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 |
|---|---|---|---|---|---|
| DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning Hanlin Zhu, Hengyu Fu, Jason D. Lee, Jiantao Jiao Published: 2026-07-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-01 | cs.CL | ai-safety, cscl, preprint | E6 / R4 (97%) | - |
| Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation Abhinav Chinta, Amin Karbasi, Amin Saberi, Azalia Mirhoseini Published: 2026-07-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-01 | cs.CL | ai-safety, cscl, preprint | E7 / R4 (99%) | - |
| Faithful by Definition: Emotion Analysis via Natural Semantic Metalanguage Explications Erik Cambria, Frank Xing Published: 2026-07-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-01 | cs.CL | ai-safety, cscl, preprint | E7 / R4 (98%) | - |
| From Personas to Plot: Character-Grounded Multi-Agent Story Generation for Long-Form Narratives Aayush Aluru, Arjun Bahuguna, Chloe Ho, Kerry Luo Published: 2026-07-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-01 | cs.CL | ai-safety, cscl, preprint | E8 / R4 (94%) | - |
| Grounded Optimization: A Layered Engineering Framework for Reducing LLM Hallucination in Automated Personal Document Rewriting Adarsh Agrawal, Shashank Indukuri Published: 2026-07-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-01 | cs.CL | ai-safety, cscl, preprint | E8 / R5 (99%) | - |
| IsoSci: A Benchmark of Isomorphic Cross-Domain Science Problems for Evaluating Reasoning versus Knowledge Retrieval in LLMs Erchin Serpedin, Hasan Kurban, Samir Abdaljalil Published: 2026-07-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-01 | cs.CL | ai-safety, cscl, preprint | E10 / R4 (98%) | - |
| Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads Aryo Pradipta Gema, Beatrice Alex, Pasquale Minervini Published: 2026-07-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-01 | cs.CL | ai-safety, cscl, preprint | E9 / R4 (97%) | - |
| Measuring the Gap Between Human and LLM Research Ideas Arman Cohan, Yilun Zhao, Ziyu Chen Published: 2026-07-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-01 | cs.CL | ai-safety, cscl, preprint | E8 / R4 (96%) | - |
| MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering Dang Quang Thien Tran, Franck Dernoncourt, Koustava Goswami, Nedim Lipka Published: 2026-07-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-01 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (91%) | - |
| MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering Dang Quang Thien Tran, Franck Dernoncourt, Koustava Goswami, Nedim Lipka Published: 2026-07-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-01 | cs.CL | ai-safety, cscl, preprint | E6 / R4 (95%) | - |
| Reading Order Inference for Complex Document Layouts Berat Kurar-Barakat, Daria Vasyutinsky-Shapira, Gal Grudka, Iddo Hakim Published: 2026-07-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-01 | cs.CL | ai-safety, cscl, preprint | E9 / R5 (96%) | - |
| Recovering Input Text from Hidden States: Study of Gradient-Based Inversion of Decoder-Only Language Models Maciej Witold Majewski, Miko艂aj S艂owikowski Published: 2026-07-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-01 | cs.CL | ai-safety, cscl, preprint | E6 / R4 (96%) | - |
| Self-conditioned Flow Map Language Models via Fixed-point Flows Chanhyuk Lee, Floor Eijkelboom, Jaehoon Yoo, Jinwoo Kim Published: 2026-07-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-01 | cs.CL | ai-safety, cscl, preprint | E6 / R4 (95%) | - |
| The State-Prediction Separation Hypothesis Giovanni Monea, Kiant茅 Brantley, Nathan Godey, Yoav Artzi Published: 2026-07-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-01 | cs.CL | ai-safety, cscl, preprint | E8 / R4 (97%) | - |
| Towards Developing a Multimodal Chat Assistant for University Stakeholders: RAG-based Approach Abdullah Al Shafi, Md Abu Hanif Shaikh Published: 2026-07-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-01 | cs.CL | ai-safety, cscl, preprint | E8 / R5 (96%) | - |
