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 |
|---|---|---|---|---|---|
| TAF-MED: Multi-Turn Safety Refusal Collapse in LLMs Under Declared Self-Treatment Intent Raphael Schmitt, Waleed Jamil Published: 2026-08-10Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-10 | cs.CL | ai-safety, cscl, preprint | E12 / R6 (92%) | 15 |
| TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Research Ability Adarsh Kumarappan, David Woodruff, Dimitris Paparas, Ernest van Wijland Published: 2026-08-10Area: cs.CLCitations: 36 Tags: ai-safety, cscl, preprint | 2026-08-10 | cs.CL | ai-safety, cscl, preprint | E9 / R7 (90%) | 36 |
| TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Research Ability Adarsh Kumarappan, David Woodruff, Dimitris Paparas, Ernest van Wijland Published: 2026-08-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-10 | cs.CL | ai-safety, cscl, preprint | - | - |
| Temporal Misgrounding in Legal RAG: A Versioned-Corpus Benchmark for French Tax Law Daniel Guez, Laurent Fabre, Rose Cymbler Published: 2026-08-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-10 | cs.CL | ai-safety, cscl, preprint | - | - |
| The Announcement Carries the Cue: Markup, Boundaries, and the Notation of Pre-Training Corpora E. M. Freeburg Published: 2026-08-10Area: cs.CLCitations: 79 Tags: ai-safety, cscl, preprint | 2026-08-10 | cs.CL | ai-safety, cscl, preprint | E10 / R6 (92%) | 79 |
| When Confidence Fails: Overconfidence in LLMs under Uncertainty and Missing Clinical Information Adnan Mahmood, Fahmida Islam, Maryam Tahermazandarani, Quan Z. Sheng Published: 2026-08-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-10 | cs.CL | ai-safety, cscl, preprint | E12 / R8 (90%) | - |
| ZetaGPT: A Reference Implementation of Positional--Encoding--Free State--Space--Attention Language Models R贸is铆n Luo Published: 2026-08-10Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-10 | cs.CL | ai-safety, cscl, preprint | - | - |
| Beyond Tables: Doc2DB-Bench for Relationally Faithful Document-to-Database Construction Jiayang Wang, Jiazhuo Chen, Nan Tang, Zhengxuan Zhang Published: 2026-08-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-09 | cs.CL | ai-safety, cscl, preprint | E9 / R6 (92%) | - |
| Calling the Bluff: Detecting Ever-Shifting Harmful Chat Dialogue via Ordered Reasoning Chain Regularization Haojie Yu, Jie Huang, Junjie Wang, Mingyang Li Published: 2026-08-09Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-09 | cs.CL | ai-safety, cscl, preprint | E12 / R9 (92%) | - |
| Can We Optimize the Performance-Carbon Emission Break-Even Point?: The Quest for Greener LLMs Kripabandhu Ghosh, Sourav Das, Tanmay Joshi Published: 2026-08-09Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-09 | cs.CL | ai-safety, cscl, preprint | E12 / R6 (94%) | 15 |
| Deployable Per-Instance Multi-Layer Activation Steering for Large Language Models Alfan Farizki Wicaksono, Muhammad Faishal Adly Nelwan Published: 2026-08-09Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-08-09 | cs.CL | ai-safety, cscl, preprint | E8 / R7 (93%) | 45 |
| Enhancing Scientific Named Entity Recognition via Large Language Models: A Type-driven Multi-task Learning Approach Chengzhi Zhang, Heng Zhang, Tong Bao, Yi Zhao Published: 2026-08-09Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-09 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (90%) | 15 |
| Hidden Language Consistency Phenomena in Reasoning LLMs Kelly Marchisio, Muhammad Ali Shafique Published: 2026-08-09Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-08-09 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (92%) | 45 |
| LibraSpec: Dynamic Diffusion-Based Speculative Decoding via Marginal-Gain-Driven Optimization Junlin Lv, Kevin S. Zhou, Xike Xie, Yuan Feng Published: 2026-08-09Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-08-09 | cs.CL | ai-safety, cscl, preprint | E8 / R8 (89%) | 45 |
| Mitigating Gender Bias in English to Romanian Machine Translation Ioana Grigore, Sergiu Nisioi Published: 2026-08-09Area: cs.CLCitations: 19 Tags: ai-safety, cscl, preprint | 2026-08-09 | cs.CL | ai-safety, cscl, preprint | E11 / R7 (96%) | 19 |
