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 |
|---|---|---|---|---|---|
| Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR Bingsen Chen, Boyan Li, Chenghao Yang, Chen Zhao Published: 2026-09-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-03 | cs.CL | ai-safety, cscl, preprint | E12 / R9 (90%) | - |
| Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR Bingsen Chen, Boyan Li, Chenghao Yang, Chen Zhao Published: 2026-09-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-03 | cs.CL | ai-safety, cscl, preprint | E12 / R10 (90%) | - |
| Shared circuits predict whether LLMs generalize across formats in arithmetic reasoning Andrea Gregor de Varda, Evelina Fedorenko, Jacob Andreas, Pengrui Han Published: 2026-09-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-03 | cs.CL | ai-safety, cscl, preprint | E17 / R8 (91%) | - |
| TabScope: Question-Adaptive Scope Selection for Table Question Answering Jianzhong Qi, Junhao Gan, Yuxiang Wang Published: 2026-09-03Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-09-03 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (91%) | 12 |
| </think> Doesn't Stop Reasoning: Analysis of Spurious CoT Termination Junmo Kim, Minchan Kwon, Seunghee Koh, Sunghyun Baek Published: 2026-09-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-03 | cs.CL | ai-safety, cscl, preprint | E14 / R11 (94%) | - |
| Towards Understanding Pause Token Fine-Tuning Dynamics: A Mode Retention Perspective Giho Lee, Jaehyeon Kim, Jimin Seo, Jungwoo Lee Published: 2026-09-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-03 | cs.CL | ai-safety, cscl, preprint | E3 / R11 (93%) | - |
| Translation as a Decision Space: A Multi-Agent Perspective on Low-Resource Dialect Generation Ahmet Zengin, Amro Najjar, Hasan Alkhder, Igor Tchappi Published: 2026-09-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-03 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (95%) | - |
| When Users Don't Ask: Benchmarking Context-Driven Memory Retrieval in Conversational Agents Wen-Yu Chang, Yun-Nung Chen Published: 2026-09-03Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-03 | cs.CL | ai-safety, cscl, preprint | E11 / R12 (93%) | - |
| You Really Didn't Get That? Benchmarking Social Pragmatic Inference for Indirect and Playful Chinese Online Comments Emma Jiren Wang, Ethan Z. Rong, Haichang Li, Junjie Ma Published: 2026-09-03Area: cs.CLCitations: 1 Tags: ai-safety, cscl, preprint | 2026-09-03 | cs.CL | ai-safety, cscl, preprint | E13 / R9 (93%) | 1 |
| Before the Script, Set the Stage: How Worldview Simulation Amplifies Psychologically Grounded Persuasion in Multi-Turn Jailbreaking Haoran Wang, Siyu Chen, Wei Xu, Xiaojian Li Published: 2026-09-02Area: cs.CLCitations: - Tags: adversarial-robustness, ai-safety, cscl, preprint | 2026-09-02 | cs.CL | adversarial-robustness, ai-safety, cscl, preprint | E12 / R8 (94%) | - |
| C$^{3}$T: Counterfactual Causal Reasoning for Sentiment Shifts in Social-Media Conversation Trees Atriya Sen, S M Rafiuddin Published: 2026-09-02Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-02 | cs.CL | ai-safety, cscl, preprint | E8 / R7 (90%) | 15 |
| DiffIE: Diffusion-based Open Information Extraction Konstantin Fedorov, Valentin Malykh Published: 2026-09-02Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-02 | cs.CL | ai-safety, cscl, preprint | E9 / R5 (92%) | 15 |
| DKL: Decoupled Knowledge Learning for Instruction-Tuned Language Models Dinesh Raghu, Gaurav Pandey, Jaydeep Sen, Kushagra Bhushan Published: 2026-09-02Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-02 | cs.CL | ai-safety, cscl, preprint | E14 / R13 (92%) | 15 |
| Do Large Language Models Capture the Diversity in their Training Data? Farzan Farnia, Youqi Wu Published: 2026-09-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-02 | cs.CL | ai-safety, cscl, preprint | E9 / R6 (94%) | - |
