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 |
|---|---|---|---|---|---|
| Learning the Arabic Dialect Continuum as a Continuous Space: A Regression Approach to Speaker Origin Prediction Adel Ammar, Bilel Benjdira, Mohamed Aziz Khadraoui, Skander Turki Published: 2026-07-22Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-22 | cs.CL | ai-safety, cscl, preprint | E8 / R7 (91%) | - |
| On the Systematic Challenges of Culturally Loaded Machine Translation: Dream of the Red Chamber as the Cultural Lens Jiayuan Di, Yiming Wang Published: 2026-07-22Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-07-22 | cs.CL | ai-safety, cscl, preprint | E19 / R17 (92%) | 15 |
| Overview of FinMMEval 2026 Task 1: Multilingual Financial Multiple-Choice Question Answering Dimitar Dimitrov, Fan Zhang, Georgi Georgiev, Haolun Wu Published: 2026-07-22Area: cs.CLCitations: 29 Tags: ai-safety, cscl, preprint | 2026-07-22 | cs.CL | ai-safety, cscl, preprint | E16 / R14 (92%) | 29 |
| Overview of FinMMEval 2026 Task 2: Multilingual Financial Short-Answer Question Answering Dimitar Dimitrov, Fan Zhang, Georgi Georgiev, Haolun Wu Published: 2026-07-22Area: cs.CLCitations: 31 Tags: ai-safety, cscl, preprint | 2026-07-22 | cs.CL | ai-safety, cscl, preprint | E39 / R23 (88%) | 31 |
| Reference-Free Evaluation of Reasoning in Open-Ended Question Answering Gregory E Dean, Guneet Singh Kohli, Maria Liakata, Michael Sejr Schlichtkrull Published: 2026-07-22Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-07-22 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E6 / R6 (94%) | 15 |
| Reinforcement Learning for Large Language Model Selective Evidence Adoption from Contaminated Retrieval Results Dongsheng Shi, Lichang Dai, Yanyu Chen, Yongyi Cui Published: 2026-07-22Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-07-22 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (93%) | 15 |
| Sentence Splitter: Uncovering Latent Factual Structure for Self-Supervised Learning Ahmad Pouramini, Mahsa Afsharizadeh Published: 2026-07-22Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-22 | cs.CL | ai-safety, cscl, preprint | E7 / R7 (92%) | - |
| SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Abdullin Amir, Baotian Hu, Barkova Maria, Bingwei Zhang Published: 2026-07-22Area: cs.CLCitations: 47 Tags: ai-safety, cscl, preprint | 2026-07-22 | cs.CL | ai-safety, cscl, preprint | E14 / R11 (94%) | 47 |
| SLPO: Scaling Latent Reasoning via a Surrogate Policy Runyang You, Wenjie Li, Yongqi Li, Zhiyuan Liu Published: 2026-07-22Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-22 | cs.CL | ai-safety, cscl, preprint | E15 / R14 (91%) | - |
| SLPO: Scaling Latent Reasoning via a Surrogate Policy Runyang You, Wenjie Li, Yongqi Li, Zhiyuan Liu Published: 2026-07-22Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-22 | cs.CL | ai-safety, cscl, preprint | E11 / R10 (90%) | - |
| Sound Probabilistic Safety Bounds for Large Language Models Alessandro Abate, Anne-Kathrin Schmuck, Mahdi Nazeri, Sadegh Soudjani Published: 2026-07-22Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-22 | cs.CL | ai-safety, cscl, preprint | E7 / R6 (91%) | - |
| The Maskability Index: Predicting Task-Objective Alignment in Pretrained Language Models Ahmad Pouramini, Mahsa Afsharzadeh Published: 2026-07-22Area: cs.CLCitations: 30 Tags: ai-safety, alignment-training, cscl, preprint | 2026-07-22 | cs.CL | ai-safety, alignment-training, cscl, preprint | E9 / R6 (91%) | 30 |
| TINY_SCHILLER: A Drop-In German Drama Corpus for Small Language Models Mark Schutera Published: 2026-07-22Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-07-22 | cs.CL | ai-safety, cscl, preprint | E16 / R14 (94%) | 15 |
| When Does Knowledge Distillation Hurt? Reliability-Aware Distillation for Low-Resource Language Summarization Ankan Kumar Roy Srizon, Atia Haque Asha, Dipto Sumit, Farig Sadeque Published: 2026-07-22Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-22 | cs.CL | ai-safety, cscl, preprint | E9 / R8 (93%) | - |
| Adaptive Capitulation: A Structural Failure Mode of LLM Responses in Vulnerability Contexts Eunna Lee Published: 2026-07-21Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-07-21 | cs.CL | ai-safety, cscl, preprint | E9 / R8 (94%) | 15 |
