published: 2026-09-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E11 / R10 (91%) | - |
| Interpretable Symptom Vectors for Depression in a Large Language Model Ajay Subramanian, Allison Constant, Camille Wang, Corey J. Keller Published: 2026-09-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E13 / R10 (95%) | - |
| Lagged Coupling: Internal Representations Become Readable Before They Become Causal Xining Xun Published: 2026-09-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E10 / R6 (94%) | - |
| Probing Factual Knowledge Transfer with Training Data Interventions Jenny Kunz, Marc Braun, Marcel Bollmann, Marco Kuhlmann Published: 2026-09-01Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E14 / R10 (92%) | 15 |
| Right Frame, Wrong Rule: Cultural Cues Expose the Financial Knowledge Gap They Were Meant to Close Ahmed Heakl, Duzhen Zhang, Fajri Koto, Fan Zhang Published: 2026-09-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E9 / R5 (93%) | - |
| Scaling Near-Optimal SFT-RL Annotation Budget Allocation from Small to Large LLMs Arun Verma, Bryan Kian Hsiang Low, Daniela Rus, Jingtan Wang Published: 2026-09-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (94%) | - |
| Some Emotions Run Deeper: Layer-wise Probing and Causal Intervention in Large Language Models Davide Buscaldi, Ga毛l Guibon, Tian Fang Published: 2026-09-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E13 / R7 (91%) | - |
| Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens Matteo He, Nicholas D. Lane, William F. Shen, Xinchi Qiu Published: 2026-09-01Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (92%) | 12 |
| StateSwap: Probing Support-Elimination Hidden States in Multiple-Choice Questions Caicai Guo, Chao Gao, Frank van Harmelen, Haijiang Liu Published: 2026-09-01Area: cs.CLCitations: 25 Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (95%) | 25 |
| The Interlingua Hypothesis: LLMs Translate via a Latent Task-agnostic Feature Space Aaron Mueller, Jacob Brinton, Jannik Brinkmann, Mark Crovella Published: 2026-09-01Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (91%) | 12 |
| The Rise of Verbal Reinforcement Learning Anirban Das, Arun Sharma, Genta Indra Winata, Kshitij Tayal Published: 2026-09-01Area: cs.CLCitations: 150 Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E103 / R39 (91%) | 150 |
| Thinking effort aligns between humans and reasoning models in abductive reasoning Henry Arthur Published: 2026-09-01Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E10 / R5 (93%) | 45 |
| Towards AI-Assisted Clinical Trial Matching: Practical Considerations, Multicenter Evaluation, and Real-World Deployment Amanda Nottke, Catarina Martins Maia, Charalampos S. Floudas, Craig E. Grossman Published: 2026-09-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-09-01 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E8 / R6 (90%) | - |
| VakyArth: Evaluating Pragmatic Competence in LLMs across Indic Languages Anand Madhusoodanan, Geyang Guo, Junyi Jessy L, Parth Nanda Published: 2026-09-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E19 / R16 (96%) | - |
| Visual Framing for News Stance Detection via Image Generation Dahyun Lee, Jiyoung Han, Kunwoo Park Published: 2026-09-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E9 / R8 (92%) | - |
| An Agentic Retrobiosynthesis Framework with Learned Frontier Selection Guillaume Gricourt, Jean-Loup Faulon, Joan H茅risson, Philippe Meyer Published: 2026-08-31Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-31 | cs.CL | ai-safety, cscl, preprint | - | - |
| Assessing Suicide Risk in Arabic Crisis Helpline Calls: A Comparison of Arabic and English Large Language Models Lilian Ghandour, Linhai Ma, Mahatab El Hajj, Rita El Hachem Published: 2026-08-31Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-31 | cs.CL | ai-safety, cscl, preprint | E18 / R15 (93%) | - |