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 |
|---|---|---|---|---|---|
| Verifiable Self-Evolution for Open-Ended Dialogue Skills via Future-Feedback Prediction ChaoJin Zhao, Xuan Jiang Published: 2026-07-21Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-07-21 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (94%) | 12 |
| Automated Discovery Has No Universally Superior Harness Akshat Gupta, Alexander Lu, Gopala Anumanchipalli, Jermaine Lei Published: 2026-07-20Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-07-20 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (91%) | 15 |
| DeLIVeR: Decomposed Learning for Information-grounded Veracity Recognition via Reinforced Knowledge Graph Exploration Cong Hoan Nguyen, Hieu Minh Duong, Long Nguyen, Thomas Hoang Published: 2026-07-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-20 | cs.CL | ai-safety, cscl, preprint | E19 / R14 (90%) | - |
| For What Reason? Interpreting Models' Encoding of Causation and Antithesis Abhidip Bhattacharyya, Shira Wein Published: 2026-07-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-20 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (91%) | - |
| How Does Alignment Tuning Shape Representations of Sycophancy and Related Cue-Induced Biases in LLMs? Bernhard Sch枚lkopf, Florent Draye, Prakhar Gupta, Terry Jingchen Zhang Published: 2026-07-20Area: cs.CLCitations: 15 Tags: ai-safety, alignment-training, cscl, preprint | 2026-07-20 | cs.CL | ai-safety, alignment-training, cscl, preprint | E15 / R12 (95%) | 15 |
| Multilingual Sentence Embeddings for Linguistic-Integrated Reliability Audit Ji Yoon Jung, Matthias von Davier, Ummugul Bezirhan Published: 2026-07-20Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-07-20 | cs.CL | ai-safety, cscl, preprint | E8 / R8 (91%) | 15 |
| Oracle Gap and Signal Fidelity: A Fixed-Pool Diagnostic for Test-Time Collaboration Jie Hu Published: 2026-07-20Area: cs.CLCitations: 1 Tags: ai-safety, cscl, preprint | 2026-07-20 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (95%) | 1 |
| Relay-Bench: Evaluating LLMs on Multi-Domain Reasoning Chains Liam Swayne Published: 2026-07-20Area: cs.CLCitations: 54 Tags: ai-safety, cscl, preprint | 2026-07-20 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (90%) | 54 |
| Structured Output Collapses Answer Diversity Across 44 Language Models Tapan Parikh Published: 2026-07-20Area: cs.CLCitations: 11 Tags: ai-safety, cscl, preprint | 2026-07-20 | cs.CL | ai-safety, cscl, preprint | E9 / R7 (89%) | 11 |
| The Story Shapes the Agent: Narrative Priors in LLM Behavior James Lester, Shashank Srivastava, Yixuan Wang Published: 2026-07-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-20 | cs.CL | ai-safety, cscl, preprint | E14 / R9 (94%) | - |
| Zero Hallucination, by Construction: Hallucination-Aware Layered Oversight for Trustworthy Enterprise AI Alexandru Preda, Bogdan Raduta, Horia Velicu, Serban Chiricescu Published: 2026-07-20Area: cs.CLCitations: 9 Tags: ai-safety, cscl, preprint | 2026-07-20 | cs.CL | ai-safety, cscl, preprint | E10 / R10 (89%) | 9 |
| Auditing Question-Order Effects in Large Language Models with the QQ Equality: Mechanism Characterization and a Saturation Caveat Pilsung Kang Published: 2026-07-19Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-07-19 | cs.CL | ai-safety, cscl, preprint | E6 / R5 (94%) | 15 |
| Debate-on-Graph: Reliable and Adaptive Reasoning of Large Language Model on Uncertain Knowledge Graph Peiji Yu, Tianxing Wu, Xin Chen Published: 2026-07-19Area: cs.CLCitations: 43 Tags: ai-safety, cscl, preprint | 2026-07-19 | cs.CL | ai-safety, cscl, preprint | E9 / R9 (91%) | 43 |
| JOR-Bench: Japanese Operations Research Benchmarks for Large Language Models Yuu Jinnai Published: 2026-07-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-18 | cs.CL | ai-safety, cscl, preprint | E16 / R14 (92%) | - |
| Real-World Evaluation of an AI Agent Drafting Translational Impact Summaries Amber E. Osterholt, Bailee Rue, Bethany C. Bray, Krishna R. Patel Published: 2026-07-18Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-07-18 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E10 / R8 (89%) | 15 |
