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 |
|---|---|---|---|---|---|
| From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents Hongyu Lin, Le Sun, Xianpei Han, Yaojie Lu Published: 2026-08-17Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-17 | cs.CL | ai-safety, cscl, preprint | E12 / R10 (91%) | 15 |
| From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents Boxi Cao, Hongyu Lin, Le Sun, Xianpei Han Published: 2026-08-17Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-17 | cs.CL | ai-safety, cscl, preprint | E12 / R9 (90%) | 15 |
| HalluTracer: Hallucination Detection via Depth-Averaging Truth Signals DaYong Ye, Huan Huo, Junwei Zhang, Qingsong Wen Published: 2026-08-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-17 | cs.CL | ai-safety, cscl, preprint | E9 / R6 (89%) | - |
| Institution-Specific LLM Prompting Recovers PHI That De-identification Systems and Their Gold Standards Both Miss Angel Adetomike Otto, Chi-fan Lin, Daniel Palacios, Hyun-Hwan Jeong Published: 2026-08-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-17 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (93%) | - |
| LENS: In-Context Search via Latent Evidence Exploration over Dynamic Raw Documents Gongsheng Li, Luyan Su, Qi Fan, Xingjun Wang Published: 2026-08-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-17 | cs.CL | ai-safety, cscl, preprint | E6 / R5 (95%) | - |
| LENS: In-Context Search via Latent Evidence Exploration over Dynamic Raw Documents Gongsheng Li, Luyan Su, Qi Fan, Xingjun Wang Published: 2026-08-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-17 | cs.CL | ai-safety, cscl, preprint | E6 / R5 (91%) | - |
| Model Hypnosis: Strong control of AI via additive subliminal effects Benedict Tessler, Enric Boix-Adsera Published: 2026-08-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-17 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (91%) | - |
| Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning Arjun Krishna, Daniel M. Bikel, Kiran Kamble, Peng Du Published: 2026-08-17Area: cs.CLCitations: 21 Tags: ai-safety, cscl, preprint | 2026-08-17 | cs.CL | ai-safety, cscl, preprint | E13 / R10 (92%) | 21 |
| Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning Arjun Krishna, Daniel M. Bikel, Kiran Kamble, Peng Du Published: 2026-08-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-17 | cs.CL | ai-safety, cscl, preprint | E14 / R10 (93%) | - |
| QUMem: Personalized Memory for Query-Conditioned User-State Inference in LLM Agents Heng Wang, Lingling Zhang, Pengyu Li, Xinyu Che Published: 2026-08-17Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-17 | cs.CL | ai-safety, cscl, preprint | E13 / R11 (91%) | 15 |
| Semantic Bandits: In-Context Exploration-Exploitation is Biased by Semantic Priors David Eric Austin, Jackie Chi Kit Cheung, Kaheer Suleman Published: 2026-08-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-17 | cs.CL | ai-safety, cscl, preprint | E11 / R10 (94%) | - |
| STAIR: Semantic-Temporal Automaton for Interpretable Reasoning in Temporal Question Answering Hui Gao, Jinchuan Zhang, Lei Gao, Xinlong Dai Published: 2026-08-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-17 | cs.CL | ai-safety, cscl, preprint | E8 / R7 (94%) | - |
| Step-Level On-Policy Distillation: Interpolating Between On-Policy Distillation and Supervised Fine-Tuning Changhui Sun, Feng Xiao, Hang Lei, Hao Liu Published: 2026-08-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-17 | cs.CL | ai-safety, cscl, preprint | E7 / R6 (92%) | - |
| Token Optimization and Context Window Management in Multi-Agent AI Workflows Dvir Shamay Published: 2026-08-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-17 | cs.CL | ai-safety, cscl, preprint | E15 / R12 (93%) | - |
| Toward Better Assessment of LLMs' Performance in Clinical Error Detection Rahmatollah Beheshti, Yifan Zhang Published: 2026-08-17Area: cs.CLCitations: 1 Tags: ai-safety, cscl, preprint | 2026-08-17 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (96%) | 1 |
