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 |
|---|---|---|---|---|---|
| Repair Before Reinforce: Context-Augmented Knowledge Graph Reasoning for Multi-Hop Question Answering Niraj K. Jha, Tharaka D. Fonseka Published: 2026-09-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-10 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (94%) | - |
| Robust Multimodal Sentiment Analysis with Incomplete Modalities via Semantic-aware Completeness based Reconstruction Byunggill Joe, Han-Jun Choi, Jin Yea Jang, Saim Shin Published: 2026-09-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-10 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (94%) | - |
| Structural priors for data-efficient language learning Jonas Mayer Martins, Jonathan Lautenschlager, Lisa Beinborn, Yana Veitsman Published: 2026-09-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-10 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (93%) | - |
| SWRouter: Similarity-Contractive Window Routing for Multi-Turn Large Language Model Conversations Dawei Yin, Haoyi Xiong, Hengyi Cai, Jiamin Chen Published: 2026-09-10Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-10 | cs.CL | ai-safety, cscl, preprint | E12 / R9 (91%) | 15 |
| Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning Fanyu Meng, Jing Guan, Junlan Feng, Yachao Yang Published: 2026-09-09Area: cs.CLCitations: - Tags: adversarial-robustness, ai-safety, cscl, preprint | 2026-09-09 | cs.CL | adversarial-robustness, ai-safety, cscl, preprint | E9 / R7 (95%) | - |
| Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization Abhisek Dash, Ayan Majumdar, Ines Abdelaziz, Ingmar Weber Published: 2026-09-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-09 | cs.CL | ai-safety, cscl, preprint | E11 / R7 (93%) | - |
| Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization Abhisek Dash, Ayan Majumdar, Ines Abdelaziz, Ingmar Weber Published: 2026-09-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-09 | cs.CL | ai-safety, cscl, preprint | E9 / R7 (92%) | - |
| Data-Efficient Language Modeling: From Frontier Advancement to Principle-Guided Model Improvement Fujia Chen, Hongsheng Chen, Jincheng Mi, Junjie Yang Published: 2026-09-09Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-09 | cs.CL | ai-safety, cscl, preprint | E14 / R14 (91%) | 15 |
| Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training Dong-Jae Lee, Junmo Kim, Junwon Ko, Minchan Kwon Published: 2026-09-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-09 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (96%) | - |
| DiSCo: A Distribution-First Steering and Cultural Prior Evaluation Framework for Measuring Cultural Preference Bias in LLMs Bhuvan Arora, Devesh Saraogi, Dhruv Kumar, Sravya Varada Published: 2026-09-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-09-09 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E16 / R10 (94%) | - |
| Does Linguistic Structure Enrichment Enhance Coherence Assessment? Not With Current Architectures Carlos Caetano, Helena Maia, Luiz Pereira, Marina Bitencourt dos Santos Published: 2026-09-09Area: cs.CLCitations: 46 Tags: ai-safety, cscl, preprint | 2026-09-09 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (90%) | 46 |
| GANDR: Claim Auditing for Verifiable Legal Answer Generation Andreas Stathopoulos, Chen Qian, Lingfei Wu, Yimeng Wang Published: 2026-09-09Area: cs.CLCitations: 35 Tags: ai-safety, cscl, preprint | 2026-09-09 | cs.CL | ai-safety, cscl, preprint | E11 / R10 (92%) | 35 |
| IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier Blake Stenstrom, Brian Sathianathan, Charangan Vasantharajan Published: 2026-09-09Area: cs.CLCitations: 43 Tags: ai-safety, cscl, preprint | 2026-09-09 | cs.CL | ai-safety, cscl, preprint | E32 / R28 (91%) | 43 |
| Improving Cross-Lingual Token Representations by Adding a Pinch of SALT Guillem Ram铆rez Published: 2026-09-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-09 | cs.CL | ai-safety, cscl, preprint | E13 / R10 (90%) | - |
| Looped GPT-BERT: Trading Parameters for Computation in Small Language Modeling Hansen Liu, Hongtao Mu, Tao Ji, Tianyu Zhou Published: 2026-09-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-09 | cs.CL | ai-safety, cscl, preprint | E11 / R8 (93%) | - |
