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 |
|---|---|---|---|---|---|
| Accuracy and Order Sensitivity Diverge Under Label-Free Strategies Chen Feng, Karl Hanna Published: 2026-08-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-12 | cs.CL | ai-safety, cscl, preprint | - | - |
| A corpus-specific clinical RAG system matches or outperforms newer frontier LLMs on HealthBench Charuta Mandke, Praveen Reddy, Sarah Khan, Shitij Arora Published: 2026-08-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-12 | cs.CL | ai-safety, cscl, preprint | - | - |
| Beyond Single-Turn Confidence: Trajectory-Adapted Uncertainty Quantification for LLM Agents Dylan Bouchard, Mohit Singh Chauhan Published: 2026-08-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-12 | cs.CL | ai-safety, cscl, preprint | - | - |
| GRPO for Financial Advice Generation: Outperforming Commercial LLMs under CATE Evaluation Oded Vainas, Ofir Ben Shoham, Shravan Mohan, Shrutendra Harsola Published: 2026-08-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-08-12 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | - | - |
| Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing Haoyu Wang, Jing Gao, Linjun Zhang, Qiming Cao Published: 2026-08-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-12 | cs.CL | ai-safety, cscl, preprint | - | - |
| Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge Arda Uzunoglu, Benjamin van Durme, Daniel Khashabi Published: 2026-08-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-12 | cs.CL | ai-safety, cscl, preprint | - | - |
| Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge Arda Uzunoglu, Benjamin Van Durme, Daniel Khashabi Published: 2026-08-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-12 | cs.CL | ai-safety, cscl, preprint | E11 / R8 (86%) | - |
| Learning to Persuade Exposes How Easily LLMs Abandon Correct Beliefs Dilek Hakkani-T眉r, Emre Can Acikgoz, Gokhan Tur, Nimet Beyza Bozdag Published: 2026-08-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-12 | cs.CL | ai-safety, cscl, preprint | - | - |
| LLMs Are Not Good Strategists, Yet Memory-Enhanced Agency Boosts Reasoning Yi Wu, Zhimin Hu Published: 2026-08-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-12 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (92%) | - |
| Locating and Controlling Implicit Personalization in Large Language Models Siqi Wu, Thai Le, Yueru Yan Published: 2026-08-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-12 | cs.CL | ai-safety, cscl, preprint | - | - |
| Novels generated by language models show compressed formal variation Justin Quinn, Mehdy Sedaghat Payam Published: 2026-08-12Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-12 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (91%) | 15 |
| One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Abe Hou, Christopher D. Manning, Derek Chong, Dilara Soylu Published: 2026-08-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-12 | cs.CL | ai-safety, cscl, preprint | - | - |
| One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Abe Hou, Christopher D. Manning, Derek Chong, Dilara Soylu Published: 2026-08-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-12 | cs.CL | ai-safety, cscl, preprint | E9 / R7 (95%) | - |
| Preference Tree Optimization: Enhancing Goal-Oriented Dialogue with Look-Ahead Simulations Doron Friedman, Kfir Bar, Lior Baruch, Moshe Butman Published: 2026-08-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-12 | cs.CL | ai-safety, cscl, preprint | - | - |
| QV-PIC: Query-Aware Visual Position-Independent Caching for Efficient RAG Serving Heng Cao, Jianxin Yan, Jinfei Liu, Libin Zheng Published: 2026-08-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-12 | cs.CL | ai-safety, cscl, preprint | - | - |
| Reinforcing Step-level Reasoning for Effective Self-Correction in LLMs Cong-Duy Nguyen, Do Xuan Long, Luu Anh Tuan, Nhat M. Hoang Published: 2026-08-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-12 | cs.CL | ai-safety, cscl, preprint | - | - |
