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 |
|---|---|---|---|---|---|
| CreativeInstruct: Scalably Teaching LLMs to Balance Quality, Creativity, and Diversity Ananya Sahu, Elias Stengel-Eskin, Mohit Bansal Published: 2026-08-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-07 | cs.CL | ai-safety, cscl, preprint | - | - |
| Explicit, Not Longer: What Makes Epistemic Stance Survive Memory Compression Alex Kwon Published: 2026-08-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-07 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (90%) | - |
| FutureBridge: Token Selection Beyond Local Preference in Collaborative Decoding Guitao Cao, Hongbo Zhang, Hongzhen Zhang, Jing Ke Published: 2026-08-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-07 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (91%) | - |
| Georeferencing Non-Gazetteered Place Names using Biological Specimen Records Aneesha Fernando, Christopher B. Jones, Kristin Stock, Raj Prasanna Published: 2026-08-07Area: cs.CLCitations: 31 Tags: ai-safety, cscl, preprint | 2026-08-07 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (91%) | 31 |
| Geo-Spatial Concept Probing of Large Language Models: Abstraction, Compositionality, and Grounding Jose G Moreno, Karim Radouane, Lynda Tamine Published: 2026-08-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-07 | cs.CL | ai-safety, cscl, preprint | - | - |
| GPTKB 2.0: Browsing, Querying, and Auditing a Disambiguated LLM-Derived Knowledge Base Simon Razniewski, Tuan-Phong Nguyen, Yujia Hu Published: 2026-08-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-07 | cs.CL | ai-safety, cscl, preprint | E10 / R10 (90%) | - |
| Measuring Concept Content in Text from LLM Activations: ESG Evidence from Concept Vectors and Linear Probes Amirhossein Zohrehvand, Luc Hazenoot, Zhaochun Ren Published: 2026-08-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-07 | cs.CL | ai-safety, cscl, preprint | - | - |
| Natural Language Processing Psychometrics Edoardo Sebastiano De Duro, Emma Franchino, Massimo Stella Published: 2026-08-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-07 | cs.CL | ai-safety, cscl, preprint | - | - |
| PHASE-Tree: Modeling Character-State Evolution in Long-Horizon Role-Playing Dialogue Bo Tang, Feiyu Xiong, Jiajun Shen, Jianan Yang Published: 2026-08-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-07 | cs.CL | ai-safety, cscl, preprint | E27 / R25 (89%) | - |
| Progressive Content Refinement with Decaying Reward Joint LinUCB Pablo Loyola, Shion Ishikawa, Young-joo Chung, Yun Ching Liu Published: 2026-08-07Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-07 | cs.CL | ai-safety, cscl, preprint | E17 / R12 (92%) | 15 |
| Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Ruijie Hou, Yingming Li, Yueyang Jiao, Zhao Wang Published: 2026-08-07Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-08-07 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | - | - |
| Answer First, Reason Later: Commitment Order in Diffusion LLMs Hwiyeong Lee, Jaewon Sok, Jeongjae Park, Jewon Yeom Published: 2026-08-06Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-08-06 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (94%) | 45 |
| Benchmarking the Benchmarks: Evaluating Benchmarks for Conversational Agents Abigail Goldsteen, Noam Koren, Roy Bar-Haim Published: 2026-08-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-06 | cs.CL | ai-safety, cscl, preprint | E18 / R13 (89%) | - |
| Beyond "AI Language": The case for the idiolectal nature of LLM output Karolina Rudnicka, Thomas Stephan Juzek Published: 2026-08-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-06 | cs.CL | ai-safety, cscl, preprint | E21 / R19 (93%) | - |
| Beyond Sequence Order: Syntax-Informed Positional Embeddings for Transformers Haris Riaz, Hyungji Kim, Mihai Surdeanu Published: 2026-08-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-06 | cs.CL | ai-safety, cscl, preprint | E13 / R11 (90%) | - |