| A Grounded and Decomposed Framework for Relation-Level Hallucination Evaluation in Abstractive Summarization Kali Prasad Vittala, Naman Kabadi, Praveen Kumar Katwe, Rakesh Chandra Balabantaray Published: 2026-08-08Area: cs.CLCitations: 22 Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-08-08 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E15 / R11 (95%) | 22 |
| Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives Bei Shi, Derek F. Wong, Jianhao Yan, Ka Hou Kam Published: 2026-08-08Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-08-08 | cs.CL | ai-safety, cscl, preprint | E7 / R5 (92%) | 45 |
| DialectS2S: End-to-End Speech Dialogue Modeling for Low-Resource Chinese Dialects Changming Xie, Jiajun Zhang, Jun Lin, Tianyu Peng Published: 2026-08-08Area: cs.CLCitations: 24 Tags: ai-safety, cscl, preprint | 2026-08-08 | cs.CL | ai-safety, cscl, preprint | E11 / R7 (92%) | 24 |
| Do Evaluation Metrics Detect Errors in Classical Chinese to English Translations? Andrew Schonebaum, Eric Bennett, Marine Carpuat, Osvaldo Quinjica Published: 2026-08-08Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-08-08 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E11 / R6 (91%) | 45 |
| Do Evaluation Metrics Detect Errors in Classical Chinese to English Translations? Andrew Schonebaum, Eric Bennett, Marine Carpuat, Osvaldo Quinjica Published: 2026-08-08Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-08-08 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E11 / R8 (91%) | 15 |
| NeuPAT: Neuron-aware Plasticity Allocation Tuning for Language-Preserving MLLMs Chen Wang, Jiayue Jin, Jing Liu, Jingwei Zhang Published: 2026-08-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-08 | cs.CL | ai-safety, cscl, preprint | E13 / R13 (89%) | - |
| Prompt Embedding Probes (PEP): Hallucination Detection in LLMs from Hidden States Valentin Malykh, Zakhar Mrykhin Published: 2026-08-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-08 | cs.CL | ai-safety, cscl, preprint | E8 / R7 (94%) | - |
| STEMMA: An Adversarial Multi-Agent Framework for Evaluating Self-Identity Consistency in LLMs Kanishka Jain, Nuthakki Siva Gopala Krishna Published: 2026-08-08Area: cs.CLCitations: 15 Tags: adversarial-robustness, ai-safety, cscl, preprint | 2026-08-08 | cs.CL | adversarial-robustness, ai-safety, cscl, preprint | E11 / R8 (94%) | 15 |
| Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Chenrui Fan, Ming Li, Soheil Feizi, Tianyi Zhou Published: 2026-08-08Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-08 | cs.CL | ai-safety, cscl, preprint | E14 / R14 (93%) | - |
| Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Chenrui Fan, Ming Li, Soheil Feizi, Tianyi Zhou Published: 2026-08-08Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-08-08 | cs.CL | ai-safety, cscl, preprint | E14 / R14 (93%) | 45 |
| An Agentic Hybrid Top-Down and Bottom-Up Approach to Knowledge Graph Generation Emma Jouffroy, Marc Palyart, Warren Jouanneau Published: 2026-08-07Area: cs.CLCitations: 27 Tags: ai-safety, cscl, preprint | 2026-08-07 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (92%) | 27 |
| Ask-E: An Environment for Calibrated Question Generation Ali Farhadi, Jae Sung Park, Sarah Pratt, Scott Geng Published: 2026-08-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-07 | cs.CL | ai-safety, cscl, preprint | E11 / R10 (90%) | - |
| Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Dianhai Yu, Guanqun Zhao, Junyuan Shang, Shuohuan Wang Published: 2026-08-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-07 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (89%) | - |
| Calibrating WEAT Against Anisotropy: ZCA Whitening as a Geometric Pre-Processing Step for Embedding Association Tests Jun Saiki, Seitaro Ono, Senna Ross Published: 2026-08-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-07 | cs.CL | ai-safety, cscl, preprint | E10 / R10 (91%) | - |
| CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG Cheoneum Park, Gyuwan Kim, Tao Yang Published: 2026-08-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-07 | cs.CL | ai-safety, cscl, preprint | - | - |