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 |
|---|---|---|---|---|---|
| When RAG Fails to Equalize: Geo-bias in Factual Question Answering over Public Companies Abhinav Havaldar, Enrico Santus Published: 2026-08-26Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-26 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (93%) | - |
| Why RAGs Hallucinate: Penalty-Aware Evaluation of Retrieval-Augmented Generation Systems with Knowledge-Gap Canaries Alden Do Rosario, Felipe Pires, Hussein Younes Published: 2026-08-26Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-08-26 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E11 / R9 (93%) | 12 |
| A Primer on Computational Semantics for Artificial Intelligence Systems Casey Kennington Published: 2026-08-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-25 | cs.CL | ai-safety, cscl, preprint | E14 / R10 (94%) | - |
| Belief Cascades Drive Persuasion in LLM Agent Networks Chien-Sheng Wu, Genglin Liu, Haoyi Qiu, Kung-Hsiang Huang Published: 2026-08-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-25 | cs.CL | ai-safety, cscl, preprint | E17 / R17 (97%) | - |
| DataKernelBench: Can LLMs Optimize Database Queries on GPUs? Andrea Giovannini, Corey Lammie, Gokul Karthik Kumar, Katja Hose Published: 2026-08-25Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-25 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (91%) | 15 |
| DataKernelBench: Can LLMs Optimize Database Queries on GPUs? Andrea Giovannini, Corey Lammie, Gokul Karthik Kumar, Katja Hose Published: 2026-08-25Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-25 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (93%) | 15 |
| Does Fine-Tuning Undo Activation Steering? Behavioural Recovery Without Weight-Edit Reversal Alina Miron, Allan Tucker, Philipp E. Glass, Yongmin Li Published: 2026-08-25Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-08-25 | cs.CL | ai-safety, cscl, preprint | E9 / R6 (94%) | 12 |
| FARCA: Fact-Aligned Reliability-Aware Credit Assignment for Reinforcement Learning with Factual Supervision Qiming Xie, Rui Xia, Wenjie Zheng, Xiangqing Shen Published: 2026-08-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-25 | cs.CL | ai-safety, cscl, preprint | E14 / R8 (89%) | - |
| 'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection Fawzia Zehra, Kara-Isitt, Sonal Khosla, Stephen Swift Published: 2026-08-25Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-25 | cs.CL | ai-safety, cscl, preprint | E14 / R8 (95%) | 15 |
| HealthBench-Psych: A Mental Health Subset of OpenAI's HealthBench Jasreen Multani, Jill Noorily, John Torous, Julian Herpertz Published: 2026-08-25Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-25 | cs.CL | ai-safety, cscl, preprint | E13 / R10 (94%) | 15 |
| PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understanding Davood Rafiei, Md Mahadi Hasan Nahid Published: 2026-08-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-25 | cs.CL | ai-safety, cscl, preprint | E15 / R14 (93%) | - |
| Reading Is Not Using: Retrieval, Judgment, and the Design of AI Financial Research Workflows Miao Liu, Zhizhe Liu Published: 2026-08-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-25 | cs.CL | ai-safety, cscl, preprint | - | - |
| SAGE: From Direct Answering to Evidence-Grounded Inference for Chinese Ancient Document Understanding Bin Li, Meng Fang, Xiangyang Xue, Xuan Luo Published: 2026-08-25Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-25 | cs.CL | ai-safety, cscl, preprint | E8 / R7 (95%) | 15 |
| SelfGraphRAG: Bridging the Supervision Gap in Graph-Based RAG with Synthetic QA Generation Ben Lagnese, Manas Gaur Published: 2026-08-25Area: cs.CLCitations: 20 Tags: ai-safety, cscl, preprint | 2026-08-25 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (92%) | 20 |
| SENSESHIFT: Continuous Sentiment-Controlled Text Generation via Encoder-based Mask Infilling Emmanouil Karystinaios, Markus Frohmann, Markus Schedl, Navid Rekabsaz Published: 2026-08-25Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-25 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (93%) | 15 |