| Multilingual in Name Only? Cultural and Linguistic Weaknesses of LLMs in Urdu Abdul Rafae Khan, Farah Adeeba, Hassan Sajjad, Rajesh Bhatt Published: 2026-09-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-09 | cs.CL | ai-safety, cscl, preprint | E13 / R9 (94%) | - |
| RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding Fang Li Published: 2026-09-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-09 | cs.CL | ai-safety, cscl, preprint | E12 / R6 (91%) | - |
| When Auditors Fabricate: Batch-Size Degradation and Confident Hallucination in LLM Detection of Planted Document Contamination Karan Parekh, Medina Maloku, Sana Mhapsekar, Sanjana Pendyala Ravinder Published: 2026-09-09Area: cs.CLCitations: 23 Tags: ai-safety, cscl, preprint | 2026-09-09 | cs.CL | ai-safety, cscl, preprint | E10 / R6 (95%) | 23 |
| Which Medical Questions Deserve Rationales? Perturbation-Sensitive Selection for Robust QA Dayou Yu, Vasile Rus, Yuexin Wu Published: 2026-09-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-09 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (91%) | - |
| Auditable Emergency Triage for Maternal and Newborn Care in India Aman Dalmia, Amrita K Prasen, Anubhav Arora, Muhammed Afeer K Published: 2026-09-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-08 | cs.CL | ai-safety, cscl, preprint | E8 / R8 (94%) | - |
| Do New Attention Mechanisms Actually Fix Attention Sinks at Million-Token Context? Samaanah Abdus Salam, Sara Rizwan Published: 2026-09-08Area: cs.CLCitations: 32 Tags: ai-safety, cscl, preprint | 2026-09-08 | cs.CL | ai-safety, cscl, preprint | E9 / R8 (93%) | 32 |
| Edu-QuRating: Multi-Dimensional Educational Data Curation with Distilled Pairwise Judgements Amy Waldock, Dominic Andrews, Meng Liu, Mohamed Huti Published: 2026-09-08Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-09-08 | cs.CL | ai-safety, cscl, preprint | E13 / R7 (92%) | 45 |
| Edu-QuRating: Multi-Dimensional Educational Data Curation with Distilled Pairwise Judgements Amy Waldock, Dominic Andrews, Meng Liu, Mohamed Huti Published: 2026-09-08Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-08 | cs.CL | ai-safety, cscl, preprint | E14 / R10 (92%) | 15 |
| Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablation Mark Stevenson, Mingzi Cao, Nikolaos Aletras, Xingyu Deng Published: 2026-09-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-08 | cs.CL | ai-safety, cscl, preprint | E7 / R5 (93%) | - |
| IGT @ FinMMEval 2026 Task 2: Question-Type Prompting with Targeted Extraction for Multilingual Financial QA Yuwen Chiu Published: 2026-09-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-08 | cs.CL | ai-safety, cscl, preprint | E13 / R11 (90%) | - |
| Measuring LLM Sycophancy under Sustained Multi-Turn Pressure Kangda Wei, Leyuan Tang, Ruihong Huang, Tianyu Jiang Published: 2026-09-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-08 | cs.CL | ai-safety, cscl, preprint | E12 / R11 (95%) | - |
| Performance of Clinical AI System and Physicians and Frontier Language Models in primary care diagnostics Aleksey Ropan, Andy Nkansah, Anna Kozlova, Hanna Plotnitskaya Published: 2026-09-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-08 | cs.CL | ai-safety, cscl, preprint | E9 / R6 (92%) | - |
| Same Values, Different Languages? From Multilingual Probing to Steering LLMs Toward Chinese Social Values Aishan Liu, Haoyu Lu, Jian Zhou, Kexin Xu Published: 2026-09-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-08 | cs.CL | ai-safety, cscl, preprint | E10 / R15 (95%) | - |
| The Audit Decides the Verdict: Instrument Effects Rival Demographic Bias in LLM Decision Audits Manikandan Ravikiran, Siddharth Vohra Published: 2026-09-08Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-09-08 | cs.CL | ai-safety, cscl, preprint | E13 / R12 (97%) | 12 |
| Tracing Stereotypes from Representation to Output in Multilingual LLMs Ariun-Erdene Tumurchuluun, Josef van Genabith, Koel Dutta Chowdhury, Pinzhen Chen Published: 2026-09-08Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-09-08 | cs.CL | ai-safety, cscl, preprint | E14 / R10 (93%) | 45 |