| Towards Computational Provenance: Carrying Causal-State Evidence in Generated Text Benjamin Belay Published: 2026-08-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-17 | cs.CL | ai-safety, cscl, preprint | E7 / R9 (94%) | - |
| When Context Misleads: Intent-Guided Decoding for Robust Retrieval-Augmented Generation Haolin Jin, Huaming Chen, Pengyue Yang Published: 2026-08-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-17 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (93%) | - |
| When Do Explanations Help In-Context Learning? A Comparative Study of Natural Language Explanation Types and Faithfulness Adam Dejl, Barbara Plank, Gjergji Kasneci, Juraj Vladika Published: 2026-08-17Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-08-17 | cs.CL | ai-safety, cscl, preprint | E12 / R11 (96%) | 12 |
| A Cognitively Motivated Multidimensional Framework for Evaluating Metaphor Explanations Ana Naveriani, Antonio Lieto, Gian Luca Pozzato, Jakob Suchan Published: 2026-08-16Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-16 | cs.CL | ai-safety, cscl, preprint | E11 / R13 (95%) | - |
| LLMs Get Smarter from Targeted Synthetic Multilingual Data Andreas Stolcke, Arkajyoti Charaborty, Ishika Agarwal, Neha Gupta Published: 2026-08-16Area: cs.CLCitations: 32 Tags: ai-safety, cscl, preprint | 2026-08-16 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (90%) | 32 |
| When Stories Evolve: Benchmarking LLM Storytelling Across Agent Architectures in Open-Ended World Simulations Ka Man Yan, Sixuan Li, Xueai Li, Ying Li Published: 2026-08-16Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-16 | cs.CL | ai-safety, cscl, preprint | E14 / R12 (91%) | - |
| Are LLMs Safe Beyond Text: Do Emojis Expose Gaps in Safety Evaluation M P V S Gopinadh Published: 2026-08-15Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-08-15 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E7 / R6 (94%) | 12 |
| Gated Against One Model, Open to the Next: Option-Only Solvability in Legal Multiple-Choice Benchmarks Volodymyr Ovcharov Published: 2026-08-15Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-15 | cs.CL | ai-safety, cscl, preprint | E9 / R6 (93%) | - |
| Handoff-H1: An Orchestrated Vision-Agent System for Material Quantity Takeoff from Construction Blueprints Bruno Chicelli, Felipe Lemos, Henrique Alves, Jan Baryla Published: 2026-08-15Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-15 | cs.CL | ai-safety, cscl, preprint | E8 / R8 (94%) | - |
| Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models Allan Hanbury, Terra Blevins, Varvara Arzt Published: 2026-08-15Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-15 | cs.CL | ai-safety, cscl, preprint | E16 / R8 (90%) | - |
| Logical Embeddings for Argument Analysis Leander Heldring, Santiago Torres Published: 2026-08-15Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-15 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (92%) | - |
| RamseyGadgets: A Graph Construction Dataset for LLMs Deepak Pandita, Zohair Raza Hassan Published: 2026-08-15Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-15 | cs.CL | ai-safety, cscl, preprint | E14 / R8 (91%) | - |
| When AI Rewrites, Classifiers Relax: Uncertainty-Aware Sentiment Analysis on Sarcastic and AI-Paraphrased Social Text Shresth Shroff Published: 2026-08-15Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-15 | cs.CL | ai-safety, cscl, preprint | E11 / R8 (94%) | - |
| ASSERT: A Measurement Pipeline for GenAI Audits Abhinav Palia, Chad Atalla, Dan Vann, Emily Sheng Published: 2026-08-14Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-14 | cs.CL | ai-safety, cscl, preprint | E9 / R8 (91%) | - |
| How Much Do Legal RAG Systems Still Hallucinate? Domenico Bianculli, Sallam Abualhaija, Souvick Das Published: 2026-08-14Area: cs.CLCitations: 36 Tags: ai-safety, cscl, preprint | 2026-08-14 | cs.CL | ai-safety, cscl, preprint | E15 / R8 (96%) | 36 |