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 |
|---|---|---|---|---|---|
| What Eviction Destroys: A Restore-Counterfactual Audit of Forgetting in Agent Memory Chen Shen Published: 2026-09-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-08 | cs.CL | ai-safety, cscl, preprint | E12 / R13 (94%) | - |
| Aha-Flow Distillation: Flow Markers Matter in LLM Reasoning Peixi Peng, Xiaodong Wang Published: 2026-09-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-07 | cs.CL | ai-safety, cscl, preprint | E11 / R8 (94%) | - |
| A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM Chaojun Xiao, Fanyu Meng, Huijia Wu, Jixun Wang Published: 2026-09-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-07 | cs.CL | ai-safety, cscl, preprint | E12 / R10 (92%) | - |
| Bag of Tricks or Bag of Myths? Reducing Modeling Complexity with Task Knowledge in Explainable Suicide Risk Assessment Amit Sheth, Manas Gaur, Shlok Shelat, Shrey Salvi Published: 2026-09-07Area: cs.CLCitations: 53 Tags: ai-safety, cscl, preprint | 2026-09-07 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (91%) | 53 |
| Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking Adam Jatowt, Ahmed Hamdi, Antoine Doucet, Emanuela Boros Published: 2026-09-07Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-07 | cs.CL | ai-safety, cscl, preprint | E9 / R7 (92%) | 15 |
| Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking Adam Jatowt, Ahmed Hamdi, Antoine Doucet, Emanuela Boros Published: 2026-09-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-07 | cs.CL | ai-safety, cscl, preprint | E8 / R7 (93%) | - |
| BlueprintAgent: Constraint-Triggered Targeted Revisits for Simulation-Ready Generation from Scanned Structural Blueprints Chen Wang, Chen Yang, Jiansheng Fan, Linhao Wang Published: 2026-09-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-07 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (93%) | - |
| Climate-ModernBERT: Revisiting Corpus Composition for Domain-Adaptive Continued Pretraining Ario Saeid Vaghefi, Dominik Stammbach, Jingwei Ni, Markus Leippold Published: 2026-09-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-07 | cs.CL | ai-safety, cscl, preprint | E9 / R7 (91%) | - |
| Fine PT-PT Web: A High-Quality 41 Billion Tokens Data Collection of the European Portuguese Web Afonso Simpl铆cio, Daniel Gomes, David Semedo, Diogo Tavares Published: 2026-09-07Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-07 | cs.CL | ai-safety, cscl, preprint | E13 / R10 (94%) | 15 |
| Fine PT-PT Web: A High-Quality 41 Billion Tokens Data Collection of the European Portuguese Web Afonso Simpl铆cio, Daniel Gomes, David Semedo, Diogo Tavares Published: 2026-09-07Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-07 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (93%) | 15 |
| FreqBLiMP: Frequency-Controlled Minimal Pairs Reveal Robustness and Fragility of LLMs Under Lexical Rarity Tyrone White, Yuki Arase Published: 2026-09-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-07 | cs.CL | ai-safety, cscl, preprint | E9 / R10 (94%) | - |
| How AI Models Manage Epistemic Authority: A Taxonomy and Comparative Analysis of Responses to User Disagreement Riyadh Alnasser, Sumin Zhao, Tu臒rulcan Elmas, Yusuf M眉cahit 脟etinkaya Published: 2026-09-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-07 | cs.CL | ai-safety, cscl, preprint | E8 / R8 (94%) | - |
| In-Place Instruction Following in Diffusion Language Models Jiaming Zhang, Kun Wang, Yufei Guo, Zheng Nie Published: 2026-09-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-07 | cs.CL | ai-safety, cscl, preprint | E9 / R7 (94%) | - |
| LANTERN: Language Model Assessment on Noisy and Transformed Tasks for Understanding Error and Robustness Nuances Rituraj Singh, Vamsi Krishna Kodavali Published: 2026-09-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-07 | cs.CL | ai-safety, cscl, preprint | E12 / R10 (92%) | - |
| ObGynLongBench: Revealing the Evidence-to-EHR Gap in Longitudinal EHR Decision-Making Jun Xiang, Kaizhou Qin, Rong Hu, Wei Chen Published: 2026-09-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-07 | cs.CL | ai-safety, cscl, preprint | E12 / R10 (91%) | - |
