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 |
|---|---|---|---|---|---|
| Uncovering Uncontrolled Repetition through Residual Stream Dynamics Fanyu Meng, Haoran Gao, Li Sun, Sen Su Published: 2026-09-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-30 | cs.CL | ai-safety, cscl, preprint | E22 / R12 (89%) | - |
| Verbalized and Internal Probabilities Are Coupled in Large Language Models Jiaxuan Li, Masha Fedzechkina, Nick Foti, Russ Webb Published: 2026-09-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-30 | cs.CL | ai-safety, cscl, preprint | E8 / R5 (92%) | - |
| When a Kindergartener Solves Calculus: Measuring Capability Leakage in Role-Prompted Reasoning Models Kunat Pipatanakul, Pakhapoom Sarapat, Pittawat Taveekitworachai, Saksorn Ruangtanusak Published: 2026-09-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-30 | cs.CL | ai-safety, cscl, preprint | - | - |
| Where MLLMs Fail and Why: Causal Task Decomposition for Capability Failure Diagnosis Andrew Gallagher, Brian Potetz, Chun-Ta Lu, Howard Zhou Published: 2026-09-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-30 | cs.CL | ai-safety, cscl, preprint | E14 / R13 (91%) | - |
| Where's Waldo? Query-language Preference under Cross-lingual Knowledge Disparities Dayeon Ki, Ning Gao, Ruochen Zhang, Ryen W. White Published: 2026-09-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-30 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (93%) | - |
| Working Around the Compute Ceiling: Byte-Exact Memory in Galahad Makes LLM Reading a One-Time Cost LLM Reading a One-Time Cost Sietse Schelpe Published: 2026-09-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-30 | cs.CL | ai-safety, cscl, preprint | - | - |
| Zero-Compute Cross-Lingual Transferability Estimation Using Typological Feature Proxies Dalton Raphael Harmsen, Joaquin Vanschoren, Swier Garst, Thomas van Osch Published: 2026-09-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-30 | cs.CL | ai-safety, cscl, preprint | - | - |
| A Proposed Rubric for Evaluating Expressed Clinical Reasoning in Large Language Model Responses James T. Teo, Zhangshu Joshua Jiang, Zina Ibrahim Published: 2026-09-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-29 | cs.CL | ai-safety, cscl, preprint | E13 / R8 (96%) | - |
| A Proposed Rubric for Evaluating Expressed Clinical Reasoning in Large Language Model Responses James T. Teo, Zhangshu Joshua Jiang, Zina Ibrahim Published: 2026-09-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-29 | cs.CL | ai-safety, cscl, preprint | - | - |
| A Proposed Rubric for Evaluating Expressed Clinical Reasoning in Large Language Model Responses James T. Teo, Zhangshu Joshua Jiang, Zina Ibrahim Published: 2026-09-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-29 | cs.CL | ai-safety, cscl, preprint | E15 / R14 (96%) | - |
| Auditable Long-Term Memory: A Deterministic Retrieval Chain Measured at 479/475 of 500 on LongMemEval-S Christopher J. Chanhnourack Published: 2026-09-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-29 | cs.CL | ai-safety, cscl, preprint | - | - |
| Auditing Long-Term Memory Evaluation: Repeated Judging, Reader Variation, and Negative Controls Christopher J. Chanhnourack Published: 2026-09-29Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-09-29 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E10 / R7 (87%) | 12 |
| BaLEEN: Biasing with Latent Encoded Entities for Context-Aware ASR Chihiro Taguchi, Rujikorn Charakorn, Yotaro Kubo Published: 2026-09-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-29 | cs.CL | ai-safety, cscl, preprint | - | - |
| Beyond Oracle Communication: Benchmarking Interactive Intent Alignment Under Miscommunication and Evolving User Intent Daoan Zhang, Ke Xiao, Mengyuan Chao, Wei Xu Published: 2026-09-29Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-09-29 | cs.CL | ai-safety, alignment-training, cscl, preprint | E9 / R6 (91%) | - |