| Do AI Personas Grow? Analyzing and Benchmarking Personality Evolution in LLM Agents After Life Events Daling Wang, Ee-Peng Lim, Fiona Fui-Hoon Nah, Ming Wang Published: 2026-08-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-06 | cs.CL | ai-safety, cscl, preprint | E7 / R5 (91%) | - |
| Factorized Hypothesis Search for Evidence-to-Taxonomy Retrieval Ethan F. Wei, Lingfei Qian, Linhai Ma, V铆ctor Guti茅rrez-Basulto Published: 2026-08-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-06 | cs.CL | ai-safety, cscl, preprint | E7 / R6 (91%) | - |
| FormBharo: Designing and Evaluating a Voice Agent for Conversational Form Filling in Rural India Aman Dalmia, Jigar Doshi, Sanskriti Midha Published: 2026-08-06Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-06 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (92%) | 15 |
| Hierarchical Latent Prediction for Language Models Chang Shi, John Langford, Manan Tomar, Siddhartha Sen Published: 2026-08-06Area: cs.CLCitations: 25 Tags: ai-safety, cscl, preprint | 2026-08-06 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (94%) | 25 |
| Learning When to Trust via Selective Context Preference Optimization Junhao Liu, Lingdong Kong, Qing Wu, Wei Chow Published: 2026-08-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-06 | cs.CL | ai-safety, cscl, preprint | E9 / R6 (91%) | - |
| MACRO: Markov Chain Routing of Transformer Layers Abtin Pourhadi, Akylgali Aitaza, Paul Swoboda, Pawe艂 Batorski Published: 2026-08-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-06 | cs.CL | ai-safety, cscl, preprint | E8 / R7 (92%) | - |
| MameLoshnLM: Yiddish Language Model and Evaluation Benchmark Noah A. Smith, Omer Goldman, Reut Tsarfaty, Tomasz Limisiewicz Published: 2026-08-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-08-06 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E9 / R7 (91%) | - |
| Mitigating Scoring Bias in LLM-as-a-Judge via Random Number Generation Kiyoaki Shirai, Natthawut Kertkeidkachorn, Yuma Asato Published: 2026-08-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-06 | cs.CL | ai-safety, cscl, preprint | E17 / R14 (93%) | - |
| Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration Fang Fang, Hongrui Bao, Jinhan You, Shi Wang Published: 2026-08-06Area: cs.CLCitations: 37 Tags: ai-safety, cscl, preprint | 2026-08-06 | cs.CL | ai-safety, cscl, preprint | E12 / R9 (88%) | 37 |
| Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution Guanzhi Deng, Haibo Wang, Haochen Luo, Junlan Feng Published: 2026-08-06Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-06 | cs.CL | ai-safety, cscl, preprint | E10 / R10 (89%) | 15 |
| Scaling Inherently Interpretable Language Models Andreas Madsen, Aya Abdelsalam Ismail, Giang Nguyen, Guide Labs Team Published: 2026-08-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-06 | cs.CL | ai-safety, cscl, preprint | E7 / R6 (91%) | - |
| SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries Liming Zhu, Qing Liu, Wenjie Zhang, Xiaoyang Wang Published: 2026-08-06Area: cs.CLCitations: 1 Tags: ai-safety, cscl, preprint | 2026-08-06 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (93%) | 1 |
| Task-Conditional Flow Matching for Balanced Multilingual Text Embedding Adaptation Mayank Singh, Naren Kumar S, Tirth Bhatt Published: 2026-08-06Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-06 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (90%) | 15 |
| TradeVerse: A Longitudinal Benchmark of Political Negotiation in International Trade Amitangshu Dasgupta, Debodeep Banerjee Published: 2026-08-06Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-06 | cs.CL | ai-safety, cscl, preprint | E13 / R12 (88%) | - |
| A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination Dong Liu, Fei Ben, Fenghua Ling, Feng Liu Published: 2026-08-05Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-05 | cs.CL | ai-safety, cscl, preprint | - | - |