| Rethinking Sign Language Translation: The Impact of Signer Dependence on Model Evaluation Conor Lynch, Haithem Afli, Keren Artiaga, Mohammed Hasanuzzaman Published: 2026-09-07Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-09-07 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E10 / R8 (94%) | 12 |
| Train Overcomplete, Deploy Compact: Scaling Recovery Capacity for Structured LLM Pruning Donggeon Lee, Jongbin Ryu, Seungmin Oh Published: 2026-09-07Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-07 | cs.CL | ai-safety, cscl, preprint | E8 / R7 (93%) | 15 |
| We're Cooked! - Probing LLM Political Alignment Via Conflict-Framed Recipe Translation Angelica Henestrosa, Ivan P. Yamshchikov, Svetlana Gorovaia Published: 2026-09-07Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-09-07 | cs.CL | ai-safety, alignment-training, cscl, preprint | E12 / R8 (95%) | - |
| You Can't Prefer Emotions You Don't Sample: Intensity Undershoot in DPO-Tuned LLMs Hyunwoo Kim, Usama Khalid Published: 2026-09-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-07 | cs.CL | ai-safety, cscl, preprint | E9 / R6 (94%) | - |
| AuthBench: A Large-Scale Multilingual Benchmark for Authorship Representation across Genres and Lengths Claire Cardie, MaoXun Huang, Zhenxing Zhang Published: 2026-09-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-06 | cs.CL | ai-safety, cscl, preprint | E12 / R11 (92%) | - |
| AutoLexSteer: Automatic Contrast Construction for Lexical Activation Steering Eduard Hovy, Jey Han Lau, Lachlan Cowley, Shuhe Wang Published: 2026-09-06Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-06 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (91%) | 15 |
| Discovering Translation-Worthy Languages with E-Values Safa Madiouni, Wajdi Ben Saad Published: 2026-09-06Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-09-06 | cs.CL | ai-safety, cscl, preprint | E11 / R10 (94%) | 12 |
| ECOKV: Geometry-Aware KV Cache Eviction via Complementary Diversity Metrics Chin Ting Hsu, Hsien-Kai Kuo, Ling Zou, Wen-Huang Cheng Published: 2026-09-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-06 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (89%) | - |
| Event Interaction in Low-Rank Bottlenecks for Temporal Relation Extraction Jesse Davis, Marie-Francine Moens, Tingyu Qu, Wei Sun Published: 2026-09-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-06 | cs.CL | ai-safety, cscl, preprint | E13 / R10 (92%) | - |
| Mind the Gap: Exposing LLM Translation Blind Spots Using the AlphaMWE Multilingual Parallel Corpus Amal Haddad Haddad, Anna Latusek, Jiahui Liang, Josua H枚fgen Published: 2026-09-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-06 | cs.CL | ai-safety, cscl, preprint | E19 / R14 (94%) | - |
| ProcArena: A Multi-Scenario Benchmark for LLMs on Direct and Interactive PL/SQL Development from Natural Language Bofan Xie, Chaokun Wang, Fang Niu, Guanchen Ge Published: 2026-09-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-06 | cs.CL | ai-safety, cscl, preprint | E10 / R12 (91%) | - |
| SAGE: A Hierarchical Framework for Evaluating Interpretive Literary Quality in Narratives Nianjun Zhou, Tianyu Wang Published: 2026-09-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-06 | cs.CL | ai-safety, cscl, preprint | E12 / R10 (92%) | - |
| Typed Federated Artifacts for the Agentic Web:Sharing Tool-Routing Knowledge Across Frozen,Heterogeneous LLM Agents Abhijit Chakraborty, Ni Trieu, Vivek Gupta Published: 2026-09-06Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-09-06 | cs.CL | ai-safety, cscl, preprint | E8 / R7 (94%) | 12 |
| XYBench: Can LLMs Respond Pragmatically to Queries with Misconceptions? Akhila Yerukola, Hyunwoo Kim, Jena D. Hwang, Jenna Godsey Published: 2026-09-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-06 | cs.CL | ai-safety, cscl, preprint | E9 / R7 (94%) | - |
| You Are What You Read: Misalignment via In-Context Persona Induction Benjamin Berczi, Cozmin Ududec, Kyuhee Kim Published: 2026-09-06Area: cs.CLCitations: 15 Tags: ai-safety, alignment-training, cscl, preprint | 2026-09-06 | cs.CL | ai-safety, alignment-training, cscl, preprint | E9 / R6 (94%) | 15 |