| AILQA: Evaluating AI-Driven Legal Question Answering Systems for the Indian Legal System Arnab Bhattacharya, Kripabandhu Ghosh, Noel Shallum, Shubham Kumar Mishra Published: 2026-07-21Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-21 | cs.CL | ai-safety, cscl, preprint | E14 / R13 (88%) | - |
| AutoJourn: Multi-Perspective Summarisation, Bias Detection and Bias Neutralisation for LLM-Generated News in Automated Journalism Ahmed Mosharafa, Georg Groh, Himel Ghosh Published: 2026-07-21Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-07-21 | cs.CL | ai-safety, cscl, preprint | E12 / R10 (88%) | 15 |
| Beyond Score Prediction: LLM-Based Essay Scoring and Feedback Generation via Reinforcement Learning with Rubric Rewards Bin Yang, Jiashuo Zhang, Teng Cao, Xuefeng Jin Published: 2026-07-21Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-21 | cs.CL | ai-safety, cscl, preprint | E9 / R8 (95%) | - |
| Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges Disheng Liu, Jing Li, Tuo Liang, Yu Yin Published: 2026-07-21Area: cs.CLCitations: 150 Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-07-21 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E15 / R12 (91%) | 150 |
| Copy Less, Ground More: Overcoming Repetitive Copying in Long-Context Reasoning via Evidence-Aware Reinforcement Learning Lizhe Fang, Tianyi Tang, Weizhou Shen, Yisen Wang Published: 2026-07-21Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-07-21 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (93%) | 15 |
| DAIS: Dependency-Aware Intermediate QA Supervision for Complex Reasoning Caiyue Xu, Dahai Hu, Ming Fan, Ting Liu Published: 2026-07-21Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-21 | cs.CL | ai-safety, cscl, preprint | E13 / R9 (92%) | - |
| Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA Aritran Piplai, Himanshu Tripathi, Shahram Rahimi, Shaswata Mitra Published: 2026-07-21Area: cs.CLCitations: 29 Tags: ai-safety, cscl, preprint | 2026-07-21 | cs.CL | ai-safety, cscl, preprint | E16 / R15 (91%) | 29 |
| Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs Alexander Manev Published: 2026-07-21Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-21 | cs.CL | ai-safety, cscl, preprint | E9 / R6 (93%) | - |
| LatentMT: Machine Translation with Latent Reasoning Chiyu Zhang, Muhammad Abdul-Mageed, Samar M. Magdy, Wei-Rui Chen Published: 2026-07-21Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-21 | cs.CL | ai-safety, cscl, preprint | E11 / R8 (93%) | - |
| MedDDC-Eval: Diagnosis-Decoupled Evaluation of Multi-Turn Medical Consultation Agents Guofeng Zhang, Huaiyi Fang, Jianwei Lv, Jinyao Liu Published: 2026-07-21Area: cs.CLCitations: 25 Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-07-21 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E7 / R6 (92%) | 25 |
| MedDDC-Eval: Diagnosis-Decoupled Evaluation of Multi-Turn Medical Consultation Agents Guofeng Zhang, Huaiyi Fang, Jianwei Lv, Jinyao Liu Published: 2026-07-21Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-07-21 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E9 / R8 (92%) | - |
| MIRA-Ev:A Benchmark for Granular Evidence Detection and Relational Reasoning in Clinical Exams Aitziber Atutxa, Ander Barrena, Iker De la Iglesia, Irune Urroz Garc铆a Published: 2026-07-21Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-07-21 | cs.CL | ai-safety, cscl, preprint | E13 / R11 (93%) | 15 |
| Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models Netanel Eliav Published: 2026-07-21Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-21 | cs.CL | ai-safety, cscl, preprint | E11 / R11 (96%) | - |
| Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoning Aixiu An, Andreas Fischer, Eloi Eynard, Jean Hennebert Published: 2026-07-21Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-07-21 | cs.CL | ai-safety, cscl, preprint | E12 / R6 (91%) | 45 |
| The Price of Reasoning: Cost-Quality Tradeoffs in Reinforcement Learning for Neural Machine Translation Aixiu An, Michael Jungo Published: 2026-07-21Area: cs.CLCitations: 16 Tags: ai-safety, cscl, preprint | 2026-07-21 | cs.CL | ai-safety, cscl, preprint | E12 / R7 (92%) | 16 |