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 |
|---|---|---|---|---|---|
| Beyond Detection: Ethical Foundations for Automated Dyslexic Error Attribution Debarati Chakraborty, Samuel Rose Published: 2026-04-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-02 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs C茅line Hudelot, Hippolyte Gisserot-Boukhlef, Nicolas Boizard, Pierre Colombo Published: 2026-04-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-02 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| Countering Catastrophic Forgetting of Large Language Models for Better Instruction Following via Weight-Space Model Merging Cheng Peng, Jieting Li Lu, Mengxian Lyu, Mengyuan Zhang Published: 2026-04-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-02 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (96%) | - |
| Development and multi-center evaluation of domain-adapted speech recognition for human-AI teaming in real-world gastrointestinal endoscopy Peiyao Fu, Pinghong Zhou, Quanlin Li, Ruijie Yang Published: 2026-04-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-04-02 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E4 / R2 (96%) | - |
| Goose: Anisotropic Speculation Trees for Training-Free Speculative Decoding Naoya Inoue, Phuong Minh Nguyen, Tao Jin Published: 2026-04-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-02 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| Grounded Token Initialization for New Vocabulary in LMs for Generative Recommendation Chengming Jiang, Chunnan Yao, Daiwei Chen, Fedor Borisyuk Published: 2026-04-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-02 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (93%) | - |
| ImplicitBBQ: Benchmarking Implicit Bias in Large Language Models through Characteristic Based Cues Abhijnan Chakraborty, Bhaskara Hanuma Vedula, Darshan Anghan, Ishita Goyal Published: 2026-04-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-02 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| LiveMathematicianBench: A Live Benchmark for Mathematician-Level Reasoning with Proof Sketches Baohao Liao, Hanze Dong, Jiang Bian, Linyang He Published: 2026-04-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-02 | cs.CL | ai-safety, cscl, preprint | E4 / R2 (96%) | - |
| Magic, Madness, Heaven, Sin: LLM Output Diversity is Everything, Everywhere, All at Once Harnoor Dhingra Published: 2026-04-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-02 | cs.CL | ai-safety, cscl, preprint | E6 / R4 (95%) | - |
| Neuro-RIT: Neuron-Guided Instruction Tuning for Robust Retrieval-Augmented Language Model Jaemin Kim, Jae O Lee, Seo Yeon Park, Sumyeong Ahn Published: 2026-04-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-02 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning Cangqi Zhou, Fanfan Wang, Rui Xia, Xiangqing Shen Published: 2026-04-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-02 | cs.CL | ai-safety, cscl, preprint | E7 / R3 (95%) | - |
| Reliable News or Propagandist News? A Neurosymbolic Model Using Genre, Topic, and Persuasion Techniques to Improve Robustness in Classification Benjamin Icard, C茅line Hudelot, G茅raud Faye, Guillaume Gadek Published: 2026-04-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-02 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (93%) | - |
| SAFE: Stepwise Atomic Feedback for Error correction in Multi-hop Reasoning Daeyong Kwon, Seung-won Hwang, Soyoung Yoon Published: 2026-04-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-02 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| The Expert Strikes Back: Interpreting Mixture-of-Experts Language Models at Expert Level Jae Hee Lee, Jeremy Herbst, Stefan Wermter Published: 2026-04-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-02 | cs.CL | ai-safety, cscl, preprint | E4 / R2 (94%) | - |
| Tracking the emergence of linguistic structure in self-supervised models learning from speech Charlotte Pouw, Gaofei Shen, Hosein Mohebbi, Marianne de Heer Kloots Published: 2026-04-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-02 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation Prakhar Bansal, Shivangi Agarwal Published: 2026-04-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-03 | cs.CL | ai-safety, cscl, preprint | E5 / R4 (94%) | - |
| Council Mode: Mitigating Hallucination and Bias in LLMs via Multi-Agent Consensus Shuai Wu, Xue Li, Yanna Feng, Yufang Li Published: 2026-04-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-03 | cs.CL | ai-safety, cscl, preprint | E6 / R4 (98%) | - |
| CresOWLve: Benchmarking Creative Problem-Solving Over Real-World Knowledge Anna Sotnikova, Antoine Bosselut, Daniil Yurshevich, Lonneke van der Plas Published: 2026-04-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-03 | cs.CL | ai-safety, cscl, preprint | E4 / R2 (98%) | - |
| Domain-Adapted Retrieval for In-Context Annotation of Pedagogical Dialogue Acts Bakhtawar Ahtisham, Jinsook Lee, Kirk Vanacore, Rene F. Kizilcec Published: 2026-04-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-03 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| Evolutionary Search for Automated Design of Uncertainty Quantification Methods Alexander Panchenko, Daniil Korbut, Elena Tutubalina, Mikhail Seleznyov Published: 2026-04-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-03 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (94%) | - |
| How Annotation Trains Annotators: Competence Development in Social Influence Recognition Aleksander Szcz臋sny, Aleksandra Sawczuk, Beata Bajcar, Grzegorz Chodak Published: 2026-04-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-03 | cs.CL | ai-safety, cscl, preprint | E6 / R3 (94%) | - |
| JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency Aichen Cai, Anmeng Zhang, Anyu Li, Bohua Cai Published: 2026-04-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-03 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation Chuang Zhou, Jin Chen, Lingfei Ren, Longhao Yang Published: 2026-04-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-03 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (98%) | - |
| One Model to Translate Them All? A Journey to Mount Doom for Multilingual Model Merging Asif Ekbal, Baban Gain, Trilok Nath Singh Published: 2026-04-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-03 | cs.CL | ai-safety, cscl, preprint | E6 / R2 (95%) | - |
| Querying Structured Data Through Natural Language Using Language Models Bunea Andrei-Alexandru, Hontan Valentin-Micu, Popovici Dan-Matei, Tantaroudas Nikolaos Dimitrios Published: 2026-04-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-03 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| R2-Write: Reflection and Revision for Open-Ended Writing with Deep Reasoning Bo Zhang, Chenliang Li, Ming Yan, Shaopeng Lai Published: 2026-04-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-03 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (95%) | - |
| Reliability Gated Multi-Teacher Distillation for Low Resource Abstractive Summarization Ankan Kumar Roy, Atia Haque Asha, Dipto Sumit, Farig Yousuf Sadeque Published: 2026-04-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-03 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (94%) | - |
| Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control Andrew Lee, Jie Zhang, Jing Shao, Lewen Yan Published: 2026-04-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-03 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (96%) | - |
| Verbalizing LLMs' assumptions to explain and control sycophancy Aryaman Arora, Dan Jurafsky, Desmond Ong, Diyi Yang Published: 2026-04-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-03 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (93%) | - |
| Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution Aswin RRV, Ben Zhou, Jacob Dineen, Zhikun Xu Published: 2026-04-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-04-03 | cs.CL | ai-safety, cscl, preprint | E5 / R3 (98%) | - |