| From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution Chenpeng Wang, Jianhui Chen, Liangming Pan, Yuzhang Luo Published: 2026-09-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-02 | cs.CL | ai-safety, cscl, preprint | E11 / R9 (93%) | - |
| From Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in Black-Box LLMs Abhishek Mandal, Christopher Martin, Houssem Chatbri, Nabeel Kemal Published: 2026-09-02Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-09-02 | cs.CL | ai-safety, cscl, preprint | E19 / R16 (95%) | 12 |
| From Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in Black-Box LLMs Abhishek Mandal, Christopher Martin, Houssem Chatbri, Nabeel Kemal Published: 2026-09-02Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-09-02 | cs.CL | ai-safety, cscl, preprint | E17 / R16 (94%) | 12 |
| From Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in Black-Box LLMs Abhishek Mandal, Christopher Martin, Houssem Chatbri, Nabeel Kemal Published: 2026-09-02Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-02 | cs.CL | ai-safety, cscl, preprint | E18 / R46 (92%) | 15 |
| Language Models Can Control Their Own Attention Cicero Nogueira dos Santos, Huzama Ahmad, Namgyu Ho, Se-Young Yun Published: 2026-09-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-02 | cs.CL | ai-safety, cscl, preprint | E9 / R8 (94%) | - |
| MultiGhostBench: A Multilingual Benchmark for Long-Form LLM-Generated Text Attribution under Distribution Shifts Andrea Tagarelli, Anudeex Shetty, Jey Han Lau, Matteo Greco Published: 2026-09-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-02 | cs.CL | ai-safety, cscl, preprint | E20 / R13 (93%) | - |
| NE-R1: Enhancing Named Entity Recognition Model via Reinforcement Learning Hanmeng Liu, Hehan Li, LI Meifang, Liwei Qian Published: 2026-09-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-02 | cs.CL | ai-safety, cscl, preprint | E16 / R14 (92%) | - |
| OBJECTION! Lawyer Agents Mitigate Guilty Bias in Legal Judgment Prediction Jaehoon Jeong, Jay-Yoon Lee Published: 2026-09-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-02 | cs.CL | ai-safety, cscl, preprint | E10 / R6 (93%) | - |
| PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compilation Hong Phuc Pham, Jaehong Yoon, Yunhao Liu Published: 2026-09-02Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-02 | cs.CL | ai-safety, cscl, preprint | E12 / R10 (94%) | 15 |
| PolERo: Studying Political Evasion in Romanian Gabriel Stefan, Sergiu Nisioi Published: 2026-09-02Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-02 | cs.CL | ai-safety, cscl, preprint | E18 / R18 (93%) | 15 |
| Predict, Don't Iterate: Efficient Adaptive-Length Infilling for Diffusion Language Models Dongqi Fu, Hanghang Tong, Haobo Xu, Jingrui He Published: 2026-09-02Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-02 | cs.CL | ai-safety, cscl, preprint | E7 / R6 (93%) | 15 |
| SHELF: A Synthetic Harness for Multi-Task Bibliographic Benchmarking Michael J. Bommarito Published: 2026-09-02Area: cs.CLCitations: 42 Tags: ai-safety, cscl, preprint | 2026-09-02 | cs.CL | ai-safety, cscl, preprint | E8 / R7 (92%) | 42 |
| TaRA: Training-Aware Low-Rank Adaptation Initialization Eunhyeok Park, Taehyeon Kim Published: 2026-09-02Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-02 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (94%) | 15 |
| text2ql: Multi-Target Natural Language Querying via a Language-Agnostic Intermediate Representation Ritesh Kumar Published: 2026-09-02Area: cs.CLCitations: 19 Tags: ai-safety, cscl, preprint | 2026-09-02 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (92%) | 19 |
| Untangling the Mechanisms of Misleading Context in Medical Question Answering No茅mie Elhadad, Robin Linzmayer Published: 2026-09-02Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-02 | cs.CL | ai-safety, cscl, preprint | E9 / R6 (90%) | - |
| Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling Chen Zhi, Hang Song, Haozhan Shen, Jiajun Li Published: 2026-09-01Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-01 | cs.CL | ai-safety, cscl, preprint | E15 / R9 (94%) | 15 |