| The RAT: A Unified Bayesian Model for RAG Evaluation Felix Matthias Saaro, Jan Deriu, Mark Cieliebak, Pius von D盲niken Published: 2026-08-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-08-25 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | - | - |
| Unsupervised Post-Training of Foundation Models: A Survey Aiwei Liu, Cehao Yang, Hui Xiong, Huizai Yao Published: 2026-08-25Area: cs.CLCitations: 91 Tags: ai-safety, cscl, preprint | 2026-08-25 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (93%) | 91 |
| Unsupervised Post-Training of Foundation Models: A Survey Aiwei Liu, Cehao Yang, Hui Xiong, Huizai Yao Published: 2026-08-25Area: cs.CLCitations: 78 Tags: ai-safety, cscl, preprint | 2026-08-25 | cs.CL | ai-safety, cscl, preprint | E12 / R11 (92%) | 78 |
| When Less Is More: An Empirical Study of Minimal Responses in Counseling Dialogues and the Behavior of LLMs Zhiyang Qi Published: 2026-08-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-25 | cs.CL | ai-safety, cscl, preprint | E18 / R9 (93%) | - |
| AraDetox: A Multi-Dialect Arabic Detoxification Dataset Mo El-Haj Published: 2026-08-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-24 | cs.CL | ai-safety, cscl, preprint | - | - |
| A Reranker for Orchestrating Heterogeneous Speech and Text Retrievers Inho Kim, Sumyeong Ahn Published: 2026-08-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-24 | cs.CL | ai-safety, cscl, preprint | E11 / R9 (92%) | - |
| Beyond Surface Cues: Disentangling Sociocultural Signals in Multilingual LLMs Stefan Feuerriegel, Tanzhou Liu, Yash Raj Shrestha, Yuanjun Feng Published: 2026-08-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-24 | cs.CL | ai-safety, cscl, preprint | - | - |
| Beyond Verdicts: A Graph-Based Analysis of Human and LLM Reasoning in Scientific Fact-Checking Abdul Ghafoor, Muhammad Arslan Manzoor, Yufang Hou Published: 2026-08-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-24 | cs.CL | ai-safety, cscl, preprint | - | - |
| Comparing Chunking and Embedding Strategies for Turkish RAG Systems Ahmet Tu臒rul Bayrak, Fatma Nur Korkmaz, Mustafa Serta莽 T眉rkel Published: 2026-08-24Area: cs.CLCitations: 24 Tags: ai-safety, cscl, preprint | 2026-08-24 | cs.CL | ai-safety, cscl, preprint | E15 / R10 (94%) | 24 |
| ConvergeFlow: Language Flow with Provable Convergence to Token Embeddings Changxiao Cai, Gen Li, Na Li, Yuchen Jiao Published: 2026-08-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-24 | cs.CL | ai-safety, cscl, preprint | - | - |
| Credal Large Language Models for Semantic Commitment under Uncertainty Fabio Cuzzolin, Shireen Kudukkil Manchingal, Sofiia Nikolenko Published: 2026-08-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-24 | cs.CL | ai-safety, cscl, preprint | - | - |
| Cross-Domain, Multi-Task Data-to-Text Generation without In-Domain Training Data Claire Gardent, Kun Efimov-Zhang, Yifei Song Published: 2026-08-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-24 | cs.CL | ai-safety, cscl, preprint | - | - |
| Cross-Domain, Multi-Task Data-to-Text Generation without In-Domain Training Data Claire Gardent, Kun Efimov-Zhang, Yifei Song Published: 2026-08-24Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-24 | cs.CL | ai-safety, cscl, preprint | E11 / R8 (95%) | 15 |
| Cross-lingual Biography Enrichment via Claim Extraction and Alignment Claire Gardent, Emil Sayilov, Yifei Song, Ziyang Chen Published: 2026-08-24Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-08-24 | cs.CL | ai-safety, alignment-training, cscl, preprint | E10 / R6 (95%) | - |
| Cross-lingual Biography Enrichment via Claim Extraction and Alignment Claire Gardent, Emil Sayilov, Yifei Song, Ziyang Chen Published: 2026-08-24Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-08-24 | cs.CL | ai-safety, alignment-training, cscl, preprint | - | - |