| TurnNat: Automatic Evaluation of Turn-Taking Naturalness in Dyadic Spoken Dialogue Georgi Tinchev, Hao Zhang, Laureano Moro-Velazquez, Thomas Thebaud Published: 2026-07-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-07-01 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E7 / R5 (98%) | - |
| TurnNat: Automatic Evaluation of Turn-Taking Naturalness in Dyadic Spoken Dialogue Georgi Tinchev, Hao Zhang, Laureano Moro-Velazquez, Thomas Thebaud Published: 2026-07-01Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-07-01 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E11 / R9 (88%) | - |
| Can LLMs Imagine Moral Alternatives Beyond Binary Dilemmas? Haerin Shin, Han Seoyoung, Jaemin Cho, Jongchan Choi Published: 2026-06-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-06-30 | cs.CL | ai-safety, cscl, preprint | E7 / R4 (97%) | - |
| CHERRY: Compressed Hierarchical Experts with Recurrent Representational Yield Dohyeon Kwon, Youngjin Park Published: 2026-06-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-06-30 | cs.CL | ai-safety, cscl, preprint | E9 / R5 (96%) | - |
| Cross-lingual Relation Extraction with Large Language Models: Zero-Shot, Few-Shot, and Fine-Tuned Evaluation on Romanian Adrian Paschke, Ciprian-Octavian Truica, Dragos-Mitrut Vasile, Elena-Simona Apostol Published: 2026-06-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-06-30 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E7 / R4 (99%) | - |
| DigitalCoach: Communication and Grounding Gaps in Human and Agentic Computer Use Coaching Alane Suhr, Amy Pavel, Anya Ji, David M. Chan Published: 2026-06-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-06-30 | cs.CL | ai-safety, cscl, preprint | E9 / R4 (98%) | - |
| FinPersona-Bench: A Benchmark for Longitudinal Psychometric Stability of Autonomous Financial Agents Ayesha Gull, Fan Zhang, Liu, Muhammad Usman Safder Published: 2026-06-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-06-30 | cs.CL | ai-safety, cscl, preprint | E9 / R5 (96%) | - |
| Gated Multi-Graph Fusion via Graph Attention Networks for Alzheimer's Disease Detection Bin Wen, Jianwu Dang, Jinyu Li, Kai Li Published: 2026-06-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-06-30 | cs.CL | ai-safety, cscl, preprint | E9 / R7 (98%) | - |
| Harnessing the Latent Space: From Steering Vectors to Model Calibrators for Control and Trust Nishant Subramani Published: 2026-06-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-06-30 | cs.CL | ai-safety, cscl, preprint | E9 / R5 (96%) | - |
| Hate Speech Detection in Turkish and Arabic: A Comprehensive Study Arzucan 脰zg眉r, Berrin Yanikoglu, Elif Erol, G枚k莽e Uludo臒an Published: 2026-06-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-06-30 | cs.CL | ai-safety, cscl, preprint | E18 / R16 (94%) | - |
| Hate Speech Detection in Turkish and Arabic Languages: A Comprehensive Study Arzucan 脰zg眉r, Berrin Yanikoglu, Elif Erol, G枚k莽e Uludo臒an Published: 2026-06-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-06-30 | cs.CL | ai-safety, cscl, preprint | E11 / R5 (98%) | - |
| Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision Belinda Z. Li, Jacob Andreas, Laura Ruis, Zifan Carl Guo Published: 2026-06-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-06-30 | cs.CL | ai-safety, cscl, preprint | E8 / R4 (95%) | - |
| Probing Stylistic Appropriation using Large Language Models: An Evaluation Framework for Copyright Infringement under EU Law Chang Sun, Noah Scharrenberg Published: 2026-06-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-06-30 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E7 / R4 (96%) | - |
| Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs Arman Cohan, Avi Caciularu, Gabrielle Kaili-May Liu, Gal Yona Published: 2026-06-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-06-30 | cs.CL | ai-safety, cscl, preprint | E7 / R4 (96%) | - |
| Seeing Is Not Sharing: Some Vision-Language Models Overestimate Common Ground in Asymmetric Dialogue Albert Gatt, Massimo Poesio, Nan Li Published: 2026-06-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-06-30 | cs.CL | ai-safety, cscl, preprint | E6 / R4 (99%) | - |