| Semantic Lenia: Emergence of Homeostatic Solitons within the Semantic Space of Large Language Models Yoshihiko Kayama Published: 2026-08-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-12 | cs.CL | ai-safety, cscl, preprint | - | - |
| Semantic Lenia: Emergence of Homeostatic Solitons within the Semantic Space of Large Language Models Yoshihiko Kayama Published: 2026-08-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-12 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (93%) | - |
| Structural Silence: When AI Infrastructure Fails Speakers of Underrepresented Languages Avijit Roy, Proma Roy Published: 2026-08-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-12 | cs.CL | ai-safety, cscl, preprint | - | - |
| TELLME: Test-Enhanced Learning for Language Model Enrichment Hyeonseok Lim, Inho Won, Jongyoul Park, Junghun Yuk Published: 2026-08-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-12 | cs.CL | ai-safety, cscl, preprint | - | - |
| The Wording Effect: Quantifying Two-Way Drift in LLM Benchmark Performance Chad DeLuca, Hima Patel, Shailja Thakur, Sungeun An Published: 2026-08-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-12 | cs.CL | ai-safety, cscl, preprint | - | - |
| When the API Speaks the Wrong Language: Revisiting Post-Training for Multilingual Tool Use Abhishek Singhania, Honey Gupta, Pankaj Porwal, Siddharth Chauhan Published: 2026-08-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-12 | cs.CL | ai-safety, cscl, preprint | - | - |
| A Cost-Efficient Routing Pipeline for Multilingual Short-Text Classification Using Small Language Models Safa Madiouni, Wajdi Ben Saad Published: 2026-08-11Area: cs.CLCitations: 18 Tags: ai-safety, cscl, preprint | 2026-08-11 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (93%) | 18 |
| Attention-Path Fragility as an Uncertainty Signal in Large Language Models Ilyong Yoon, Kisung Moon, Minsoo Kim, Sungyoung Ji Published: 2026-08-11Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-11 | cs.CL | ai-safety, cscl, preprint | E11 / R8 (93%) | - |
| Auditing Chinese Web-scale Corpora via Sampled BPE Token Statistics Gelei Deng, Han Qiu, Hui Xue, Jie Zhang Published: 2026-08-11Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-11 | cs.CL | ai-safety, cscl, preprint | E25 / R18 (92%) | 15 |
| ConVAWG: A Retrieval-Grounded Framework for Controlled Synthetic Dialogue Generation in Violence Against Women and Girls Arshad Jhumka, Chen Lyu, Gabriele Pergola, Lois Arthurs Published: 2026-08-11Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-11 | cs.CL | ai-safety, cscl, preprint | - | - |
| FaithformBench: Benchmarking Faithfulness of Mathematical Chain-of-Thought Autoformalisation Dominik Wagner, Haoxuan Yin, Iacopo Ghinassi, Luke Ong Published: 2026-08-11Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-11 | cs.CL | ai-safety, cscl, preprint | E22 / R19 (91%) | 15 |
| From Interpretability to Control: Insights from Six Years of the TrustNLP Workshop Abhinav Mohanty, Anaelia Ovalle, Anil Ramakrishna, Anubrata Das Published: 2026-08-11Area: cs.CLCitations: - Tags: ai-safety, cscl, interpretability, preprint | 2026-08-11 | cs.CL | ai-safety, cscl, interpretability, preprint | E12 / R9 (91%) | - |
| From Reasoning Depth to Reasoning Breadth: Evaluating Multi-Point Associative Reasoning in Large Language Models Biao Yang, Fan Yang, Jiaxun Liu, Ming Wu Published: 2026-08-11Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-11 | cs.CL | ai-safety, cscl, preprint | E13 / R10 (90%) | - |
| MD-ProTector: Positioning Multiple Data-Driven Prototypes for LLM-Generated Text Detection Chanyeong Moon, Jimin Hong, Jinmo Han, Ju Yeon Kang Published: 2026-08-11Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-11 | cs.CL | ai-safety, cscl, preprint | E10 / R6 (91%) | - |