| Real-World Evaluation of an AI Agent Drafting Translational Impact Summaries Amber E. Osterholt, Bailee Rue, Bethany C. Bray, Krishna Riteshkumar Patel Published: 2026-07-18Area: cs.CLCitations: 16 Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-07-18 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E14 / R16 (90%) | 16 |
| Trace-Based On-Policy Distillation for Masked Diffusion Language Models Chenhao Yuan, Haolin Ren, Jun Zhao, Kang Liu Published: 2026-07-18Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-07-18 | cs.CL | ai-safety, cscl, preprint | E11 / R7 (94%) | 15 |
| CAMMAR: Culture-Aware Matryoshka for Metaphorical Arabic Representations Alfonso Ortega del Puente, Suzan Awinat Published: 2026-07-17Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-07-17 | cs.CL | ai-safety, cscl, preprint | E8 / R7 (90%) | 15 |
| Candidate Attended Dialogue State Tracking Using BERT John Chan, Junyuan Zheng, Onkar Salvi Published: 2026-07-17Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-07-17 | cs.CL | ai-safety, cscl, preprint | E11 / R8 (93%) | 15 |
| Committed Before Reasoning: Behavioral Reproduction and Preliminary Activation-Level Evidence of Answer Pre-Commitment in an Open-Weight LLM Heejin Jo Published: 2026-07-17Area: cs.CLCitations: 1 Tags: ai-safety, cscl, preprint | 2026-07-17 | cs.CL | ai-safety, cscl, preprint | E6 / R5 (92%) | 1 |
| Conditional Reliability of Toxicity Signals for Multilingual and Code-Mixed Abuse Detection Arnab Mallick, Harmesh Rana, Indraveni Chebolu, Rohan Singh Published: 2026-07-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-17 | cs.CL | ai-safety, cscl, preprint | E11 / R9 (93%) | - |
| DECODEM: Data Extraction from Corporate Organizational Documents via Enhanced Methods Jens Frankenreiter Published: 2026-07-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-17 | cs.CL | ai-safety, cscl, preprint | E6 / R5 (92%) | - |
| DECODEM: Data Extraction from Corporate Organizational Documents via Enhanced Methods Jens Frankenreiter Published: 2026-07-17Area: cs.CLCitations: 39 Tags: ai-safety, cscl, preprint | 2026-07-17 | cs.CL | ai-safety, cscl, preprint | E13 / R12 (90%) | 39 |
| Frontier AI performance across the business disciplines: a case-grounded benchmark of knowledge work and analytical reasoning Ajay Patel, Chris Callison-Burch, Karim Lakhani, Kartik Hosanagar Published: 2026-07-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-17 | cs.CL | ai-safety, cscl, preprint | E11 / R8 (92%) | - |
| Frontier AI performance across the business disciplines: a case-grounded benchmark of knowledge work and analytical reasoning Ajay Patel, Chris Callison-Burch, Karim Lakhani, Kartik Hosanagar Published: 2026-07-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-17 | cs.CL | ai-safety, cscl, preprint | E15 / R16 (91%) | - |
| Induction in Both Directions: A Mechanistic Analysis of In-Context Learning in Masked Diffusion Language Models Andy Catruna, Emilian Radoi Published: 2026-07-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-17 | cs.CL | ai-safety, cscl, preprint | E9 / R8 (91%) | - |
| Induction in Both Directions: A Mechanistic Analysis of In-Context Learning in Masked Diffusion Language Models Andy Catruna, Emilian Radoi Published: 2026-07-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-17 | cs.CL | ai-safety, cscl, preprint | E9 / R7 (92%) | - |
| Loop the Loopies! Bryan Dai, Joey Zhou, Ran Tao, Xinyu Yang Published: 2026-07-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-17 | cs.CL | ai-safety, cscl, preprint | E19 / R15 (90%) | - |
| Loop the Loopies! Bryan Dai, Joey Zhou, Ran Tao, Xinyu Yang Published: 2026-07-17Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-07-17 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (91%) | 15 |
| On the Structure of Address in Multi-Party Dialogue: From Discrete Labels to Continuous Levels Divesh Lala, Koji Inoue, Taiga Mori, Tatsuya Kawahara Published: 2026-07-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-17 | cs.CL | ai-safety, cscl, preprint | E21 / R18 (94%) | - |