| BITEM at the NTCIR-19 R2C2 Task: Predicting Confidence from Agentic RAG Pipeline Signals Alexandre Flament, Esteban Gaillac, Julien Knafou, Luc Mottin Published: 2026-09-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-29 | cs.CL | ai-safety, cscl, preprint | - | - |
| Breaking Babel: A Self-Evolving Multi-Agent System for Long-Form Subtitle Translation Haibo Jin, Najmeh Sadoughi, Xinjie Li, Yang Liu Published: 2026-09-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-29 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (94%) | - |
| Breaking Babel: A Self-Evolving Multi-Agent System for Long-Form Subtitle Translation Haibo Jin, Najmeh Sadoughi, Xinjie Li, Yang Liu Published: 2026-09-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-29 | cs.CL | ai-safety, cscl, preprint | E8 / R7 (94%) | - |
| Compiling Learning Problems into Adaptation Programs for Language Models Brian Scassellati, Rebecca Ramnauth Published: 2026-09-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-29 | cs.CL | ai-safety, cscl, preprint | - | - |
| ContextAdapt: Evaluating Contextual Adaptation and Value Alignment in LLMs Mirco Musolesi, Olivia Macmillan-Scott Published: 2026-09-29Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-09-29 | cs.CL | ai-safety, alignment-training, cscl, preprint | E12 / R13 (94%) | - |
| Correct Answers, Invalid Traces: What Verifiable Grade-School Math Reveals About Chain-of-Thought Traces Durgesh Kalwar, Paarth Iyer, Pranabendu Misra, Ratish Puduppully Published: 2026-09-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-29 | cs.CL | ai-safety, cscl, preprint | - | - |
| Correct, Don't Delete: Mitigating Emergent Misalignment with Corrective Supervision Jacob Epifano Published: 2026-09-29Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-09-29 | cs.CL | ai-safety, alignment-training, cscl, preprint | - | - |
| DraftTrace: A Multi-View Analytics Environment for AI-Integrated Writing Divyansh Chandarana, Sandipan De, Vivek Gupta Published: 2026-09-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-29 | cs.CL | ai-safety, cscl, preprint | - | - |
| DuplexSpeechBench-Document Grounding: Benchmarking Document Grounding and Hallucinations in Voice Agents Dinesh Manocha, Nedim Lipka, Puneet Mathur, Zeyu Jin Published: 2026-09-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-29 | cs.CL | ai-safety, cscl, preprint | E16 / R12 (92%) | - |
| ER-JEPA: Experience Replay Improves Joint-Embedding Predictive Learning in Language Models Feng Lian, Jingnan Pu, Zi-En Fan Published: 2026-09-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-29 | cs.CL | ai-safety, cscl, preprint | - | - |
| Evaluating and Benchmarking the System One Model Jev Lorenz Sparrenberg, Rafet Sifa, Tobias Deu脽er Published: 2026-09-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-29 | cs.CL | ai-safety, cscl, preprint | - | - |
| Follow the Entities: A Corpus Map for Agentic Search Andrew Joohun Nam, Soyeong Jeong, Sujay Kumar Jauhar, Sung Ju Hwang Published: 2026-09-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-29 | cs.CL | ai-safety, cscl, preprint | - | - |
| Gender bias across LLMs is common and highly heterogeneous Edoardo Bolzoni, Valerio Capraro Published: 2026-09-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-29 | cs.CL | ai-safety, cscl, preprint | E15 / R10 (93%) | - |
| Gender bias across LLMs is common and highly heterogenous Edoardo Bolzoni, Valerio Capraro Published: 2026-09-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-29 | cs.CL | ai-safety, cscl, preprint | - | - |
| How Local Mixing Encodes Relative Position in Global NoPE Attention Beren Millidge, Cutter Dawes, Nick Alonso, Tom Figliolia Published: 2026-09-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-29 | cs.CL | ai-safety, cscl, preprint | - | - |
| It's Not What the Image Shows: Irrelevant Context Destabilises VLM Judges Without Informing Them Kinan Ibraheem, Lotem Peled-Cohen, Mahmoud Jabarin, Nagham Omar Published: 2026-09-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-29 | cs.CL | ai-safety, cscl, preprint | - | - |