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 |
|---|---|---|---|---|---|
| ASTRA: Adaptive Semantic Tree Reasoning Architecture for Complex Table Question Answering Huajun Chen, Songze Li, Wen Zhang, Xiaoke Guo Published: 2026-04-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-10 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (96%) | - |
| BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation C茅line Hudelot, Emmanuel Malherbe, Hippolyte Gisserot-Boukhlef, Nicolas Boizard Published: 2026-04-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-04-10 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E5 / R3 (93%) | - |
| Case-Grounded Evidence Verification: A Framework for Constructing Evidence-Sensitive Supervision Daniel Truhn, Mahshad Lotfinia, Mehdi Joodaki, Soroosh Tayebi Arasteh Published: 2026-04-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-10 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (96%) | - |
| CONDESION-BENCH: Conditional Decision-Making of Large Language Models in Compositional Action Space Dongha Lee, Jinyoung Yeo, Minju Kim, Sungyong Park Published: 2026-04-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-10 | cs.CL | ai-safety, cscl, preprint | E4 / R2 (98%) | - |
| Do LLMs Follow Their Own Rules? A Reflexive Audit of Self-Stated Safety Policies Avni Mittal Published: 2026-04-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-10 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (96%) | - |
| GIANTS: Generative Insight Anticipation from Scientific Literature Anikait Singh, Chelsea Finn, Emma Brunskill, Ge Gao Published: 2026-04-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-10 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| Interactive ASR: Towards Human-Like Interaction and Semantic Coherence Evaluation for Agentic Speech Recognition Kai Yu, Peng Wang, Qinyuan Chen, Wupeng Wang Published: 2026-04-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-04-10 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E5 / R3 (95%) | - |
| Interactive ASR: Towards Human-Like Interaction and Semantic Coherence Evaluation for Agentic Speech Recognition Kai Yu, Peng Wang, Qinyuan Chen, Wupeng Wang Published: 2026-04-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-04-10 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E6 / R3 (97%) | - |
| Large Language Models Generate Harmful Content Using a Distinct, Unified Mechanism Boyi Wei, Hadas Orgad, Kaden Zheng, Martin Wattenberg Published: 2026-04-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-10 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (94%) | - |
| Litmus (Re)Agent: A Benchmark and Agentic System for Predictive Evaluation of Multilingual Models Avni Mittal, Monojit Choudhury, Sandipan Dandapat, Shanu Kumar Published: 2026-04-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-04-10 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E5 / R3 (93%) | - |
| Many-Tier Instruction Hierarchy in LLM Agents Benjamin Van Durme, Daniel Khashabi, Hongyuan Zhan, Jingyu Zhang Published: 2026-04-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-10 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| Many-Tier Instruction Hierarchy in LLM Agents Benjamin Van Durme, Daniel Khashabi, Hongyuan Zhan, Jingyu Zhang Published: 2026-04-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-10 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (94%) | - |
| MuTSE: A Human-in-the-Loop Multi-use Text Simplification Evaluator Adrian-Marius Dumitran, Angela-Liliana Dumitran, Gabriel Petre1, Rares-Alexandru Roscan Published: 2026-04-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-10 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| NyayaMind- A Framework for Transparent Legal Reasoning and Judgment Prediction in the Indian Legal System Arnab Bhattacharya, Balaramamahanthi Deepak Patnaik, Debtanu Datta, Noel Shallum Published: 2026-04-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-10 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (97%) | - |
| PerMix-RLVR: Preserving Persona Expressivity under Verifiable-Reward Alignment Jihwan Oh, Minchan Jeong, Murad Aghazada, Se-Young Yun Published: 2026-04-10Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-04-10 | cs.CL | ai-safety, alignment-training, cscl, preprint | E5 / R3 (95%) | - |
| Persona-E$^2$: A Human-Grounded Dataset for Personality-Shaped Emotional Responses to Textual Events Dong She, Haoran Tu, Haowu Zhou, HaoYang Li Published: 2026-04-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-10 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (95%) | - |
| RecaLLM: Addressing the Lost-in-Thought Phenomenon with Explicit In-Context Retrieval Kyle Whitecross, Negin Rahimi Published: 2026-04-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-10 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| Scalable High-Recall Constraint-Satisfaction-Based Information Retrieval for Clinical Trials Matching Chieh-Ju Chao, Cyrus Zhou, Monica S. Lam, Yilin Xu Published: 2026-04-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-10 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (98%) | - |
| Should We be Pedantic About Reasoning Errors in Machine Translation? Calvin Bao, Marine Carpuat Published: 2026-04-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-10 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (97%) | - |
| SPASM: Stable Persona-driven Agent Simulation for Multi-turn Dialogue Generation Guy Laban, Han Luo Published: 2026-04-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-10 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| Towards Linguistically-informed Representations for English as a Second or Foreign Language: Review, Construction and Application Weiwei Sun, Wenxi Li, Xihao Wang Published: 2026-04-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-10 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (94%) | - |
| ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models Chi-Yuan Hsiao, Guan-Ting Lin, Hsiao-Tsung Hung, Hung-yi Lee Published: 2026-04-11Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-11 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (96%) | - |
| CircuitSynth: Reliable Synthetic Data Generation Jiahao Sun, Thomas Lukasiewicz, Wei Dai, Zehua Cheng Published: 2026-04-11Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-11 | cs.CL | ai-safety, cscl, preprint | E6 / R4 (97%) | - |
| Computational Implementation of a Model of Category-Theoretic Metaphor Comprehension Fumitaka Iwaki, Hayato Saigo, Miho Fuyama, Tatsuji Takahashi Published: 2026-04-11Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-11 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| CoSToM:Causal-oriented Steering for Intrinsic Theory-of-Mind Alignment in Large Language Models Mengfan Li, Xuanhua Shi, Yang Deng Published: 2026-04-11Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-04-11 | cs.CL | ai-safety, alignment-training, cscl, preprint | E5 / R3 (95%) | - |
| ODUTQA-MDC: A Task for Open-Domain Underspecified Tabular QA with Multi-turn Dialogue-based Clarification Kun Zhou, Weijia Jia, Wenmian Yang, Yiquan Zhang Published: 2026-04-11Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-11 | cs.CL | ai-safety, cscl, preprint | E4 / R2 (98%) | - |
| Think in Sentences: Explicit Sentence Boundaries Enhance Language Model's Capabilities Yang Xu, Yongyuan Li, Zhichen Liu Published: 2026-04-11Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-11 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (96%) | - |
| Think in Sentences: Explicit Sentence Boundaries Enhance Language Model's Capabilities Yang Xu, Yongyuan Li, Zhichen Liu Published: 2026-04-11Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-11 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| Advancing Polish Language Modeling through Tokenizer Optimization in the Bielik v3 7B and 11B Series Adrian Gwo藕dziej, Krzysztof Ociepa, Krzysztof Wr贸bel, 艁ukasz Flis Published: 2026-04-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-12 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (97%) | - |
| Bridging Linguistic Gaps: Cross-Lingual Mapping in Pre-Training and Dataset for Enhanced Multilingual LLM Performance Aiti Aw, Chang Liu, Kui Wu, Muhammad Huzaifah Md Shahrin Published: 2026-04-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-12 | cs.CL | ai-safety, cscl, preprint | E4 / R3 (95%) | - |